WO2023242878A1

WO2023242878A1 - System and method for generating automated adaptive queries to automatically determine a triage level

Info

Publication number: WO2023242878A1
Application number: PCT/IN2023/050578
Authority: WO
Inventors: Anmol SINGH; Kumar SHUBHAM; Ankush Patel; Lavish MAHESHWARI; Sanskriti A; Singamsetty Sanjeeva Krishna SAI DINESH; Abhishek Joshi; Ima RASHID; Harshit AGRAWAL; Sreevidya K V; Mayank NEGI; Chaitanya BHARADWAJ; Abdussamad G M
Original assignee: Apollo Healthco Limited
Priority date: 2022-06-17
Filing date: 2023-06-17
Publication date: 2023-12-21

Abstract

The system and a computer-implemented method for generating automated adaptive queries to automatically determine a triage level is provided. The method includes (a) receiving unstructured text input provided by the user in response to a query, (b) disambiguating distinct entities and concepts using a NLP model to obtain a context of the user, (c) performing relation extraction between the distinct entities concepts to detect a manifestation of anomalies, (d) automatically generating an updated personalized medical history and context of the user, (e) determining a flagging sign based on responses, (f) automatically generating a second updated query by using the adaptive query generation model with the flagging sign, (g) and automatically determining a triage level of the user using a triage determination model with a response to the second updated query.

Description

SYSTEM AND METHOD FOR GENERATING AUTOMATED ADAPTIVE QUERIES TO AUTOMATICALLY DETERMINE A TRIAGE LEVEL BACKGROUND

Technical Field

[0001] The embodiments herein generally relate to artificial intelligence (Al) and Natural Language Processing (NLP), and more particularly, to a system and method for generating automated adaptive queries to automatically determine a triage level for decision support and providing recommendations to users and/or medical professionals.

Description of the Related Art

[0002] In the field of healthcare, accurate and efficient triage plays a critical role in determining the urgency and priority of medical care for patients. Traditional methods of triage often involve a series of manual questioning by healthcare professionals to gather information about the patient's symptoms, medical history, and current condition. However, these traditional approaches are associated with several technical challenges that hinder their effectiveness and efficiency.

[0003] A key technical problem is asking relevant questions based on the context and medical history of the user. Obtaining comprehensive and accurate information from patients is essential for accurate triage, but it is challenging to identify the most relevant questions to ask in a given situation. Healthcare professionals often face difficulties in tailoring their inquiries to specific condition of an individual, which leads to missing critical details or asking unnecessary questions.

[0004] Another technical problem is capturing the symptoms of the user in a minimal number of questions. Gathering information about the symptoms is crucial for triage, but lengthy and repetitive questioning processes can be burdensome for both the patient and the healthcare system.

[0005] Moreover, optimizing admissions to medical establishments is essential to prevent overburdening emergency healthcare facilities. By accurately determining the triage level remotely, unnecessary hospital visits can be avoided, reducing the strain on emergency medical establishments. [0006] Accordingly, there remains a need of addressing the aforementioned technical problems using method for generating automated adaptive queries to automatically determine a triage level.

SUMMARY

[0007] In view of the foregoing, according to a first aspect, there is provided a method for generating automated adaptive queries to automatically determine a triage level. The method comprising (a) receiving, from a user interface, unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user, (b) disambiguating at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the user, (c) performing relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly, (d) automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model that personalizes the updated query based on a medical history and the context of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly, (e) presenting the updated query to the user using a text-based conversation at the user interface and recording, from the user interface, a set of responses of the updated query, (f) determining at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data, (g) automatically generating a second updated query by using the adaptive query generation model with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign, and (h) automatically determining a triage level of the user by using a triage determination model with a response to the second updated query.

[0008] The method is of advantage that the method enhances the user interface (UI) by asking only relevant queries that are personalized the context and medical history of the user. By focusing on the specific information needed for triage determination, the method captures the symptoms of the user in a reduced number of questions, saving valuable time and effort for both the user.

