WO2021159167A1 - Systems and methods for creating and managing clinical decision support systems - Google Patents
Systems and methods for creating and managing clinical decision support systems Download PDFInfo
- Publication number
- WO2021159167A1 WO2021159167A1 PCT/AU2021/050055 AU2021050055W WO2021159167A1 WO 2021159167 A1 WO2021159167 A1 WO 2021159167A1 AU 2021050055 W AU2021050055 W AU 2021050055W WO 2021159167 A1 WO2021159167 A1 WO 2021159167A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cdss
- diagnosis
- data
- creation
- user
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Definitions
- the presently disclosed subject matter generally relates to the field of data processing.
- the present subject matter relates to a system and method for enabling users such as, but not limited to, health care providers to create, customize, and manage one or more clinical decision support systems.
- EMR electronic medical record
- EHR electronic health record
- the EMR systems may store or contain a patient’s medical history, diagnoses, medications, treatment plans, immunization dates, allergies, radiology images, and laboratory and test results. Further, the EMR systems may provide access to evidence-based tools that medical practitioners can use to make decisions about a patient’s care.
- Clinical decision support systems can provide staff, doctors, clinicians, nurses, patients or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, for improving health and health care.
- a CDSS normally includes a variety of tools to enhance decision-making in the clinical workflow. Some of these tools may include computerized alerts and reminders to care providers, medical practitioners, and patients; clinical guidelines; condition- specific order sets; focused patient data reports and summaries; documentation templates; diagnostic support, and contextually relevant reference information, among other tools.
- CDSS clinical decision support system
- the present disclosure provides a clinical decision support system (CDSS) creation and management system and method for enabling a health care provider like hospitals or a doctor to create and manage one or more clinical decision support systems including latest up-to-date medical information on their own.
- the CDSS can facilitate the physicians or other medical practitioners with latest up-to-date medical information to assist them in treating their patients in a better way.
- the CDSS creation and management system may be a standalone system. Further, the CDSS creation and management system may enable health care providers to create their own CDSS that can be connected or integrated with any EMR or EHR system of the health care providers.
- the CDSS creation and management system may also allow the health care providers to share their CDSS with other health care providers.
- An embodiment of the present disclosure provides a clinical decision support system (CDSS) creation and management system for enabling a user to create and manage one or more clinical decision support systems (CDSSs).
- the CDSS creation and management system (hereinafter may also be referred as a system) includes a storage module configured to store information comprising at least one of a CDSS global library, de-identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database; and a pharmacological database.
- the system also includes a display module configured to display one or more interfaces to enable the user to create, modify, and customize at least one clinical decision support system based on the information stored in the storage module.
- the system further includes an input/output module configured to receive at least one of a CDSS creation input from the user and data comprising at least one of de-identified data of one or more patients, treatments data, investigations data from at least one of a plurality of users and the user in real-time, wherein the CDSS global library is automatically created and updated based on the received data in real-time.
- the system also includes a CDSS creation module configured to create the at least one clinical decision support system for the user by using the information stored in the storage module in accordance with the received CDSS creation input.
- the system also includes an analysis module configured to perform self-analysis of usage of the CDSS creation and management system by the plurality of users and a plurality of CDSS associated with the plurality of users; and optimize performance of the CDSS creation and management system based on the self-analysis.
- the user and the plurality of users may include a health care provider.
- the non-limiting examples of the health care provider may include a hospital, a physician, a care taker, a nurse, a medical clinic, a paramedic, and a nursing home.
- the display module is further configured to enable the user and the plurality of users to access analysed data and the information stored in the storage module in a display format according to the requirement and preference of the user and the plurality of users.
- the CDSS creation and management system also includes an analysis module configured to: aggregate the data received from the plurality of data in real-time; automatically analyse the received data in real-time, wherein the analysed data is stored in the storage module; and update at least one of the clinical decision support system global library, the at least one CDSS, and the relational database based on the analysis in real-time.
- the analysis module may also be configured to perform self- analysis of usage of the CDSS creation and management system the plurality of users and a plurality of CDSS associated with the plurality of users; and optimize performance of the CDSS creation and management system based on the self-analysis.
- the CDSS creation and management system also includes a CDSS sharing module configured to enable the user to share the at least one CDSS with one or more users of the plurality of users.
- the CDSS creation and management system also includes a revenue generation module configured to generate revenues by presenting one or more targeted promotional media comprising advertisements on an associated CDSS interface of the plurality of users and the user based on a type of the plurality of users and the user.
- the CDSS creation and management system also includes a CDSS control module configured to enable the at least one CDSS to: at least one of connect or integrate with an electronic health record (EHR) system of the user; and provide a plurality of assist modes comprising a diagnosis mode, an investigation mode, and a treatment mode to an end user of the at least one CDSS.
- EHR electronic health record
- the CDSS control module is further configured to enable the at least one clinical decision support system to read data about at least one patient from the electronic health record system; determine at least one of a diagnosis and a differential diagnosis by analysing the data; display the at least one of a diagnosis and the differential diagnosis to the end user, wherein the end user is allowed to accept or reject the at least one of a diagnosis and the differential diagnosis, wherein on receiving a rejection input from the end user, the end user is prompted to enter another diagnosis in the at least one CDSS, wherein the another diagnosis is logged in to at least one of the EHR system and the CDSS; suggest a latest investigation based on s selection or input of at least one of the diagnosis, differential diagnosis, and another diagnosis by the end user; analyse results of the latest investigations to generate and display a final diagnosis about a condition of the at least one patient; perform risk factor analysis by comparing with the risk factor analysis data of the storage module to determine a total risk for the final diagnosis; determine a latest treatment protocol for the final
- the CDSS creation and management system further comprises an EHR Access Bridge compatible with the EHR system.
- Another embodiment of the present disclosure provides a method for enabling a user to create and manage one or more clinical decision support systems (CDSSs).
- the method includes enabling the user to access a clinical decision support system (CDSS) creation and management system via one or more interfaces on a computing device.
- the CDSS creation and management system includes a storage module containing information comprising at least one of a CDSS global library, de-identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database; and a pharmacological database.
- the method also includes receiving, by an input/output module of the CDSS creation and management system, a CDSS creation input via an input interface of the computing device to create at least one clinical decision support system.
- a CDSS creation module of the CDSS creation and management system may create the at least one clinical decision support system for the user by using the information stored in the storage module in accordance with the received CDSS creation input.
- the method also includes performing, by an analysis module, self-analysis of usage of the CDSS creation and management system by the plurality of users and a plurality of CDSS associated with the plurality of users.
- the method also includes optimizing, by the analysis module, performance of the CDSS creation and management system based on the self-analysis.
- the method includes enabling, by a display module of the CDSS creation and management system, the user and the plurality of users to access analysed data and the information stored in the storage module in a display format according to the requirement and preference of the user and the plurality of users.
- the method also includes aggregating, by an analysis module of the CDSS creation and management system, the data received from at least one of the plurality of users and the user in real-time; automatically analysing, by the analysis module, the received data in real-time, wherein the analysed data is stored in the storage module; and updating, by the analysis module, at least one of the clinical decision support system global library, the at least one CDSS, and the relational database based on the analysis in real-time.
- the method also includes performing, by the analysis module, self-analysis of usage of the CDSS creation and management system by the plurality of users and a plurality of CDSS associated with the plurality of users; and optimizing, by the analysis module, the performance of the CDSS creation and management system based on the self-analysis.
- the method also includes enabling, by a CDSS sharing module of the CDSS creation and management system, the user to share the at least one CDSS with one or more users of the plurality of users.
- the method also includes generating revenues, by a revenue generation module of the CDSS creation and management system, by presenting one or more targeted promotional media comprising advertisements on an associated CDSS interface of the plurality of users and the user based on a type of the plurality of users and the user.
- the method also includes enabling, by a CDSS control module of the CDSS creation and management system, the at least one clinical decision support system to: at least one of connect or integrate with an electronic health record system of the user; and provide a plurality of assist modes comprising a diagnosis mode, an investigation mode, and a treatment mode to an end user of the at least one CDSS.
- the method also includes enabling, by the CDSS control module, the at least one clinical decision support system to: read data about at least one patient from the electronic health record system; determine at least one of a diagnosis and a differential diagnosis by analysing of the data; display the at least one of a diagnosis and the differential diagnosis to the end user, wherein the end user is allowed to accept or reject the at least one of a diagnosis and the differential diagnosis, wherein on receiving a rejection input from the end user, the end user is prompted to enter another diagnosis in the at least one CDSS, wherein the another diagnosis is logged in to at least one of the EHR system and the CDSS; suggest a latest investigation based on s selection or input of at least one of the diagnosis, differential diagnosis, and another diagnosis by the end user; analyse results of the investigations to generate and display a final diagnosis about a condition of the at least one patient; perform risk factor analysis by comparing with the risk factor analysis data of the storage module to determine a total risk for the final diagnosis; determine a latest
- Another embodiment of the present disclosure provides a method for enabling a user to create and manage one or more clinical decision support systems (CDSSs).
- the method includes storing, in a storage module, information comprising at least one of a CDSS global library, de- identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database, and a pharmacological database.
- the method also includes displaying, by a display module, one or more interfaces to enable the user to create, modify, and customize at least one clinical decision support system based on the information stored in the storage module.
- the method further includes receiving, by an input/output module, at least one of a CDSS creation input from the user and data comprising at least one of de-identified data of one or more patients, treatments data, investigations data from at least one of a plurality of users and the user in real time, wherein the CDSS global library is automatically created and updated based on the received data in real-time.
- the method includes creating, by a CDSS creation module, the at least one clinical decision support system for the user by using the information stored in the storage module in accordance with the received CDSS creation input.
- the method also includes performing, by an analysis module, self-analysis of usage of the CDSS creation and management system by the plurality of users and a plurality of CDSS associated with the plurality of users.
- the method also includes optimizing, by the analysis module, performance of the CDSS creation and management system based on the self-analysis.
- a yet another embodiment of the present disclosure provides anon-transitory computer- readable storage medium enabling a user to create and manage one or more clinical decision support systems (CDSSs), when executed by a computing device, cause the computing device to: store, in a storage module, information comprising at least one of a CDSS global library, de- identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database, and a pharmacological database; display, by a display module, one or more interfaces to enable the user to create, modify, and customize at least one clinical decision support system based on the information stored in the storage module; receive, by an input/output module, at least one of a CDSS creation input from the user and data comprising at least one of de-identified data of one or more patients, treatments data, investigations data from at least one of a plurality of users and
- Figure. 1 A is a schematic diagram illustrating an exemplary environment, where various embodiments of the present disclosure may function;
- Figure IB is a schematic diagram illustrating another exemplary environment, where various embodiments of the present disclosure may function
- FIG. 2 is a block diagram illustrating various system elements of an exemplary clinical data support system (CDSS) creation and management system, in accordance with an embodiment of the present disclosure
- FIG. 3 is a block diagram illustrating various system elements of a CDSS control module of the CDSS creation and management system of Figure 2, in accordance with an embodiment of the present disclosure
- Figure 4 is a flowchart diagram illustrating a method for creating a CDSS by using the CDSS creation and management system of Figure 2, in accordance with an embodiment of the present disclosure.
- Figures 5A-5B are a flowchart diagram illustrating a method of determining a latest treatment protocol by a CDSS, in accordance with an embodiment of the present disclosure.
- a device or a module may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like.
- the devices or modules may also be implemented in software for execution by various types of processors.
- An identified device or module may include executable code and may, for instance, comprise one or more physical or logical blocks of computer instructions, which may, for instance, be organized as an object, procedure, function, or other construct. Nevertheless, the executable of an identified device/module need not be physically located together, but may comprise disparate instructions stored in different locations which, when joined logically together, comprise the device and achieve the stated purpose of the device/module.
- an executable code of a device or module could be a single instruction, or many instructions, and may even be distributed over several different code segments, among different applications, and across several memory devices.
- operational data may be identified and illustrated herein within the device, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, as electronic signals on a system or network.
- the disclosed computer programs or modules can be executed in many exemplary ways, such as an application that is resident in the memory of a device or as a hosted application that is being executed on a server and communicating with the device application or browser via a number of standard protocols, such as TCP/IP, HTTP, XML, SOAP, REST, JSON and other sufficient protocols.
- the disclosed computer programs can be written in exemplary programming languages that execute from memory on the device or from a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages such as JavaScript, Python, Ruby, PHP, Perl or other sufficient programming languages.
- the network may include, for example, one or more of the Internet, Wide Area Networks (WANs), Local Area Networks (LANs), analog or digital wired and wireless telephone networks (e.g., a PSTN, Integrated Services Digital Network (ISDN), a cellular network, and Digital Subscriber Line (xDSL)), radio, television, cable, satellite, and/or any other delivery or tunnelling mechanism for carrying data.
- WANs Wide Area Networks
- LANs Local Area Networks
- analog or digital wired and wireless telephone networks e.g., a PSTN, Integrated Services Digital Network (ISDN), a cellular network, and Digital Subscriber Line (xDSL)
- the network may include multiple networks or sub networks, each of which may include, for example, a wired or wireless data pathway.
- the network may include a circuit- switched voice network, a packet-switched data network, or any other network able to carry electronic communications, a cellular telephone network configured to enable exchange of text or SMS messages.
- Examples of the network include, but are not limited to, a personal area network (PAN), a storage area network (SAN), a home area network (HAN), a campus area network (CAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a virtual private network (VPN), an enterprise private network (EPN), Internet, a global area network (GAN), and so forth.
- PAN personal area network
- SAN storage area network
- HAN home area network
- CAN campus area network
- LAN local area network
- WAN wide area network
- MAN metropolitan area network
- VPN virtual private network
- EPN enterprise private network
- GAN global area network
- the term “clinical decision support system” refers to a system configured to provide an end user with updated information and tools required for assisting the end user in diagnosis, investigations, treatments, etc. while treating one or more patients.
- the clinical decision support system may include hardware, software, firmware, or combination of these.
- the end user may be a doctor, a paramedic, a physiotherapist, a surgeon, a nurse, and so forth.
- the Clinical decision support system can provide doctors and nurses with knowledge and patient-specific information, intelligently filtered and presented at appropriate times in the clinical workflow, for improving health care.
- a CDSS normally includes a variety of tools to enhance decision-making in the clinical workflow. Some of these tools may include computerized alerts and reminders to care providers, medical practitioners, and patients; clinical guidelines; condition-specific order sets; focused patient data reports and summaries; documentation templates; diagnostic support, and contextually relevant reference information, among other tools.
- the term “clinical decision support system creation and management system” refers to a system configured to provide set of resources comprising relational databases, medical information, modules that can be used by a user such as, but not limited to, a hospital to create, customize or manage its own CDSS.
- the CDSS creation and management system may include a single device or multiple devices including the resources required for enabling the user to create, customize, share, update and access one or more CDSS. Further, the CDSS creation and management system may include hardware, software, firmware, or combination of these.
- the CDSS created by using the clinical decision support system creation and management system are compatible with all EHR systems.
- the clinical decision support system creation and management system provides an AI platform configured to analyse data from unstructured data files in the EHR system and combine it with data analysis from structured data files to make accurate early diagnosis and management plans.
- the predictive AI algorithms are built into the CDSS created by using the clinical decision support system creation and management system, enabling disease deterioration to be detected before symptomatic evidence.
- the clinical decision support system creation and management system enables health care providers to develop CDSS for any diagnosis/medical condition.
- the clinical decision support system creation and management system enables customisation of the CDSS according to a hospital protocols and requirements and can be updated as often as required.
- the CDSS have Self Analytical functionality built in to analyse its performance and optimize accordingly.
- the term “user” may refer to an entity who accesses a clinical decision support system creation and management system.
- the non-limiting examples of the user may include a health care provider, a hospital, a medical clinic, a physician, and so forth.
- the term “Electronic Health Record (EHR) system” refers to a system including a device or multiple devices configured to store electronic records of a plurality of patients.
- the EHR system may also enable the user or end user to enter details such as medical history, diagnosis, investigations, results of investigations about the patients.
- the CDSS may read information from the EHR system.
- the term “computing device” refers to a device configured to enable a user to access the CDSS creation and management system and/or the CDSS.
- Examples of the computing device may include such as, but not limited to, computers, smart phones, laptops, smart televisions, servers, tablet computers, and so forth.
- a system comprising an EHR Access Bridge compatible with EHR systems of different hospitals or health care providers.
- the different hospitals or health care providers may use different EHR systems of the EHR vendors.
- the EHR Access bridge may be developed as an API, specific to an CDSS.
- the system also includes a CDSS development system configured to develop a CDSS (or standalone CDSS).
- the system may also include data analytic tools, structures, and systems for medical research.
- the system may be an AI based platform configured to allow for customisation of the CDSS according to any hospital and/or physician specifications, independent of the EHR system.
- the system is compatible with any EHR system.
- the system allows health care providers (or hospitals) and ambulatory care physicians to use multiple customized CDSS’s even those customized to other hospitals and physicians.
- the data analytics tools built into the system may result feedback into the system.
- the algorithms used by the system may learn from these results and can improve the performance of the system.
- the system may be a cloud-based system and is scalable.
- the system is designed to be used by physicians and nurses in hospitals, hospices, nursing homes and in ambulatory care e.g., specialists and primary care physicians including General Practitioners in private practice, using any EHR system (or platform).
- the EHR Access Bridge may be used to read data in EHR.
- the EHR Access Bridge may include software, hardware, firmware or combination of these.
- EHR Access Bridge utilizes API’s- HL7 (Health Level 7 Standards) FffiR protocols (Fast Healthcare Interoperability Resources), SMART on FHIR and CDS hooks API’s by SMART Health IT and Lighthouse Gateway API’s.
- FHIR API is a draft standard describing data formats describing data formats and elements and an API for exchanging electronic health records to read data in the EHR system.
- the SMART (Substitutable Medical Apps & Reusable Technology) platform defines a specification for an EHR system to safely and securely open other applications with context. These SMART applications are commonly web applications but may also be native mobile applications and will use the FHIR® standard to read and write data from the EHR system. SMART on FHIR application programming interface (API) enables an app written once to run anywhere in the healthcare system.
- API application programming interface
- CDS Hooks developed by SMART Health IT describes a “hook” based pattern for invoking decision support from within a clinician's workflow.
- CDS Hooks API Application Programming Interface
- CDS Hooks API supports synchronous, workflow-triggered CDSS calls returning information and suggestions and launching a user-facing SMART app when CDSS requires additional interaction
- An API gateway has also been developed to integrate EHR data through the Lighthouse platform. Lighthouse leverages new analytic capabilities through the API gateway to map the electronic medical record to the FHIR APIs and create common data standards.
- the FHIR API, SMART on FHIR API, CDS Hooks API and Lighthouse gateway API are enabled by each EHR vendor and the disclosed system connects the CDSS data endpoints to the FHIR API thus resulting in an EHR Access Bridge.
- the health care providers such as, Hospital can request an EHR vendor to enable the following API’s: SMART, CDS Hooks, FHIR and Lighthouse API.
- the EHR vendor installs the API’s in their datacentre.
- the API’s connect the FHIR API for that Hospital's EHR instance.
- the API’s map the Hospital's ontology to the FHIR API.
- the CDSS via an API is connected to Hospital via the completed and mapped FHIR API.
- the EHR Access Bridge is specific to an EHR vendor and thus specific to a health care provider (or hospital).
- the EHR Access Bridge can be stored on the cloud-based server, which will enable updates to occur.
- the IT department of the health care provider may be assigned a security credential, on presentation of which the EHR Access Bridge specific to that health care provider can be downloaded., all future updates will be automated and live (in real-time).
- the responses of the CDSS are through a text-based user interface.
- the specific responses are determined by the CDSS and are described in the below.
- the clinical aspect of the CDSS is designed to assist the physician with diagnosis, investigations and treatment protocols.
- FIG. 1A is a schematic diagram illustrating an exemplary environment 100A, where various embodiments of the present disclosure may function.
- the environment 100A includes a health care provider 102A.
- the non-limiting examples of the health care provider 102A includes a hospital, a nursing home, a medical clinic, a doctor, a nurse, a physiotherapist, and any medical practitioner.
- the health care provider 102A may have an associated electronic health (or medical) record system 104A configured to allow end users like medical practitioners, doctors, admin staff etc. to enter information of new patients, create a new digital record.
- the EHR system 104A may store or contain a patient’s medical history, diagnoses, medications, treatment plans, immunization dates, allergies, radiology images, and laboratory and test results. Further, the EHR system 104A may provide access to evidence-based tools that medical practitioners can use to make decisions about a patient’s care.
- the health care provider 102A such as a hospital, may have one EHR system 104A and a plurality of clinical decision support systems (CDSSs) 106A-106N.
- the environment 100A also includes a clinical decision support system creation and management system 110 that may be located in a network 108.
- the network 108 may be a cloud network.
- the CDSS creation and management system 110 may be located in a cloud network.
- a user such as the health care provider 102A, may access the CDSS creation and management system 110 for creating one or more CDSS like the CDSSs 106A-106N.
- the clinical decision support systems 106A-106N are compatible with any type of EHR system 104A.
- the clinical decision support systems 106A-106N can provide staff, doctors, clinicians, nurses, patients or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, for improving health and health care.
- Each of the CDSSs 106A- 106N may include a variety of tools to enhance decision-making in the clinical workflow. Some of these tools may include computerized alerts and reminders to end user like care providers, medical practitioners, and patients; clinical guidelines; condition-specific order sets; focused patient data reports and summaries; documentation templates; diagnostic support, and contextually relevant reference information, among other tools.
- the CDSS creation and management system 110 may be a standalone system and is designed to be compatible with an existing and future developed EHR systems or EMR systems.
- the CDSS creation and management system 110 may also be referred as a system 110 without change in its meaning.
- the CDSS creation and management system 110 and/or the CDSSs 106A-106N developed using the system 110 may be configured to read data from the EHR system 104A.
- the CDSS creation and management system 110 and/or the CDSSs 106A-106N developed using the system 110 may be configured to integrate with the EHR system 104A and therefore may be able to read/write data from and to the EHR system 104A.
- the system 110 allows the health care provider 102A to share one or more of the developed CDSSs 106A-106N with other health care providers or users via a library of the system 110 and further customize one another’s CDSSs to their requirement.
- the health care provider 102 A can download a CDSS of the other health care provider and customize the same according to its own needs.
- the system 110 may allow each health care provider 102A such as a hospital to develop their own CDSS, customised to their hospital and requirements and to share CDSS that have been developed by other hospitals across all EHR IT platforms. This may allow an enormous library of CDSS to be developed rapidly, all of which can be customisable and is stored in a storage module of the CDSS creation and management system 110.