[0009] Furthermore, the method is of advantage that it optimizes computational resources by minimizing the number of queries required to capture the symptoms of the user and determine the triage level of the user. By avoiding repetitive queries, the method efficiently utilizes its computing power for running the adaptive query generation model to generating queries, leading to improved performance and reduced resource consumption. The method eliminates repetitive and irrelevant questions using the adaptive query generation model that adapts the queries based on the context of the user, the manifestation of anomalies and the medical history of the user.

[0010] Additionally, by enabling remote triage determination, the method helps alleviate the burden on emergency medical establishments. With the ability to determine the triage level remotely, unnecessary admissions to medical facilities are avoided, ensuring that limited resources are allocated to those who require immediate attention, thus optimizing the overall efficiency of a healthcare system.

[0011] In some embodiments, the method further comprises performing (a) generating a triage case sheet or triage protocol for the triage inquiry when the triage level is below the predetermined threshold, and (b) repeating the method of claim 1 until the triage level exceeds the predetermined threshold.

[0012] In some embodiments, the method further comprises analyzing the context of the named entities and relations extracted from the unstructured text to determine a presence or an absence of negation in the response from the user.

[0013] In some embodiments, the adaptive query generation model is trained by utilizing a learning process that incorporates at least one of Unified Medical Language System (UMLS), International Classification of Diseases (ICD), personal health record, historical consultations of users.

[0014] In some embodiments, the method further comprises further comprising generating, using the adaptive query generation model, at least one multiple choice question that comprises a plurality of choices to describe the current or past state of the user the user interface comprises, and providing the at least one multiple choice question to the user in a conversational chat-box at the user interface, wherein the conversational chat-box provides a visual cue or multi-lingual support for the user to describe the current or past state of the user.

[0015] In some embodiments, the triage determination model comprises a Bayesian probabilistic causation model that is trained by (i) obtaining at least one of (a) real-world data of patients generated by a hospital, (b) publicly available clinical data that comprises symptoms, expert surveys data, triage and clinical pathways in a digitized form, (ii) determining probabilities associated with the historical pathways and outcomes, and (iii) training the Bayesian probabilistic causation model by dynamically constructing a knowledge graph that captures relationships between the flagging sign and triage levels as probabilities.

[0016] In another aspect, there is provided a system for generating automated adaptive queries to automatically determine a triage level. The system comprises an automated adaptive query server that comprises a processor and a memory that are configured to perform: (a) receiving, from a user interface, unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user, (b) disambiguating at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the user, (c) performing relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly, (d) automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model that personalizes the updated query based on a medical history and the context of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly, (e) presenting the updated query to the user using a text-based conversation at the user interface and recording, from the user interface, a set of responses of the updated query, (f) determining at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data, (g) automatically generating a second updated query by using the adaptive query generation model with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign, and (h) automatically determining a triage level of the user by using a triage determination model with a response to the second updated query. [0017] The system is of advantage that the system enhances the user interface (UI) by asking only relevant queries that are personalized the context and medical history of the user. By focusing on the specific information needed for triage determination, the system captures the symptoms of the user in a reduced number of questions, saving valuable time and effort for both the user.

[0018] Furthermore, the system is of advantage that it optimizes computational resources by minimizing the number of queries required to capture the symptoms of the user and determine the triage level of the user. By avoiding repetitive queries, the system efficiently utilizes its computing power for running the adaptive query generation model to generating queries, leading to improved performance and reduced resource consumption. The system eliminates repetitive and irrelevant questions using the adaptive query generation model that adapts the queries based on the context of the user, the manifestation of anomalies and the medical history of the user.

[0019] Additionally, by enabling remote triage determination, the system helps alleviate the burden on emergency medical establishments. With the ability to determine the triage level remotely, unnecessary admissions to medical facilities are avoided, ensuring that limited resources are allocated to those who require immediate attention, thus optimizing the overall efficiency of a healthcare system.

[0020] In some embodiments, the system is further configured to performing (a) generating a triage case sheet or triage protocol for the triage inquiry when the triage level is below the predetermined threshold, and (b) repeating the method of claim 1 until the triage level exceeds the predetermined threshold, wherein the context of the named entities and relations extracted from the unstructured text are analyzed to determine a presence or an absence of negation in the response from the user.

[0021] In some embodiments, the system is further configured to generate, using the adaptive query generation model, at least one multiple choice question that comprises a plurality of choices to describe the current or past state of the user the user interface comprises, and providing the at least one multiple choice question to the user in a conversational chat-box at the user interface, wherein the conversational chat -box provides a visual cue or multi-lingual support for the user to describe the current or past state of the user.

[0022] In some embodiments, the triage determination model comprises a Bayesian probabilistic causation model that is trained by (i) obtaining at least one of (a) real-world data of patients generated by a hospital, (b) publicly available clinical data that comprises symptoms, expert surveys data, triage and clinical pathways in a digitized form, (ii) determining probabilities associated with the historical pathways and outcomes, and, (iii) training the Bayesian probabilistic causation model by dynamically constructing a knowledge graph that captures relationships between the flagging sign and triage levels as probabilities. [0023] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:

[0025] FIG. 1 illustrates a system for generating automated adaptive queries to automatically determine a triage level according to an embodiment herein;

[0026] FIGS. 2A and 2B illustrate a user interface of triage creation and review for a patient according to an embodiment herein;

[0027] FIG. 2C illustrates a flow diagram of triage determination for a patient according to an embodiment herein;

[0028] FIG. 3A illustrates an assistance system for providing medical recommendations based on user inputs using an Artificial Intelligence (Al) model according to an embodiment herein; [0029] FIG. 3B illustrates an exploded view of a data processing unit of FIG. 2A according to an embodiment herein;

[0030] FIG. 3C illustrates an exemplary view of a parsing architecture of a data processing unit of FIG. 3 A according to an embodiment herein;

[0031] FIG. 4 illustrates an exemplary block diagram of a reasoning unit of FIG. 2 according to an embodiment herein;

[0032] FIGS. 5A to 4D illustrate a user interface of an assistance system for assisting a patient at a patient device according to an embodiment herein;

[0033] FIGS. 6A to 6F illustrate a user interface of an assistance system for providing medical assistance to a patient in a doctor consultation setting according to an embodiment herein;

[0034] FIG. 7 illustrates an exemplary process flow diagram of an assistance system for providing medical recommendations according to an embodiment herein; [0035] FIGS. 8A-B is a flow diagram illustrating a computer-implemented method of generating automated adaptive queries to automatically determine a triage level according to an embodiment herein;

[0036] FIG. 9 illustrates an exploded view of an assistance system of FIG. 1 according to an embodiment herein; and

[0037] FIG. 10 illustrates a schematic view of a hardware configuration of device management/ computer architecture according to an embodiment herein.

DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

[0038] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0039] In the view of the foregoing, the need for a method for generating automated adaptive queries to automatically determine a triage level is fulfilled in the ongoing description by: (a) receiving, from a user interface, unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user, (b) disambiguating at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the user, (c) performing relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly, (d) automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model that personalizes the updated query based on a medical history and the context of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly, (e) presenting the updated query to the user using a text-based conversation at the user interface and recording, from the user interface, a set of responses of the updated query, (f) determining at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data, (g) automatically generating a second updated query by using the adaptive query generation model with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign, and (h) automatically determining a triage level of the user by using a triage determination model with a response to the second updated query.

[0040] Referring now to the drawings, and more particularly to FIGS. 1 through 10, where similar reference characters denote corresponding features consistently throughout the figures^ there are shown preferred embodiments.