- the CDSS creation and management system 110 enables the health care provider 102A to create one or more of the CDSSs 106A-106N by downloading a CDSS from the system 110 and customizing the downloaded CDSS according to the EHR system 104A or requirement of the health care provider 102.
- the CDSSs 106A-106N may be designed to assist the physician with diagnosis, investigations and treatment protocols.
- Each of the CDSSs 106A-106N may have an end user such as, but not limited to, a doctor, a nurse, a paramedic, a dentist, a physiotherapy, and so forth.
- HL7 Health Level 7 standards
- FHIR Fest Healthcare Interoperability Resources
- CDS Code Division Multiple Access Services
- HL7 are a set of international standards used to transfer and share data between various health care providers (e.g., 102).
- Fast Healthcare Interoperability Resources is a draft standard describing data formats and elements and an API for exchanging electronic health records.
- the system 110 may utilize API’s - HL7 FHIR protocols to read data in EHR system 104A.
- CDS Connect API may be used instead of FHIR API, if FHIR is unable to satisfactorily function.
- HL7 CD Hooks API may be used to trigger the CDSS from within the EHR system 104 A.
- the CDS Hooks API describes a hook-based pattern for invoking clinical decision support from within a clinician's workflow in the EHR system 104A.
- the CDS Hooks API supports synchronous, workflow- triggered CDSS calls returning information and suggestions and can launch a user-facing smart application when the CDSS (e.g., CDSS 106A) requires additional interaction.
- the responses of the CDSS may be through a text-based user interface. The specific responses are determined by the CDSS for example the CDSS 106A by using the information and algorithms stored in the CDSS creation and management system 110.
- FIG. IB is a schematic diagram illustrating another exemplary environment 100B, where various embodiments of the present disclosure may function.
- the environment 100B includes a plurality of users.
- the non-limiting examples of the users may include health care providers 102A-102N.
- Each of the health care providers 102A-102N may have their associated EHR system for recording and maintaining digital records of the patients.
- the health care provider 102A has the associated EHR system 104 A
- the health care provider 102B has the associated EHR system 104B
- the health care provider 102N has an associated EHR system 104N.
- Each of the health care providers 102A-102N can access the CDSS creation and management system 110 via an associated computing device such as, but not limited to, a computer.
- the health care providers 102A-102N may access the system 110 via a web uniform resource locator (URL) on a computing device.
- the health care providers 102A-102N may access the system 110 by downloading the data from the CDSS creation and management system 110 on the computing device, and may be used by the user for creating a CDSS as per their requirement.
- each of the health care providers 102A-102N may create one or more CDSSs by using the data from the CDSS creation and management system 110.
- the health care provider 102A can create the CDSSs 106A-106N
- the health care provider 102B can create a plurality of CDSS comprising CDSSs 112A-112N
- the health care provider 102N can create a plurality of CDSS comprising CDSSs 114A-114N.
- Each of the health care providers 102A-102N may develop or create their CDSSs based on their own requirement and can connect it to their respective EHR systems 104A-104N.
- each of the CDSSs 106A-106N, CDSSs 112A-112N, and CDSSs 114A-114N has built in patient data acquisition and analytics capabilities.
- Data from the health care providers 102A-102N, for example, all hospitals, utilising each type of CDSS, is harvested, collated and aggregated, in real-time, in the system 110 that may yield large datasets that can be analysed automatically by the system 110.
- the system 110 may also feedback or store the results of the data analysis into the respective CDSS and/or the storage module of the system 110.
- the analysed data may be available to the hospitals in real-time, thus resulting in improved treatment protocols, amongst other benefits.
- the CDSS creation and management system 110 may enable a user, such as the health care provider 102A, to create and manage one or more clinical decision support systems (CDSSs) such as, the CDSSs 106A-106N.
- the CDSS creation and management system 110 is configured to store information such as, but not limited to, a library comprising a CDSS global library, de-identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database, and a pharmacological database.
- the diagnosis database may include information about various diagnosis and algorithms for deriving a diagnosis based on one or more inputs like symptoms of the patient and so forth.
- the investigation database may include investigations data and algorithms for determining one or more investigations or test required for a particular diagnosis or symptoms.
- the risk factor analysis database may include list of risk factors and algorithms for risk factor analysis.
- the CDSS global library may store one or more CDSS (e.g., CDSS 106A-106N, 112A-112N, and 114A-114N) of the plurality of health care providers 102A-102N. In some embodiments, the CDSS global library is extensive and may ultimately cover every facet of medicine, and is constantly being edited and updated.
- the CDSS global library may include the newly burgeoning fields of genomics and proteomics, imaging, photo (syndromes, dermatological, ophthalmological etc) databases and incorporate medical telemetry.
- the CDSS creation and management system 110 is configured to display one or more interfaces to enable the user to create, modify, and customize at least one clinical decision support system based on the information stored in the system 110. Further, the system 110 is configured to receive at least one of a CDSS creation input from the user i.e., a health care provider of the health care providers 102A-102N and data comprising at least one of de-identified data of one or more patients, treatments data, investigations data from at least one of a plurality of users and the user in real-time. In some embodiments, the CDSS global library is automatically created and updated based on the received data in real-time.
- the system 110 may also be configured to create the at least one clinical decision support system 110 for the user e.g., the health care provider like health care provider 102B by using the information stored in the system 110 in accordance with the received CDSS creation input.
- each of the health care providers 102A-102N may maintain a CDSS local library including a number of CDSSs that may be of other health care providers 102A-102N downloaded from the system 110 and/or may be CDSS developed using the system 110.
- the CDSS local library may also include other data or databases required for developing, updating, and functioning of the CDSSs of the respective health care providers 102A-102N.
- the user and the plurality of users comprises a health care provider.
- the system 110 is further configured to enable the health care providers 102A-102N to access analysed data and the information stored in the storage module in a display format according to the requirement and preference of the health care providers 102A-102N.
- the system 110 is configured to aggregate the data received from the plurality of users in real-time; automatically analyse the received data in real-time, wherein the analysed data is stored in the storage module of the system 110; and update at least one of the clinical decision support system global library, the at least one CDSS, and the relational database based on the analysis in real-time.
- the system 110 performs self-analysis of usage of the system 110 by the plurality of health care providers 102A-102N and a plurality of CDSS 106A-106N, 112A- 112N, and 114A-114N; and optimize performance of the system 110 based on the self-analysis.
- the CDSS creation and management system 110 includes data analytical tools for self-analysis. Further, these data analytical tools may be combined with feedback sessions conducted by the system 110 with the end users (e.g., doctors and nurses) to determine the effectiveness of the system 110.
- the self-analysis data may include information such as: are alerts being utilised- for every alert there will be an override function, the system 110 may compare the users next response in the EHR system 104A. Number of times the override function is used; are investigations, treatment protocols being used- the system 110 may compare the users next response in the EHR system 104A to the protocols; Is the Diagnosis being utilised- the system 110 may compare the users next response in the EHR system 104A to the diagnosis in the protocols; If Investigations protocols are not followed vs being followed- the system 110 may compare costs of each and patient hospitalisation duration; and symptoms and duration of hospitalisation for adherence to CDSS recommendations versus no adherence.
- the system 110 enables each of the health care providers 102A- 102N to share the at least one CDSS of their associated CDSSs with one or more of the health care providers 102A-102N.
- the health care provider 102N can share its CDSS 114A with the health care provider 102B via the system 110 may be by uploading the CDSS 114A onto the CDSS global library of the system 110.
- the system 110 is configured to enable the at least one CDSS to either connect or integrate with an electronic health record system of the health care provider.
- the CDSS 106A may connect with the EHR system 104A of the health care provider 102A.
- the system 110 may also provide a plurality of assist modes comprising a diagnosis mode, an investigation mode, and a treatment mode to an end user of the at least one CDSS.
- the end user may be a doctor, a paramedic, a nurse, a physiotherapist or anyone who is using the CDSS.
- FIG 2 is a block diagram illustrating various system elements of an exemplary clinical data support system (CDSS) creation and management system 202, in accordance with an embodiment of the present disclosure.
- the clinical decision support system creation and management system 202 may enable a user to create and manage one or more clinical decision support systems (CDSSs).
- CDSSs clinical decision support systems
- a user may be the health care provider 102B that may create the plurality of CDSSs 112A-112N by using the CDSS creation and management system 202 (hereinafter may also be referred as system 202 without change in its meaning).
- the system 202 primarily includes a storage module 204, a display module 206, an input/output module 208, a CDSS creation module 210, an analysis module 212, a CDSS sharing module 214, and a CDSS control module 216.
- the storage module 204 is configured to store information such as, but not limited to, a CDSS global library, de-identified data of a plurality of patients, treatments protocols, results of investigations data, risk factor analysis data, treatment data, instructions for creating a CDSS, a relational database comprising at least one of a diagnosis database, an investigation database, a risk factor analysis database, and a pharmacological database.
- the storage module 204 may also store algorithms and other maintenance tools that may enable a user like a health care provider to develop its own customized CDSS.
- the storage module 204 may also store algorithms or instructions for determining diagnosis, investigations, results of investigations analysis, risk factor analysis, treatment, and so forth.
- the storage module 204 may store any other information such as, but not limited to, symptoms, diagnosis, articles for medical research, details about the users, authentication information, payment information, revenue information, and so forth.
- the storage module 204 may include software, hardware, firmware or combination of these.
- the storage module 204 may be a local storage system.
- the storage module 204 may be a remotely located storage system and may be located in a cloud network.
- the system 202 may use five sets of algorithms for diagnosis, investigations, results of investigations analysis, risk factor analysis, and treatment. Further, there may be two types of CDSSs that can be developed using the disclosed system 202. In type 1 CDSS, the diagnosis is made by the CDSS using algorithms, then Investigations for that Diagnosis as specified by the CDSS, results of Investigations analysed using algorithms, diagnosis either confirmed or new diagnosis made, then treatment as specified by a CDSS (e.g., CDSS 106A) for diagnosis. In type 2 CDSS, diagnosis is made by physician. The CDSS may specify investigations and/or treatment for the diagnosis.
- the system 202 may use natural language processing method (or program) for the analysis of presenting/current symptoms requires the application of a Natural Language Processing Program that is trained on medical terminology and can be applied to an unstructured data file such as Doctor or nursing notes, e.g., History notes.
- a Natural Language Processing Program that is trained on medical terminology and can be applied to an unstructured data file such as Doctor or nursing notes, e.g., History notes.
- the system 110 may check If patient is not taking any current medications, proceed as for scenario “2?” below.
- Scenario A If a patient is taking current medications then the system 202 may check dates when symptoms began and when medications were prescribed, if ⁇ 10 days apart. At Step 1, If patient taking 2 or more current medications then map patients’ current medications from EHR system 104A to drug-drug interaction database screen for Drug - Drug (from current medications) interactions and match to a drug-drug interaction database for result. The system 202 may map Presenting/Current symptoms of patient, from the EHR system 104A (as shown in Figure 1A) to drug-drug interaction database. In some embodiments, the analysis of presenting/current symptoms requires the application of a natural language processing program that is trained on medical terminology.
- Step 2 if there is no Past Medical History, proceed with Step 3. If Step 1 above is negative or if patient taking 1 or more Current Medications and if there is a Past medical History: Map patients’ Past history medical diagnoses and current medications from the EHR system 104A to drug-disease interaction database. The system 202 may screen for drug (from Current medications) - disease (diseases from Past History medical diagnoses) interactions and match to drug-disease interaction database for result. If result of interaction/s matches Presenting/Current symptoms, display the following text “This patients’ symptoms match the Drug - disease interactions (Specify the drug /s and the disease). Do you wish to proceed with further screening Yes or No. If the Selection is Yes, then: proceed as for B] below.