[0041] FIG. 1 illustrates a system for generating automated adaptive queries to automatically determine a triage level according to an embodiment herein. The system 100 includes one or more users 102A-N that are associated with a plurality of user devices 104A-N that are communicatively connected to a distributed cloud 108 via a data communication network 106. The data communication network 106 may be one or more of a wired network, a wireless network, a combination of the wired network and the wireless network or the Internet. The user devices 104A-N include, but are not limited to, a mobile device, a smartphone, a smart watch, a notebook, a Global Positioning System (GPS) device, a tablet, a desktop computer, a laptop or any network enabled device, the distributed cloud 108 comprises an automated adaptive query server 110 and an adaptive query generation model 112.

[0042] The automated adaptive query server 110 is configured to receive, from a user interface at the one or more user devices 104A-N, unstructured text input from one or more users 102A- N, wherein the unstructured text is provided by the one or more users 102A-N in response to a query and comprises current or past state of the one or more users 102A-N.

[0043] The automated adaptive query server 110 disambiguates at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the the one or more users 102A-N. the automated adaptive query server 110 performs relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly.

[0044] The automated adaptive query server 110 automatically generates an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model that personalizes the updated query based on a medical history and the context of the one or more users 102A-N, wherein the updated query inquires the one or more users 102A-N for additional information associated with the manifestation of the at least one anomaly.

[0045] The automated adaptive query server 110 presents the updated query to the one or more users 102A-N using a text-based conversation at the user interface at the one or more user devices 104A-N and recording, from the user interface at the one or more user devices 104A- N, a set of responses of the updated query, the automated adaptive query server 110 determines at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data.

[0046] The automated adaptive query server 110 automatically generates a second updated query by using the adaptive query generation model with the flagging sign, wherein the second updated query inquires the one or more users 102A-N for additional information associated with the flagging sign.

[0047] The automated adaptive query server 110 automatically determines a triage level of the one or more users 102A-N by using a triage determination model with a response to the second updated query.

[0048] The system 100 is of advantage that the system 100 enhances the user interface (UI) by asking only relevant queries that are personalized the context and medical history of the user. By focusing on the specific information needed for triage determination, the system 100 captures the symptoms of the user in a reduced number of questions, saving valuable time and effort for both the user.

[0049] Furthermore, the system 100 is of advantage that it optimizes computational resources by minimizing the number of queries required to capture the symptoms of the user and determine the triage level of the user. By avoiding repetitive queries, the system 100 efficiently utilizes its computing power for running the adaptive query generation model to generating queries, leading to improved performance and reduced resource consumption. The system 100 eliminates repetitive and irrelevant questions using the adaptive query generation model that adapts the queries based on the context of the user, the manifestation of anomalies and the medical history of the user.

[0050] Additionally, by enabling remote triage determination, the system 100 helps alleviate the burden on emergency medical establishments. With the ability to determine the triage level remotely, unnecessary admissions to medical facilities are avoided, ensuring that limited resources are allocated to those who require immediate attention, thus optimizing the overall efficiency of a healthcare system 100.

[0051] In some embodiments, the method further comprises performing (a) generating a triage case sheet or triage protocol for the triage inquiry when the triage level is below the predetermined threshold, and (b) repeating the method of claim 1 until the triage level exceeds the predetermined threshold.

[0052] In some embodiments, the system 100 further comprises analyzing the context of the named entities and relations extracted from the unstructured text to determine a presence or an absence of negation in the response from the user.

[0053] In some embodiments, the adaptive query generation model is trained by utilizing a learning process that incorporates at least one of Unified Medical Language System (UMLS), International Classification of Diseases (ICD), personal health record, historical consultations of users.

[0054] In some embodiments, the system 100 further comprises further comprising generating, using the adaptive query generation model, at least one multiple choice question that comprises a plurality of choices to describe the current or past state of the user the user interface comprises, and providing the at least one multiple choice question to the user in a conversational chat-box at the user interface, wherein the conversational chat-box provides a visual cue or multi-lingual support for the user to describe the current or past state of the user.

[0055] In some embodiments, the triage determination model comprises a Bayesian probabilistic causation model that is trained by (i) obtaining at least one of (a) real-world data of patients generated by a hospital, (b) publicly available clinical data that comprises symptoms, expert surveys data, triage and clinical pathways in a digitized form, (ii) determining probabilities associated with the historical pathways and outcomes, and (iii) training the Bayesian probabilistic causation model by dynamically constructing a knowledge graph that captures relationships between the flagging sign and triage levels as probabilities.

[0056] With reference to the FIG. 1, FIG. 2A and 2B illustrate a user interface of triage knowledge -base creation according to an embodiment herein. In some embodiments, triage creation 202 and one or more triage reasoning editing options 204A-N. In some embodiments, the triage dashboard includes two process pages for triage creation 202 and triage reviewer 206. The doctors of the organisation utilize the triage creation as a process page while preparing the triage case sheets or protocols. Experts of the organisation validate and provide feedbacks on the triage case sheets on the triage reviewer page.

[0057] With reference to the FIG. 2, FIG. 2C illustrate a flow diagram of triage determination for a patient according to an embodiment herein. At step 2002, the triage determination unit 210 checks for a flagging sign and a new triage when inquiry is received. At step 2004, the triage determination unit 210 generates the reasoning and reports for the inquiry when the flagging sign and the new triage is greater than a predetermined level. At step 2006, the triage determination unit 210 checks for the triage inquiry and the triage case sheet or triage protocol is generated for the triage inquiry when the flagging sign and the new triage is less than a predetermined level. The process is repeated until the flagging sign and the new triage is greater than a predetermined level. In some embodiments, the recommendation unit 212 provides medical recommendations for the user using the report. In some embodiments, the medical recommendations include at least one of Differential Diagnosis, Fab, imaging, Inquiry, medication prescription, assessment, treatment plan.

[0058] With reference to FIG. 2, FIG. 3 A illustrates an exploded view of the assistance system 300 for providing the medical recommendations based on the user inputs using the Artificial Intelligence (Al) model according to an embodiment herein. The assistance system 300 includes a database 302, an automated adaptive query server 110, a data processing unit 306, a reasoning unit 308, a triage determination unit 310 and a recommendation unit 312. The database 302 stores at least one of real time data from the organization, a clinical knowledge base, triage and clinical pathways in a digitized form or a digitized clinical content from medical journals. The data from the organization includes at least one of de-identified, real- world hospital generated patient data, publicly available clinical data such as MIMIC and Pubmed datasets or parsed data that is constructed as knowledge graphs, where relationships are captured as probabilities. The clinical knowledge base includes at least one of data that is curated by a team of in-house doctors, peer reviewed by organization specialists, case sheets cover clinical background, care and management, treatment options, discharge advice. In some embodiments, data is ingested into Artificial Intelligence (Al) models 316 periodically to update. The automated adaptive query server 110 includes one or more application programming interfaces that enables at least one of the end users (example: patient and doctor) to provide inputs and access the medical recommendations. [0059] The data processing unit 306 obtains the inputs from the end user and transforms into an analyzed data. The analyzed data includes one or more medical condition and one or more medical recommendations provided for similar medical conditions.

[0060] The reasoning unit 308 determines the medical recommendations along with justification to the user responses using the Artificial Intelligence (Al) models 316. In some embodiments, the reasoning unit 308 acts as a brain and connects dots together for the assistance system 300. In some embodiments, the reasoning unit 308 is aware of patient demographics, medical history - details such as chronic conditions, surgeries, family medical history etc. The reasoning unit 308 analyses every detail such as symptoms, symptom attributes, vitals, lab/imaging results, comorbidity, hospitalization history, etc. using clinical knowledge base, millions of patient records and user inputs. The reasoning unit 308 dynamically creates a graph with possible outcomes and calculates probabilities associated with each path. In some embodiments, the graph is converted into actions or recommendations such as Differential diagnosis, Lab, imaging, medication prescription, Assessment, Treatment, Management, etc.