- Step 3 If Step 1 or Step 2 above are negative and if patient taking 1 or more Current Medications then system 202 may map patients’ current medications from the EHR system 104A to adverse effects database. Screen for adverse effects of drugs (for each of the drugs from Current medications) and match to adverse effects database for result. If result of interaction/s matches Presenting/Current symptoms, display the following text “This patients’ symptoms match the Adverse Effects of (specify the drug/s). The analysis of presenting/current symptoms may require the application of a Natural Language Processing Program that is trained on medical terminology. Do you wish to proceed with further screening? Yes or No”. If the Selection is Yes, then: proceed as for B] below. If No then close application. If result of screening for Adverse Effects does not match Presenting/Current symptoms, proceed with scenario B below.
- Scenario B If patient is not taking current medication or If dates when symptoms began and when medications were prescribed are > 10 days apart or if screening in all of the Steps 1 - 3 above are negative: Map Presenting/Current symptoms and signs in EHR system 104A to symptoms and signs (particularly tagged symptoms and signs) in reference database - don’t have to match every symptom and sign. Note: analysis of presenting/current symptoms requires the application of a Natural Language Processing Program that is trained on medical terminology. If they match even partially, accept as Diagnosis. The system 202 may display the following text “This patient’s symptoms and signs match the Provisional diagnosis (Specify). The following Investigations will be required to confirm Diagnosis” and proceed with Algorithm for Investigations. If there are no matches - reject and keep looping this algorithm until there is a match.
- CDSS e.g., CDSS 106A
- a CDSS e.g., CDSS 106A
- the system 202 may proceed as for Scenario A i.e., Steps 1 - 3 above. If there is a match in any of the above Steps 1-3 then the system 110 can display the following text “This patient’s symptoms match the Drug - drug interactions and/or Drug - disease interactions and/or Adverse Effects of drugs (strike out whichever does not apply). Do you wish to proceed with further screening? Yes or No”. If the Selection is Yes, then the system 202 may map the presenting/current symptoms, (Please note, analysis of presenting/current symptoms requires the application of a Natural Language Processing Program that is trained on medical terminology) signs and lab test results from EHR system 104A to each of the Scenarios listed in the reference relational database.
- the system 110 may discard and keep looping this algorithm until there is a match.
- the system 202 performs the step a).
- the system 202 may map diagnosis in EHR system 104A to diagnosis in reference relational database. If the diagnosis matches, continue with the appropriate algorithm.
- the system 202 may reject and close application.
- diagnosis in the EHR system 104A contains words that partially match diagnosis in reference relational database
- the system may display a query in the text-based interface.
- the query may be “Please select the diagnosis (from reference diagnosis database) to continue”. Once the selection is made then the system 202 may proceed with an appropriate algorithm.
- the system 202 may list the investigations from the reference relational database and display investigations in a suitable interface such as, but not limited to, a text-based interface - “Investigations for Diagnosis (specify)”. If there is a care plan, then the system 202 may display a list of variances first and also display on the text-based interface with the query “Please select from the following Care Plan Variances to continue”. Once the selection is made (e.g., by the user), then the system 202 can display the text for the specified Variance of care plan as entered in the reference database.
- a suitable interface such as, but not limited to, a text-based interface - “Investigations for Diagnosis (specify)”. If there is a care plan, then the system 202 may display a list of variances first and also display on the text-based interface with the query “Please select from the following Care Plan Variances to continue”. Once the selection is made (e.g., by the user), then the system 202 can display the text for the specified Variance
- the system 202 is configured to analyse the results of the investigations.
- CDSS e.g., CDSS 106A
- the system 202 may map the presenting/current symptoms, signs and lab test results from the EHR system 104A to each of the Scenarios listed in the reference relational database. If results match then the system 202 may display text “Symptoms, signs and Investigations confirm Diagnosis (specify Scenario)”. If there is no match the system 110 may proceed as for 3) below.
- the system 202 may map lab test results to the investigations database.
- the system 110 may read off the diagnoses for the lab test result from the investigations database and display text “Lab tests (specify) suggest the following diagnoses (specify)”. If the Diagnosis from the investigations database matches any of the past history diagnoses from the EHR system 104A, then the system 202 may display in a text-based Interface as “Lab tests confirm Past History Diagnosis (specify)”. If lab test results don’t match any diagnosis in the investigations database, then the system 202 may keep looping the algorithm/s in steps 1 or 2 as disclosed above.
- the system 202 may proceed to Risk Factor Analysis.
- the system 202 (or a risk factor analysis module as shown in Figure 3) may calculate risk for a diagnosis based on weighted score OR by using pre-developed graphs/calculators whereby the physician does the calculation manually.
- the system 202 may assign 2 scores for each risk factor in the reference database for quality and quantity.
- the quality of the weighted score is more important and may range from 1 - 5 in some embodiments, than quantity, which may range from 1, 2, and 3.
- the quality refers to the relative importance of a risk factor relative to the other risk factors. 1-2 (low), 3 (med), 4-5 (high).
- the quantity may refer to the absolute value of the risk factor i.e., l(low), 2 (med) and 3 (high). For a risk factor such as gender, ethnicity or occupation where there is no quantifiable value then the system 202 may assign the value of 3.
- the weighted score may be calculated as follows:
- Weighted score Quality x Quantity of risk factor a + Quality x quantity of risk factor b
- the system 202 may read off associated risk factors e.g., from the reference database) if applicable.
- the system 202 may map the corresponding risk factors from the EHR system 104A to this location. If the risk factors have been linked from the risk factor analysis database to score then calculate total risk based on the weighted score as described above.
- system 202 may read of lifestyle modification, medication or further screening advice from reference database.
- the system 202 may display via the text-based Interface “Risk Factor analysis Advice is as follows (advice from reference database)”. If total risk is determined as low - then the system 202 may not provide any advice.
- the system 202 may display a graph or a calculator. If total risk is high, then the system 202 may use the vital observations/exam findings and trends of lab tests to develop predictive algorithms. Once this step is completed the system 202 may determine a Treatment.
- the system 202 may read of corresponding treatment from the reference database. This treatment can be either Pharmacological and/or non - Pharmacological.
- the system 202 may also display text of Treatment “Treatment for Diagnosis or Scenarios of Diagnosis. (Specify text)”. This text may contain both pharmacological and non-pharmacological treatment and further management advice. If only non-pharmacological treatment is included in advice, then system 202 may stop here. Alternatively, if Pharmacological Treatment (prescribed) is included in above advice then the system 202 may map data from Allergies in the HER system 104A to this location.
- the system 202 displays text “This patient is Allergic to (specify drug/s), please select alternate medication”. Th system 202 may loop this algorithm for the new drug selected. Once there is no match, the system 202 may check A’ : if patient taking Current Medication drugs and perform the following step A.1 and A.2. At step A.1 , the system 202 may map drugs from current medications list in the HER system to this location and screen for Drug (Prescribed drug) - drug (for each of the Current medication drug/s from the EHR system 104A) interactions. At step A.2, the system 202 may map medical past history diagnoses list in the EHR system 104A to this location and screen for drug (Prescribed drug) - disease (for each of the medical diagnoses from the EHR system 104A) interaction.
- the system 202 may display the text of interaction in Text based interface with the Warning “You have the options of selecting an alternative medication because of significant interaction (specify interaction) or proceeding with selected medication.” The system 202 then may display text “Alternative medication” and “As selected medication”. If Alternative medication is selected then the system may loop the algorithms as in the step A.1 and A. 2 above for each alternate medication. If As selected medication is selected, then the system 202 may proceed as in B’ below.
- the system 202 determines if patient NOT taking Current Medications or if no interactions, then the system 202 may map data from Allergies in the EHR system 104A to this location. If Allergies data match any of the prescribed medication then the system 202 may display text “This patient is Allergic to (specify drug/s); Please select alternate medication”. The system 202 may loop this algorithm for the new drug selected. Once there is no match, the system 202 stops here.
- the system 202 may display “Select from the list of Care Plan Variances” in the text-based interface. Once a particular Variance is selected from Text based Interface then display Text of Care Plan protocols for that Variance. These Variances may contain pharmacological treatment advice.
- the system 202 may proceed as for A’ and B’ above.
- the health care provider 102B may develop its own CDSS, such as the CDSS 112A, by entering medical content into a relational database.
- the medical content may need to be edited and updated constantly by the specialist developers at the health care provider 102B.
- Multiple CDSS encompassing all facets of medicine developed by different health care providers 102A-102N e.g., hospitals) may result in the CDSS global library.
- Resources, such as the CDSS global library, may be pooled between the health care providers 102A-102N so that rapid and extensive CDSS deployment can occur.
- a health care provider of the health care providers 102A-102N can edit CDSS in the CDSS global library that have been developed by other health care providers 102A-102N to further customise to their requirements.
- the system 202 is compatible with any EHR system, this means that the health care providers 102A-102N are not locked in to the vendor of their EHR system and can use the CDSS global library easily for developing their own CDSS.
- the relational database may primarily include the diagnosis database, the investigation database, and the risk factor analysis database.
- the diagnosis database may include four components i.e., general diagnosis, specific diagnosis, pathological diagnosis, genetic/proteomic diagnosis.
- the general diagnosis for gastroenteritis may include a list of sub categories. Specific diagnosis for each of the sub categories (if applicable) of the general diagnosis (gastroenteritis): e.g., bacterial gastroenteritis, viral gastroenteritis, protozoal gastroenteritis may be stored in the general diagnosis.
- the pathological diagnosis for each specific diagnosis sub category e.g., for bacterial gastroenteritis, the pathological diagnosis may include salmonella, shigella etc.
- the genetic or proteomic mutation if applicable for each pathological diagnosis is also stored in the diagnosis database.
- the relational database for each general or specific diagnosis, following information may be entered in the relational database (or the diagnosis database): age group (adult, paediatric, specify age group), gender, ethnicity specific for the diagnosis, family history, e.g., consanguinity or hereditary genetic abnormalities, social/occupation significance if any, symptoms (list, check box (tag any significant symptoms - qualifying criteria for diagnosis then upload text, images/photos of symptoms), signs (list, check box (tag any significant signs such as, qualifying criteria for diagnosis, upload text, images/photos of signs, criteria for diagnosis e.g., no and type of symptoms, signs and results of investigations to make diagnosis, and so forth.
- age group adult, paediatric, specify age group
- gender ethnicity specific for the diagnosis
- family history e.g., consanguinity or hereditary genetic abnormalities
- social/occupation significance if any, symptoms
- symptoms list, check box (tag any significant symptoms - qualifying criteria for diagnosis then upload text, images/photos of symptoms)
- signs list, check box
- the investigations categories may be entered in the relational database, for example, the first line investigations may include listing investigations and their results, tag any significant diagnostic investigations, for positive result - specify whether elevated, reduced or abnormal, negative result- specify whether elevated reduced or normal, and the second line investigations may include listing investigations and their results, tag any significant diagnostic investigations, for positive result - specify whether elevated, reduced or abnormal.
- the first line investigations may include listing investigations and their results, tag any significant diagnostic investigations, for positive result - specify whether elevated, reduced or abnormal
- negative result- specify whether elevated reduced or normal and the second line investigations may include listing investigations and their results, tag any significant diagnostic investigations, for positive result - specify whether elevated, reduced or abnormal.