[0061] The triage determination unit 310 determines a triage level using the Artificial Intelligence (Al) models 316. The triage determination unit 310 includes triage protocols to determine the triage level. In some embodiments, the triage protocols were selected as per body system category. In some embodiments, the triage protocols include at least one of Cardiac, Respiratory, Neurology, Gastrointestinal or Mental health flagging signs. In some embodiments, Pediatrics and Pregnancy Related emergency protocols are also captured for body systems. The system covers 5000+ Triage protocols. The triage case sheet is a user- friendly triage dashboard that is built to create and edit the triage protocols. The triage level is briefed, and the triage case sheets are reviewed by the doctors of the organization.

[0062] The following table “Table 1” illustrates experimental data illustrating responses from the one or more users 102A-N, manifestation of an anomaly.

Table 1

[0063] With reference to the FIG. 3A, FIG. 3B illustrates an exploded view of the data processing unit 306 of FIG. 3A according to an embodiment herein. The data processing unit 306 includes a Natural Language Processing (NLP) system 314, the Artificial Intelligence (Al) models 316 and a computation system 318. In some embodiments, the computation system 314 performs computations on billions of data points. The computation system 314 includes a spark based scalable cluster computational framework 320. The computation system parses medical notes and builds knowledge graph. The Artificial Intelligence (Al) models 316 include a symptom checker module 322 to predict diagnosis from symptoms. The symptom checker module 322 capture symptoms, diagnosis and relationships between them as knowledge. In some embodiments, the Artificial Intelligence (Al) models 316 include a Bayesian probabilistic causation model 324 for predicting disease probability from symptoms. In some embodiments, the Artificial Intelligence (Al) models 316 include a symptom inquiry model 326 that suggests unreported symptoms. In some embodiments, the Artificial Intelligence (Al) models 316 include a neural network model 328 that captures relationships between medical entities and recommendations provided by the medical entities. The Artificial Intelligence (Al) models 316 capture graphs Patient demography, history and its impact on knowledge graph.

[0064] In some embodiments, the data processing unit 306 generates the Natural Language Processing (NLP) system 314 based on open-source technologies (example: Apache C-takes). In some embodiments, the Natural Language Processing (NLP) system 314 includes various stages of processing that includes (a) pre-processing, (b) Natural Language Processing (NLP) parsing, (c) unified medical language system (UMLS) lookup system for normalizing & standardizing clinical terms, (d) entity-entity relationship identification and (e) knowledge graph extraction and medical language modeling. The Natural Language Processing (NLP) system 314 classifies medical terms such as symptoms, diagnosis, medication, history etc. The Natural Language Processing (NLP) system 314 identifies assertions and relationships between entities such as onset, severity, duration, location etc. In some embodiments, the preprocessing includes spell correct, abbreviation expansion, substitution etc. In some embodiments, the Unified Medical Language System (UMLS) is a compendium of many controlled vocabularies in biomedical sciences. The unified medical language system provides a mapping structure among vocabularies that allows one to translate among a various terminology system for interoperability. The Unified Medical Language System (UMLS) provides facilities for Natural Language Processing (NLP) and that is intended to be used mainly by developers of medical informatics systems. In some embodiments, the Metathesaurus forms are the base of the Unified Medical Language System (UMLS). The Metathesaurus construction understands the intended meaning of each name in each source vocabulary and to link all the names that mean the same thing (the synonyms). In some embodiments, the examples of the incorporated controlled vocabularies include at least one of CPT, ICD-10, MeSH, SNOMED CT, LOINC, WHO Adverse Drug Reaction Terminology or RxNorm. A Concept Unique Identifier (CUI) is assigned to a meaning or a term which includes many different names.

[0065] The Natural Language Processing (NLP) system 314 performs at least one action of (a) normalizing clinical text, (b) extracting medical concepts out of free text, (c) identifying associations and relevance of medical concepts and (d) understanding context and user intent for Natural language understanding (NLU) systems. In some embodiments, the data processing unit 306 utilizes the database 302 as a knowledge base database to store at least one of digitized clinical contents from journals, digitized publicly available data sources, physician/expert knowledge from surveys, medical domain knowledge repository, triage and clinical pathways in a digitized form or parsed clinical information.