- text images of investigations such as, but not limited to, ECG, EEG, EMG, Others, Radiology - X-rays, CT, MRI, U/S, Radio nuclear scans may be uploaded into the relational database.
- scenarios of investigations and treatment for each diagnosis is entered in the diagnosis database (or the relational database).
- age, F.H. social/occupational history, symptoms, signs, medications, immunisations, result of investigations, then further investigations and treatment for above scenario may be needed.
- no care plan For each investigation category above a treatment protocol comprising text, images of management techniques (physio etc., and further investigations, bibliography may be uploaded. Further, information such as select if diagnosis is to be displayed with Red warning Flags, e.g., Sepsis, is also uploaded.
- the system may either assign a score or link to graph/calculator in the diagnosis database.
- the lifestyle modification and/or specific advice such as medications or further screening for each risk factor may be entered in to the diagnosis database.
- the diagnosis database may refer to the criteria and values of the criteria that are necessary to make a diagnosis, for every variation of type or severity of diagnosis.
- user may enter any or all of the following to make the first diagnosis: symptoms, signs, lab tests and specify lookback period for every sign. For every sign (such as vital observations or clinical measurements) and every lab test enter the value or ranges that are necessary to make the first diagnosis.
- the plurality of details may include such as, but not limited to name of investigation; normal range: as specified by laboratory, if not specified by lab, enter normal range; specify if investigation is 1 st line (e.g., screening test) or 2 nd line (2 nd line investigations are diagnostic); if elevated result for first line investigation then list of diagnoses; and if depressed result for first line Investigation: list of diagnoses. [00126] If care plan used then investigations and treatment for each variance of diagnosis.
- variance 1 of care plan if: select from any or all: Age, F.H., Social/Occupational History, Symptoms, Signs, Medications, Immunizations, Result of Investigations, then further investigations and treatment for above scenario. If variance 2 of care plan then infinity.
- the investigations database may be purchased or may be pre-developed.
- the risk factor analysis database may include risks related information like list of risk factors for each specific diagnosis e.g., Myocardial infarct, Diabetes 1, Diabetes 2, etc. Further, the risk factor analysis database may include links to each risk factor to a location of data file in EHR. e.g., Past history, Family history, Social/Occupational history, Examination, Results, link each risk factor to score. Alternatively, the risk factor analysis database may include analytical graphs or calculators (e.g., NZ CVD risk calculator) linked to risk factors. Further, for each risk factor, list of lifestyle modification, specific advice or medication or further screening procedures may also be stored in the risk factor analysis database. In some embodiments, the risk factors together with vital observations/examination findings and lab test results can be used to develop predictive algorithms.
- pharmacological databases there may be three types of pharmacological databases: 1) Drug-drug interaction database; 2) Drug-disease interaction database; 3) Adverse effects of drugs database. Further, all or some of the pharmacological databases may be purchased or pre-developed.
- the display module 206 is configured to display one or more interfaces to enable the user like a hospital to create, modify, and customize at least one clinical decision support system based on the information stored in the storage module 204.
- the display module 206 is further configured to enable the user e.g., the hospital and the plurality of users, e.g., a plurality of hospitals, to access analysed data and the information stored in the storage module 204 in a display format according to the requirement and preference of the plurality of users.
- the non-limiting examples of the display formats may include a word document, an excel sheet, a power point presentation, a PDF, graphs, charts, tables, and so forth.
- the input/output module 208 is configured to receive at least one of a CDSS creation input from the user e.g., the hospital.
- the input/output module 208 is also configured to receive data such as, but not limited to, de-identified data of one or more patients, treatments data, investigations data from at least one of a plurality of users and the user in real-time.
- the CDSS global library in the storage module 204 may be automatically created and updated based on the received data in real-time.
- the CDSS creation module 210 is configured to create the at least one clinical decision support system for the user (e.g., the hospital) by using the information stored in the storage module 204 in accordance with the received CDSS creation input.
- the type 1 CDSS may derive all the diagnosis using algorithms stored in the storage module 204, and specify investigations for that diagnosis.
- the type 1 CDSS may also determine and analyse results of investigations using algorithms stored in the storage module 204.
- the type 1 CDSS may suggest a diagnosis or a differential diagnosis. An end user like a physician may accept or may enter a new diagnosis.
- the type 1 CDSS may specify treatment for the diagnosis either confirmed or new diagnosis made by the physician.
- the analysis module 212 is configured to aggregate the data received from the plurality of users e.g., a plurality of hospitals or health care providers, in real-time.
- the analysis module 212 may automatically analyse the received data in real-time, and store the analysed data in the storage module 204. Further, the analysis module 212 may be configured to update at least one of the clinical decision support system global library, the at least one CDSS, and the relational database based on the analysis in real-time.
- the plurality of users e.g., hospitals, may access analysed data and the information stored in the storage module 204 in a display format according to the requirement and preference of the hospitals.
- the analysis module 212 is further configured to perform self- analysis of usage of the CDSS creation and management system 202 by the plurality of users (e.g., health care providers 102A-102N) and a plurality of CDSS associated with the plurality of users; and optimize performance of the CDSS creation and management system 202 based on the self- analysis.
- the CDSS creation and management system 202 is designed to self-learn and optimize its own performance over a period of time.
- the CDSS sharing module 214 is configured to enable the user (e.g., a hospital) to share the at least one CDSS with one or more users of the plurality of users (e.g., other hospitals).
- the CDSS sharing module 214 may allow a hospital to share its CDSS created using the system 202 with other hospitals.
- the hospital may share the CDSS by uploading the data of the CDSS into a CDSS global library and other hospitals can access the CDSS from the CDSS global library.
- the hospital may share the CDSS with the other hospitals directly by allowing the other hospitals to download or access the CDSS.
- the hospital may charge other hospitals for access its CDSS. This means the hospital may generate some revenue by sharing the CDSS with the other hospitals.
- the CDSS control module 216 may enable the at least one CDSS to at least one of connect or integrate with an electronic health record system of the user.
- the CDSS control module 216 may enable the CDSS 106A of the health care provider 102A to connect or integrate with the EHR system 104A of the provider 102A.
- the CDSS control module 216 is further configured to provide a plurality of assist modes comprising a diagnosis mode, an investigation mode, and a treatment mode to an end user, such as the doctor, of the at least one CDSS.
- the CDSS control module 216 is further configured to enable the at least one clinical decision support system such as the system 202 to read data about at least one patient from the electronic health record system.
- the CDSS control module 216 may also determine at least one of a diagnosis and a differential diagnosis by analysing the data; display the at least one of a diagnosis and the differential diagnosis to the end user, wherein the end user is allowed to accept or reject the at least one of a diagnosis and the differential diagnosis, wherein on receiving a rejection input from the end user, the end user is prompted to enter another diagnosis in the at least one CDSS, wherein the another diagnosis is logged in to at least one of the EHR system and the CDSS; suggest a latest investigation based on a selection or input of at least one of the diagnosis, differential diagnosis, and another diagnosis by the end user; analyse results of the latest investigations to generate and display a final diagnosis about a condition of the at least one patient; perform risk factor analysis by comparing with the risk factor analysis data of the storage module 204 to determine a total risk for the final diagnosis; determine a latest treatment protocol for the final diagnosis based on at least one of the total risk and the treatment data of the storage module 204; and display the latest
- the system 202 may include a revenue generation module configured to generate revenues by presenting one or more targeted promotional media comprising advertisements on an associated CDSS interface of the plurality of users (hospitals) and the user (e.g., a clinic) based on a type of the plurality of users and the user.
- the revenue generation module may include hardware, software, firmware or combination of these.
- the revenue may be derived from sales of the CDSS library and advertising within each CDSS.
- This advertising can be targeted to specific sections within each CDSS, for example, in Investigations for a given diagnosis, Non pharmacological treatment for a diagnosis, Pharmacological treatment for a diagnosis, and Risk factor advice for a diagnosis.
- the advertising by being extremely targeted to each diagnosis may therefore actually be assistive to the physician user.
- the advertising can be integrated into the advice being given to the user (e.g., physician, nurse, hospital) and will not be gratuitous or superfluous. In short it will not look like advertising to the user.
- the non-limiting examples of targeted adverts are: Celiac Disease: Investigation: capsule endoscopy, gastroscopy: advertisers are gastroenterologists; Celiac Disease: Non pharmacological treatment: advertisers are Dietitians, Gluten free food manufacturers and stores selling Gluten free foods; Diabetes Type 1, 2: Non pharmacological treatment (diet, weight control): advertisers are Dietitians, gyms/personal trainers; Diabetes Type 1, 2: Pharmacological treatment: advertisers are Pharmaceutical companies; Obesity: Risk factor mitigation: advertisers are bariatric surgeons, Weight Watchers, Gyms/personal trainers, low calorie diet foods, appetite suppressants (pharmaceutical companies)]. Further, each advertiser may actually assist the physician in managing the patient for that particular diagnosis.
- the medical content can determine the revenue indirectly.
- the analysis module 212 is further configured to process the data read from the EHR system and derive at least one of the diagnosis and a differential diagnosis, investigations for the diagnosis, may analyse the results of the investigations and determine treatment protocol based on the results.
- FIG. 3 is a block diagram illustrating various system elements of the CDSS control module 216 of the CDSS creation and management system 202 of Figure 2, in accordance with an embodiment of the present disclosure.
- the CDSS control module 216 includes an electronic health record access module 302, a diagnosis module 304, an investigation module 306, a risk factor analysis module 308, and a treatment module 310.
- the CDSS control module 216 may include more or less than five modules. Further functionality of one or more modules of the 302-310 may be combined in different embodiments.
- the electronic health record access module 302 may read data from an electronic health record system of a user.
- the EHR access module 302 may read data such as patients name, age, symptoms, past history, family history data etc. from the EHR system 104A of the health care provider 102 A.
- the electronic health record access module 302 may write data in to the electronic health record system of the user.
- the electronic health record access module 302 may read and/or write data from or to an electronic health record system of a user.
- the electronic health record access module 302 may enable at least one CDSS (such as the CDSS 106A) to read data about at least one patient from the electronic health record system 104 A.
- the diagnosis module 304 may be configured to determine at least one of a diagnosis and a differential diagnosis by analysing the data e.g., the data of at least one patient from the EHR system (e.g., 104A).
- the diagnosis module 304 may enable at least one CDSS (such as the CDSS 106A) to determine at least one of a diagnosis and a differential diagnosis by analysing the data e.g., the data of at least one patient from the EHR system (e.g., 104A).
- the diagnosis module may perform following steps for determining a diagnosis.
- the past history medical diagnoses may be read or recorded from a temporary file of an EHR system (such as the EHR system 104A) into a CDSS (such as, the CDSS 106A) and match presenting symptoms in the EHR system (copied into logfile) to symptoms of medical diagnoses in the past history that are copied into the temporary file using step 4 below, if they match then accept the matched diagnosis as a diagnosis. If no match then the diagnosis may be rejected.
- the past history surgical diagnoses are read or recorded from the temporary file into the CDSS.
- exclusions of diagnoses involving those organs that have been removed are listed, if presenting symptoms in the EHR system (copied into logfile) match symptoms of excluded diagnoses then reject this diagnosis.
- family history diagnoses are recorded or read from the temporary file into the CDSS, presenting symptoms in EHR (copied into logfile) may be matched to symptoms of diagnoses copied into family history (copied into the temporary file) using step 4 below. If they match then accept the match as a diagnosis, if no match then the diagnosis module 304 rejects the diagnosis.
- presenting symptoms are read from logfile into the CDSS, presenting symptoms in the EHR system (copied into logfile) are matched to symptoms (particularly tagged symptoms) in general diagnosis or specific diagnosis (whichever is specified by the CDSS diagnosis database) - don’t have to match every symptom, if they match even partially, accept as diagnosis if there are no matches then reject.
- the display device 206 may display the at least one of a diagnosis and the differential diagnosis to the end user, wherein the end user (e.g., a doctor) is allowed to accept or reject the at least one of a diagnosis and the differential diagnosis. Further, on receiving a rejection input from the end user, the display module 206 may prompt the end user to enter another diagnosis in the at least one CDSS.
- the another diagnosis entered by the end user may be logged in to at least one of the EHR system, the CDSS and the storage module 204.
- a diagnosis or a differential diagnosis is determined by the CDSS and may be displayed on the computing device through with the end user is accessing the CDSS, then the end user may accept the diagnosis or modify or reject it, and if the diagnosis is rejected, then the CDSS may prompt the end user to enter the another diagnosis.
- the end user may enter the another diagnosis and that will be logged into the CDSS/EHR system/ or the storage module 204. This way the information on the CDSS and the storage module 204 may be automatically updated in real-time.
- the type 2 CDSS may not provide diagnosis but may only provide investigation advice, results analysis and treatment advice for a diagnosis that has already been made may be by the physician or an end user.
- the investigation module 306 may suggest a latest investigation based on a selection or input of at least one of the diagnosis, differential diagnosis, and another diagnosis by the end user. Further, the investigation module 306 may analyse results of the latest investigations to generate and display a final diagnosis about a condition of the at least one patient. In some embodiments, the investigation module 306 may enable the CDSS of the user to suggest a latest investigation based on a selection or input of at least one of the diagnosis, differential diagnosis, and another diagnosis by the end user. In some embodiments, the investigation module 306 may enable the CDSS to analyse results of the latest investigations to generate and display a final diagnosis about a condition of the at least one patient. The investigation module 306 may suggest investigations based on the diagnosis etc. for the type 2 CDSS, which in turn may provide investigation advice, results analysis and treatment advice for a diagnosis that has already been made.
- the type 2 CDSS may provide investigation advice by performing following steps.
- step 1 matching diagnosis in the EHR system (copied into logfile) to either general diagnosis or specific diagnosis of the CDSS. If diagnosis matches, continue with determining investigations by using investigations algorithms stored in the storage module 204.
- step 2 if diagnosis does not match then reject and close the interface.
- diagnosis in the EHR system (copied into logfile) contains words that partially match general or specific diagnosis in the CDSS then display text-based interface with the query and please select from the list of following diagnosis to continue. The list of “following diagnosis” are read off from specific diagnosis database. Once the selection is made then proceed as for the step 1. Once the step 3 is completed, then the system 202 may proceed to investigations.
- the investigation module 306 may determine investigations based on the determined diagnosis or diagnosis accepted by the end user. For each diagnosis, investigations from diagnosis database of the relational database may be listed and duplicate tests are removed. Then, the display module206 may display the investigations to the end user via a text-based interface to the end user.
- the investigation module 306 may analyse the results of the investigations. Each diagnosis (i.e., a diagnosis that is read from the logfile) may be matched with the corresponding results of investigation that are copied into the logfile to those listed in the investigations (i.e., from the diagnosis database in the CDSS) either in general or specific diagnosis. If results match then the investigation module 306 selects the diagnosis. If results don’t match then investigation module 306 may search for a match in the investigations database. The investigation module 306 may then list the diagnoses for the matching investigation. If the diagnosis from the investigations database does not match any of the diagnoses in the logfile, then accept the diagnosis from the investigations database as a new diagnosis or a differential diagnosis.
- the display module 206 may display the new diagnosis, or the differential diagnosis in a text- based interface.
- the risk factor analysis module 308 may perform or enable the CDSS to perform risk factor analysis by using an algorithm for risk factor analysis stored in the storage module 204.
- the risk factor analysis module 308 may perform risk factor analysis by comparing with the risk factor analysis data of the storage module 204 to determine a total risk for the final diagnosis.
- risk for a diagnosis may be calculated based on a score or may use graphs/calculators, where the end user (i.e., the physician) may do the calculation.
- the risk factor analysis module 308 may calculate the score by assigning two scores i.e., a quantity score, and a quality score for each risk factor in the diagnosis database of the relational database.
- the quality score of the weight is more important and may be in a range from for example, 1 to 5 than the quantity score that may be in a range from for example, 1 to 3.
- the quality score may refer to the relative importance of a risk factor relative to the other risk factors, wherein a quality score of 1 -2 may mean a low risk, 3 may mean medium risk, and 4-5 may mean high risk.
- the quantity score may refer to the absolute value of the risk factor, wherein a quantity score of 1 may mean a low absolute value of the risk factor, 2 may mean a medium absolute value of the risk factor, and a 3 may mean a high absolute value of the risk factor.
- a risk factor such as gender, ethnicity or occupation where there is no absolute value then the analysis module 212 may assign the value of 3.
- Age may have a quality score of 3, and quantity score for 0-40 years - 1, 40-60 years- 2, > 60 years - 3; Gender may have a quality score of 3, a quantity score for male-3, and for female-1, for obesity.
- the risk factor analysis module 308 may calculate the score (may also be referred as a weighted score) by using the following formula:
- Weighted score Quality x Quantity of risk factor a + Quality x quantity of risk factor b
- the risk factor analysis module 308 may use the following formula for calculating total risk:
- the risk factor analysis module 308 may read off associated risk factors from risk factor analysis database, if applicable. If the risk factors have been linked (from risk factor analysis database) to weighted score then calculate total risk based on weighted score as above. If the risk factors have been linked to graphs or pre developed calculators, display graph or calculator. For each diagnosis calculated from using weighted score or graph/pre developed calculator display the calculated total risk. If total risk is medium to high, the risk factor analysis module 308 may read off or provide lifestyle modification, medication or further screening advice from the risk factor analysis database.
- the display module 206 may display the total risk and other outcomes of the risk factor analysis via a text-based interface on the CDSS of the end user like on a CDSS interface on the computer of the doctor. If total risk is low, then no further advice may be provided to the end user for the patient.
- the treatment module 310 may determine a treatment by using an algorithm for treatment stored in the storage module 204. In some embodiments, the treatment module 310 may determine a latest treatment protocol for the final diagnosis based on at least one of the total risk and the treatment data of the storage module 204. For each diagnosis, the treatment module 310 may read corresponding treatment from the diagnosis database, either from general or specific diagnosis.
- the display module 206 may display the latest treatment protocol in the text-based interface on the CDSS of the end user like on a CDSS interface on the computer of the doctor. The end user is allowed to at least one of accept the latest treatment protocol and modify the latest protocol, wherein the modified latest treatment protocol is logged into at least one of the CDSS and the EHR system.
- the display module 206 may display “Select from the list of scenarios” (as specified in diagnosis database) in a text-based interface. Once a particular scenario is selected by the end user from the text-based interface then the display module 206 may display investigations and treatment protocols for that scenario from the diagnosis database in another text-based interface.
- FIG 4 is a flowchart diagram illustrating a method for creating a CDSS by using the CDSS creation and management system 202 of Figure 2, in accordance with an embodiment of the present disclosure.
- the health care provider 102A such as a hospital have the EHR system 104A for entering and maintaining records about the patients.
- the health care providers 102A may create the CDSSs 106A-106N by using the CDSS creation and management system 110.
- the CDSS may be created by downloading a CDSS from the CDSS library and customizing it according to the requirement of the health care provider 102A.
- the CDSS creation and management system 110 may enable a user, i.e., the health care provider 102A, to access the CDSS creation and management system 110 via one or more interfaces on a computing device of the user.
- the health care provider 102A may be a hospital wanting to create one or more CDSS by using the system 110.
- the CDSS creation and management system 110 may receive a CDSS creation input via an input interface of the computing device to create a clinical decision support system for the user.
- the input/output module 208 may receive the CDSS creation input from the user.
- the CDSS creation input may include medical data.
- the CDSS creation and management system 110 may create the CDSS for the user and enable the user to customize the CDSS as per requirement of the user.
- the CDSS creation module creates the CDSS based on the CDSS creation input for the user.
- the CDSS creation and management system 110 may enable the user to connect or integrate the CDSS with an electronic health record system of the user and use information stored in the CDSS creation and management system as per his/her requirement and preference.
- the health care provider 102A may connect or integrate the CDSS 106A-106N with the EHR system 104A.
- the created CDSS may be connected, integrated or used with an EHR or EMR system of any vendor.
- FIGS 5A-5B are a flowchart diagram illustrating a method 500 of determining a latest treatment protocol by a CDSS, in accordance with an embodiment of the present disclosure.
- the CDSS control module 216 may enable the at least one CDSS to at least one of connect or integrate with an electronic health record system of the user (such as a hospital). Further, the CDSS control module 216 may enable the at least one CDSS to provide a plurality of assist modes comprising a diagnosis mode, an investigation mode, and a treatment mode to an end user of the at least one CDSS. The end user may access the at least one CDSS on an associated computing device like a computer.
- the end user such as a doctor may select a diagnosis mode when the doctor wants the CDSS to provide a diagnosis based on one or more symptoms or patient’s information.
- the end user may accept, reject or modify the suggested diagnosis r may enter a new diagnosis.
- the diagnosis is modified, then the modified diagnosis and/or the new diagnosis is stored in the CDSS, or the system 202.
- the doctor may select an investigation mode when the doctor wants the CDSS to suggest one or more investigations and analyse the results of investigations based on the diagnosis.
- the end user may accept, reject or modify the suggested investigations or may also enter new investigations.
- the modified treatment is stored in the CDSS, or the system 202 and when new investigations are entered, then the new investigations are stored in the CDSS or the system 202. Further, the doctor may select the treatment mode, when the doctor wants the CDSS to suggest a treatment based on the results of the investigation. In some embodiments, the end user may accept, reject or modify the suggested treatment or may enter a new treatment. When the treatment is modified, then the modified treatment is stored in the CDSS, or the system 202, or when the end user enters the new treatment then the new treatment is entered in the CDSS or the system 202.
- the CDSS (e.g., the CDSS 106A) of the health care provider (See 102A in Figure 1A) reads patient’s data from the EHR system (See the EHR system 104A) of the health care provider.
- the EHR access module 302 enables the CDSS to the read the patient’s data from the EHR system.
- the CDSS analyses data to derive at least one of a diagnosis and a differential diagnosis.
- the diagnosis module 304 enables the CDSS to analyse the received patient’s data to derive at least one of a diagnosis and a differential diagnosis when an end user selects a diagnosis mode on the computing device. The end user is allowed to accept or reject the diagnosis or the differential diagnosis by providing an input at an interface on the computing device.
- the end user may be prompted by the CDSS to enter another diagnosis and the another diagnosis is received from the end user.
- the investigation module 306 suggests and displays a latest investigation based on at least one of the diagnosis, differential diagnosis and another diagnosis selected by the end user.
- the investigation module 306 determines the latest investigation based on at least one of the diagnosis, differential diagnosis and another diagnosis selected by the end user and enables the CDSS to display the same to the end user via a text-based interface on the computing device of the end user in real-time.
- the results of the investigations are received and saved in the CDSS.
- the results of the investigations may be saved in the storage module 204.
- the CDSS analyses the results of the investigations to determine a final diagnosis in real-time.
- the investigation module 306 enables the CDSS to analyse the results of the investigations to determine a final diagnosis in real-time.
- the final diagnosis may be displayed to the end user via a text-based interface.
- the CDSS determines a latest treatment protocol for the final diagnosis in real-time.
- the treatment module 310 may determine or may enable the CDSS to determine the latest treatment protocol for the final diagnosis in real-time.
- the risk factor analysis module 308 may calculate total risk for each of the risk factors for the final diagnosis and based on the risk factor analysis, the treatment module 310 may determine the latest treatment protocol.
- the CDSS displays the latest treatment protocol to the end user and updates the latest treatment protocol in the storage module of the CDSS creation and management system in real-time.
- a care plan is developed for the CDSS then once a diagnosis is selected by the end user, then display a list of scenarios on a text-based interface for the end user to select from. Once a particular scenario, is selected from text-based interface then display investigations and treatment protocols for the selected scenario from the diagnosis database in another text-based interface.
- an end user like a physician enters the patient history into their EHR system (See 104A of Figure 1A), which is either in hospital or in an ambulatory care.
- a temporary file may be created in one of the CDSSs 106A-106N such as, CDSS 106A.
- the system 110 (or the CDSSs 106A-106N) may utilize API’s - HL7 FfflR protocols to read data in the EHR system 104A.
- the following data may be copied into the temporary file from the EHR system, such as the EHR system 104 A, using the EHR Access Bridge: Medical Record Number of that patient (for hospital patients) or Medicare number (for all other patients) for identification during course of admission in hospital or during consultation in ambulatory care.
- the Medical Record Number or Medicare number will be used to identify the patient during admission or during consultation.
- a logfile may be created in the temporary file by using the following data from EHR of the patient daily or whenever EHR of the patient is updated/modified, using the EHR Access Bridge: date and time, symptoms, exam findings, investigations, results of the investigations, diagnoses, treatment (both pharmacological and non-pharmacological), bookmark the last actionable alert/advice in the CDSS 106A for the patient.
- the EHR Access Bridge may include interface(s) to allow the EHR system to securely access to the medical records of the patients.
- the temporary file may be deleted when the patient is discharged from hospital or discharged from consultation.
- the CDSS 106A reads this temporary file and logfile data and performs the analysis for suggesting at least one of a diagnosis, investigations, risks, and treatment in real-time based on the information stored in the storage module of the CDSS creation and management system 110.
- this logfile and temporary file data is entered into the diagnostic analysis algorithms to arrive at a diagnosis or differential diagnosis.
- This diagnosis is entered into the logfile data if different from the existing diagnosis.
- this CDSS response is displayed in the text-based response interface. If the diagnoses in the logfile is changed in any way then the screening starts from the beginning again.
- the physician may accept the recommendations of the CDSS response or not. If the physician decides on a diagnosis or differential diagnosis which is entered in their HER system, this diagnosis is noted by the CDSS (e.g., CDSS 106A), using the EHR Access Bridge and then copied into the logfile.
- CDSS e.g., CDSS 106A
- the CDSS 106A may suggest the latest investigations for each of those diagnoses according to the algorithm for Investigations.
- This CDSS response may be displayed in the text- based response interface.
- the results of the investigations return to the EHR system (e.g., the EHR system 104A)
- the results are noted by the CDSS 106A, using the EHR Access Bridge and then copied into the logfile.
- the CDSS 106A may analyse the results according to the algorithms for analysis of Investigations to make a final diagnosis. This CDSS 106A response is displayed in the text-based response interface.
- the CDSS 106A can then advise on the latest treatment protocol for that diagnosis according to the algorithm for Treatment. This CDSS response is displayed in the text-based response interface. At each stage the physician may or may not accept the recommendations of the CDSS 106A. When the patient returns for follow-up the CDSS 106A may then harvest patient specific data from the EHR system 104A using the EHR Access Bridge and then copied into the temporary file and logfile.
- the system 110 also has Data Analytic tools that analyses itself (i.e., the system 110) and its usage by the physicians and will issue alerts, so that the system 110 can improve that component and customise the application to the physician’s preferences.
- the system 110 provides one or more assist modes to the end user e.g., one or more assist modes that the physician can switch on or off if they so desire: diagnosis mode, investigation mode, and treatment mode.
- the system 110 may also include developer tool package, and data analytic tools.
- the developer tool package may include a Reference Relational Database, algorithms, and other maintenance tools.
- the system 110 may be used to develop a CDSS by entering medical content into a Reference Relational database.
- the CDSS that are developed by using the system 110 are called Root versions.
- the Root versions of CDSS can be customised by hospitals (or other health care provider 102A) to their individual requirements.
- CDSS encompassing all facets of medicine customised by different hospitals will result in a library of CDSS.
- the resources i.e., the CDSS library
- the hospital can edit CDSS in the library that have been developed by other hospitals to further customise to their requirements.
- the system 110 is compatible with any EHR system therefore the hospital is not locked in to their EHR vendor and can use the CDSS library easily.
- the reference relational database includes six components i.e., a diagnosis database, an investigation database, a risk factor analysis database, and a pharmacological database. [00184] Interaction between EHR system and the CDSS creation and management system 110 is explained below.
- the system 110 launches outside of the EHR System 104A, and also has its own User Interface i.e., it is independent of the EHR System Interface.
- the system 110 reads data in the EHR system 104A via the EHR Bridge (see page 5). Data from the EHR system 110 as specified in pages 6 and 7 is copied into Temporary file and logfile in CDSS as it is generated in the EHR system 110 and read.
- the CDSS (for example, 106A) is activated to commence the appropriate algorithm (Diagnosis, Investigation, Treatment as discussed above) and displays the response in its own user interface of the system 110.
- Disease progression refers to the complications of a disease on other (other than the primary organ affected by the disease) organ systems as the severity of the disease worsens.
- Prediction of disease deterioration refers to the ability to predict disease progression before the patient develops disease complications.
- the purpose of prediction is prevention of complications.
- the system 110 uses the concept of CDSS Swarm Artificial Intelligence.
- the other CDSS can combine this “transferred data” with its own locally programmed data to provide a higher level of analysis to the treating physician.
- This higher-level analytical data can be combined with Predictive algorithms at a much earlier period of disease activity to Predict Disease deterioration.
- the CDSS creation and management system of present disclosure may be a standalone platform that is compatible with any EHR system or platform.
- the CDSS creation and management system of present disclosure may allow the health care providers to develop standalone CDSS that can be connected or integrated with any EHR or EMR system.
- the CDSS creation and management system of the present disclosure may allow the users such as the health care providers to create one or more CDSSs and customize medical content of the CDSSs according to the health care provider’s requirements.
- the CDSS creation and management system of present disclosure may allow the health care providers to share developed CDSSs with one another via a library like a global library stored in the storage module of the CDSS creation and management system and further customize one another’s CDSS’s according to their own requirements.
- the data analytics built into the CDSS creation and management system of present disclosure may store the analysed data into the storage module of the CDSS creation and management system and also in respective CDSS of the health care providers.
- One or more machine learning algorithms of the analysis module of the system may learn from the analysed data and can improve performance of the CDSS creation and management system.
- the CDSS creation and management system may include at least 2 libraries of CDSSs: 1) Root versions - that are developed by the CDSS creation and management system and 2) Local Customised versions - to the local health care provider (or hospital). Each local health care provider will have its own local library of CDSSs that are customised to that health care provider. A local health care provider can only utilise a CDSS if it is assigned the local health care provider ID. [00197]
- the CDSS creation and management system allows any health care provider to access both CDSS libraries so that rapid and extensive CDSS deployment can occur. A health care provider can download a CDSS from the local library of another health care provider that has been already customised and further customise that CDSS and save it in their local library.
- the Root version library will contain CDSSs that have been developed by CDSS creation and management system. Each CDSS may be identified by its Clinical name. The root version is the starting point for customisation of the CDSS. Once the CDSS is customised, it is saved in the health care provider’s local customised library.
- a health care provider can download either a Root version of a CDSS or a customised version of a CDSS from another health care provider.
- the health care provider can either customise the Root version or further modify the already customised version of another health care provider’s CDSS and save this customisation in its own local library.
- each local library may have two directories: Final (each CDSS in this directory will have the local health care provider ID assigned to it) and Temporary (no ID assigned to it, making it unusable).
- the Temporary library may contain CDSSs that are in the process of being modified/edited.
- one physician in every health care provider e.g., a hospital may be assigned a security credential that will allow access to the two libraries. On presentation of the appropriate credential, the physician may be allowed access to the libraries to download and edit the content and on completion of this function to save the edited version in the local library.
- the CDSS creation and management system may allow to add a CDSS from the Root library to a local library by downloading the CDSS from the Root Library to the Temporary directory in local library; and editing the CDSS in the Temporary directory. On completion of customisation, the CDSS is transferred from the Temporary directory to Final directory.
- the CDSS creation and management system may assign the local health care provider ID to the customised CDSS, making it usable.
- the customised CDSS may be colour coded with a label of the date of customisation and author.
- the end user may download the customised CDSS from the Final directory of the (desired) health care provider to the Temporary directory of the local library of the (target) health care provider and edit the CDSS in the Temporary directory.
- the CDSS creation and management system may transfer the CDSS from the Temporary directory to the Final directory of the local health care provider.
- the customised CDSS will be assigned the local health care provider ID, making it usable.
- the customised CDSS may be colour coded with a label of the date of customisation and author.
- At least one of the Root library and Local Libraries may be located on the cloud server.
- the Final Directory of the local library specific to a hospital or health care provider may be downloaded from the cloud server onto the hospital’s or health care provider’s intranet.
- customisation and updating of CDSS can however only occur on the versions stored on the cloud server and not on the hospital or health care provider intranet. Once the CDSS in the local library on the cloud server is customized/updated it will automatically update the CDSS in the corresponding hospital’s or health care provider’s intranet.
- the CDSS created using the CDSS creation and management system can be connected or used with any of the existing or future developed electronic health record or electronic medical record (EMR) systems.
- the CDSS may be a stand-alone system that is compatible with any EHR or EMR systems.
- the CDSS created using the CDSS creation and management system may be integrated with the EHR or EMR systems.
- the CDSS may read data from the EHR system via the FHIR or CDS connect interface. The data from the EHR system may be copied into a temporary file and a logfile in the CDSS as it is generated in the EHR system and read.
- the words may trigger the CDSS via the CDS hooks interface for the appropriate response.
- the CDSS is activated to commence the appropriate algorithm or method (i.e., diagnosis, investigation, treatment method) stored in the storage module and display the response in its own interface.
- the CDSS creation and management system is configured for real-time data acquisition and analysis of the acquired data.
- the CDSS creation and management system may harvest (or receive) extensive raw de-identified clinical data in real-time from a plurality of health care providers (See 106A-106N of Figure IB).
- the CDSS creation and management system may aggregate the clinical data with similar data from other health care providers (e.g., hospitals) and then analyse the aggregated data for example by using one or more automated tools. The results of the analysis may be fed back into the relational database in the storage module of the system to replace ineffective or inferior protocols.
- the CDSS creation and management system is configured to perform two types of data analysis i.e., self-analysis of usage data and analysis of patient specific data.
- the self-analysis of the usage data may determine if Alerts of the CDSS are being utilised by the end users. For every Alert there will be an override function available for the end users. Then the system may compare the users next response in the EHR system and number of times the override function is used. The system may also determine if investigations, treatment protocols suggested by the CDSS are being used. The system may also compare the users next response in the EHR system to the protocols. The system may also determine if the Diagnosis is being utilised and accordingly compare the users next response in the EHR to the diagnosis in the protocols. If Investigations protocols are not followed vs being followed, then the system may compare costs of each and patient hospitalisation duration. The system may also observe symptoms and duration of hospitalisation for adherence to CDSS recommendations vs no adherence.
- the CDSS creation and management system of the present disclosure includes data analysis tools, structures and technology for medical research.
- the data analysis tools primarily include two components: 1) Database development: the researcher specifies the components of the database that they require for their research.
- the Empty Database is constructed using automated tools; 2) Data source location: the researcher specifies data sources. There may be 4 locations for data source: public hospitals, private hospitals, Specialists rooms, GP’s surgeries.
- an API may be constructed for the specified database. Both the Empty Database structure as specified by the researcher and the EHR Access Bridge specific for the database components are accessible from the cloud server where the CDSS libraries are stored, via presentation of appropriate security credentials.
- the Empty Database and the API’s can each only be accessed by the researcher and the location owner via credentials. It is the responsibility of the researcher to obtain the necessary approvals from the relevant authorities and present these approvals together with the appropriate location API credential to the location owner.
- the location owner has to give permission to the researcher to access their proprietary data archives via acceptance of the specified owner credential.
- the CDSS creation and management system may allow the researcher to download the empty database onto his local computer. The researcher can only access the empty database on the cloud server, via their specific researcher credential.
- the location owner downloads the specific EHR Access Bridge API for that location, from the cloud server onto their local computer network via presentation of the owner credential.
- the specified data is then extracted from the owner’s EHR system and copied into the empty database which is on the researcher’s computer.
- the CDSS creation and management system may analyse the patient specific data i.e., the de-identified data received from the health care providers.
- the CDSS of the health care providers may de-identify the data prior to sending the same to the CDSS creation and management system.
- Examples of the patient specific data from the temporary file or the log file may include, but are not limited to, an age, gender, ethnicity, past history (both medical and surgical), family history, social and occupational history, current medications, symptoms before and after treatment, signs before and after treatment (from logfile in temporary file), diagnosis, investigation results before and after treatment, cost of investigations (read from Investigations database or billing data in EHR system), treatment protocols, cost of medications (read from billing data in EHR), total cost of admission (read from billing data in EHR), duration of symptoms, duration of admission (read from billing data in EHR system), referral letters (from the EHR system).
- the CDSS creation and management system may enter data into corresponding columns of the database specific for patient data in the storage module (See 204 in the Figure 2).
- the temporary file may be deleted on discharge.
- the received patient data may be aggregated with data from other hospitals and physicians that have been using the same CDSS.
- the system may collate the data into relational database.
- the system may also include maintenance and editing tools, different type of data analytical display tools such as tables, charts, graphs etc., and data analytical and reporting tools.
- the analysed data is then available in various analysed formats to the physicians.
- the system may provide tools to re-configure and display data in various formats to the health care providers 106A-106N. Further, the analysed data may be fed back in to the CDSS and the in the storage module of the system by replacing pre-existing ineffective protocols.
- the CDSS creation and management system may be configured to generate revenue from sales of the CDSS library (i.e., the CDSS global library) and advertising within each CDSS.
- This advertising may be targeted to specific sections within each CDSS. Examples of the sections may include investigations for a given diagnosis, non-pharmacological treatment for a diagnosis, pharmacological treatment for a diagnosis and Risk factor advice for a diagnosis.
- the advertising by being extremely targeted to each diagnosis may therefore actually be assistive to the physician user.
- the advertising may be integrated into the advice being given to the end user (e.g., physician, nurse, hospital) and may not be gratuitous or superfluous and it may not look like advertising to the end user.
- the non-limiting examples of the targeted advertisements may include: For celiac disease investigation may include capsule endoscopy, gastroscopy, therefore the advertisers can be gastroenterologists.
- celiac disease non-pharmacological treatment the advertisers may be dietitians, gluten free food manufacturers and stores selling gluten free foods.
- diabetes type 1, 2 non-pharmacological treatment e.g., diet, weight control
- the advertisers may be dietitians, gyms/personal trainers and so forth.
- the advertisers may be pharmaceutical companies.
- each advertiser is actually assisting the physician in managing the patient for that particular diagnosis.
- the CDSS creation and management system allows each hospital to develop their own CDSS, customised to their requirements.
- the system may also allow the hospitals to share CDSS that have been developed by other hospitals across all EHR IT platforms. This in turn may allow an enormous library of CDSSs to be developed rapidly, all of which can be customisable.
- the disclosed CDSS creation and management system is designed to assist physicians in the hospitals, hospices, nursing homes, and in ambulatory care such as specialists, primary care physicians including General Practitioners in private practice, in making a diagnosis, ordering the right investigations, interpreting results of investigations and treatment protocols.
- the disclosed CDSS creation and management system may allow each hospital to develop their own CDSS and customise CDSS to their own requirements and to share CDSS that have been developed by other hospitals across all EHR systems. This allows an enormous library of CDSS to be developed rapidly, all of which can be customisable and shareable and allows for an exponential expansion of the knowledge base.
- the disclosed CDSS creation and management system stores clinical knowledge, medical evidence and healthcare analytics, technical specifications, medical content and data analytics different from every other CDSS.
- the disclosed CDSS creation and management system is a point of care, stand-alone, cloud based, scalable system.
- the disclosed CDSS creation and management system differs from all other CDSS in that it can be made compatible with any EHR system or EHR IT platform.
- the disclosed CDSS creation and management system is Cloud based i.e., a one central location in which to make modifications and will be instantly available to all users.
- the CDSS library is extensive and can ultimately cover every facet of medicine, and is constantly being edited and updated. They may include the newly burgeoning fields of genomics and proteomics, imaging, photo (syndromes, dermatological, ophthalmological etc) databases and incorporate medical telemetry.
- the disclosed CDSS creation and management system differs from all other CDSS in that the hospital can develop its own customised CDSS to their own requirements and can share the library of CDSS with other hospitals.
- the disclosed CDSS creation and management system also includes data analytics tools (may also be referred as Sophia), which facilitates medical research via provision of tools and technology.
- data analytics tools may also be referred as Sophia
- the disclosed CDSS creation and management system have complex and extensive data analytics built in. They include self-analysis of system’s usage as well as data, self-analysis of patient specific diagnosis, investigations and treatment protocols. System’s usage. The results feedback into the CDSS creation and management system. The machine learning algorithms learn from these results and will continue to improve the CDSS creation and management system performance.
- the design of CDSS creation and management system features a novel mechanism of revenue generation, namely targeted advertising.
- the CDSS creation and management system may be a point of care, stand-alone, cloud based, scalable system.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Bioethics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
Claims
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021200650A AU2021200650A1 (en) | 2020-02-14 | 2021-01-28 | Systems and methods for creating and managing clinical decision support systems |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2020900422 | 2020-02-14 | ||
AU2020900422A AU2020900422A0 (en) | 2020-02-14 | Systems And Methods For Creating And Managing Clinical Decision Support Systems |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021159167A1 true WO2021159167A1 (en) | 2021-08-19 |
Family
ID=77291305
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/AU2021/050055 WO2021159167A1 (en) | 2020-02-14 | 2021-01-28 | Systems and methods for creating and managing clinical decision support systems |
Country Status (2)
Country | Link |
---|---|
AU (1) | AU2021200650A1 (en) |
WO (1) | WO2021159167A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113744838A (en) * | 2021-09-08 | 2021-12-03 | 杭州康晟健康管理咨询有限公司 | Parkinson's motion rehabilitation intelligent management system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140100881A1 (en) * | 2012-10-08 | 2014-04-10 | Delaware Valley Outcomes Research | Computer method for exploring drugs in disease |
US20160188822A1 (en) * | 2014-12-30 | 2016-06-30 | Cerner Innovation, Inc. | Clinical decision support rule generation and modification system and methods |
WO2019045637A2 (en) * | 2017-08-28 | 2019-03-07 | Agency For Science, Technology And Research | A predictive analytics solution for personalized clinical decision support |
US10452981B1 (en) * | 2011-06-30 | 2019-10-22 | Allscripts Software, Llc | Clinical decision support systems, apparatus, and methods |
-
2021
- 2021-01-28 AU AU2021200650A patent/AU2021200650A1/en not_active Abandoned
- 2021-01-28 WO PCT/AU2021/050055 patent/WO2021159167A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10452981B1 (en) * | 2011-06-30 | 2019-10-22 | Allscripts Software, Llc | Clinical decision support systems, apparatus, and methods |
US20140100881A1 (en) * | 2012-10-08 | 2014-04-10 | Delaware Valley Outcomes Research | Computer method for exploring drugs in disease |
US20160188822A1 (en) * | 2014-12-30 | 2016-06-30 | Cerner Innovation, Inc. | Clinical decision support rule generation and modification system and methods |
WO2019045637A2 (en) * | 2017-08-28 | 2019-03-07 | Agency For Science, Technology And Research | A predictive analytics solution for personalized clinical decision support |
Also Published As
Publication number | Publication date |
---|---|
AU2021200650A1 (en) | 2021-09-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pendergrass et al. | Using electronic health records to generate phenotypes for research | |
JP6780520B2 (en) | Systems and methods for assessing patient risk using open data and clinician input | |
US10885150B2 (en) | System and a method for assessing patient treatment risk using open data and clinician input | |
US9536052B2 (en) | Clinical predictive and monitoring system and method | |
Halamka | Early experiences with big data at an academic medical center | |
US20170132371A1 (en) | Automated Patient Chart Review System and Method | |
JP7035314B2 (en) | Systems and methods to assist patient diagnosis | |
US20110093295A1 (en) | Consumer enabling system for personalized health maintenance | |
Keehbauch et al. | Increased documentation and management of pediatric obesity following implementation of an EMR upgrade and education | |
US8630448B1 (en) | Method and system for image-based nutrition/health monitoring | |
Bellazzi et al. | Big data technologies: new opportunities for diabetes management | |
WO2019155267A1 (en) | Integrative medical technology artificial intelligence platform | |
Cooper et al. | Geographical variation in health spending across the US among privately insured individuals and enrollees in Medicaid and Medicare | |
US11688510B2 (en) | Healthcare workflows that bridge healthcare venues | |
WO2021159167A1 (en) | Systems and methods for creating and managing clinical decision support systems | |
Neprash et al. | Association of evaluation and management payment policy changes with Medicare payment to physicians by specialty | |
Ong et al. | Effective regulation of digital health technologies | |
Adebayo et al. | Exploring the effectiveness of artificial intelligence, machine learning and deep learning in trauma triage: A systematic review and meta-analysis | |
GB2548627A (en) | A system and a method for assessing patient treatment risk using open data and clinician input | |
Socal et al. | Ownership and interoperability challenges of Alzheimer monoclonal antibody registries | |
US20220188281A1 (en) | Automated transformation documentation of medical data | |
US20220189592A1 (en) | Automated transformation documentation of medical data | |
US20220189596A1 (en) | Automated transformation documentation of medical data | |
Ioerger et al. | How to Fully Leverage the Power of Electronic Health Records for Research—Self-Service Analytics | |
Vezertzis et al. | Development of patient databases for endocrinological clinical and pharmaceutical trials: a survey |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2021200650 Country of ref document: AU Date of ref document: 20210128 Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21753194 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21753194 Country of ref document: EP Kind code of ref document: A1 |