[0066] With reference to the FIG. 3A, FIG. 3C illustrates an exemplary view of a parsing architecture 330 of the data processing unit 306 of FIG. 3 A according to an embodiment herein. In some embodiments, the Natural Eanguage Processing (NEP) parsing includes stemming, lemmatizing, sentence segmentation, word tokenization, stop words removal, part-of-speech recognition, dependency passing, nouns and named entity recognition etc. The Natural Eanguage Processing (NLP) parsing includes named entity recognition, relation extraction, entity linking and negation detection. The named entity recognition detects words and phrases mentioned in unstructured text that is associated with one or more semantic types, such as diagnosis, medication name, symptom/sign, or age. The relation extraction identifies meaningful connections between concepts mentioned in text. For example, a "time of condition" relation is found by associating a condition name with a time. The entity linking disambiguates distinct entities by associating named entities mentioned in text to concepts found in a predefined database of concepts. For example, the Unified Medical Language System (UMLS). In some embodiments, the meaning of medical content is highly affected by modifiers such as negation, which includes critical implication if misdiagnosed. Text Analytics for health supports negation detection for the different entities mentioned in the text.

[0067] With reference to the FIG. 3, FIG. 4 illustrates an exemplary block diagram of a reasoning unit 308 of FIG. 3 according to an embodiment herein. The block diagram includes a computational cloud 108, a clinical knowledge base 404, a real-world data 406, a reinforcement learning model 408, a clinical Natural Language Processing (NLP)/ Natural Language Understanding (NLU) system 410 and conversational AI/(Natural Language Generation) NLG module 412. In some embodiments, the clinical NLP/NLU system 410 is communicatively connected with the computational cloud 108, the clinical knowledge 404, the real-world data 406, the reinforcement 408 and the reasoning unit 308. The computational cloud 108 provides previous case history to the clinical NLP/NLU system 410. The clinical knowledge 404 captures at least one of latest disease specific assessment, diagnosis and management details from specialists or journals. The clinical Natural Language Processing (NLP)/ Natural Language Understanding (NLU) 410 identifies clinical concepts, phrases, context, relationships. The reasoning unit 308 determines the medical recommendations along with justification to the user responses using the Artificial Intelligence (Al) model. In some embodiments, real-world data includes at least one of de -identified, real world hospital generated patient data, publicly available clinical data such as MIMIC and Pubmed datasets or parsed data that is constructed as knowledge graphs where relationships are captured as probabilities. The conversational AI/NLG module 412 enables inquiry with the user by providing an intelligent query to the user based on a response of the user to a previous query.

[0068] With reference to the FIG. 4, FIGS. 5A to 5D illustrate a user interface of an assistance system 300 for assisting a patient at a patient device according to an embodiment herein. The assistance system 300 provides a symptom checker for patients to obtain the user responses. The user interface of the symptom checker includes a guide 502, a disclaimer 504, symptom assessment 506, a symptom assessment report 508, medical recommendations 510. In some embodiments, the guide 502 includes one or more instructions that include “tell us your symptoms, your answers will be carefully analyzed, review possible causes etc.”. In some embodiments, the symptom assessment 506 includes one or more multiple choice questions and an option to describe the symptoms. In some embodiments, the symptom assessment report 508 includes one or more medical conditions related to the symptoms. In some embodiments, the medical recommendations 510 includes suggested lab, imaging tests and/or speciality for doctor consultation.

[0069] With reference to the FIG. 3A-C, FIGS. 6A to 6F illustrate a user interface of providing medical assistance to a patient in a doctor consultation setting according to an embodiment herein. The virtual consultation room enables the user to provide the medical conditions of the user using one or more queries 602 and briefs the medical conditions 604 for the doctor. The one or more queries 602 are generated based on the user response to a query. The user is enabled to report more medical conditions on any other symptoms option 606. The one or more queries 602 includes multiple choices and the option 606 to describe the symptoms. The choices may include, for example, sore throat, nasal congestion, coryza, ear pain etc. In some embodiments, the medical conditions include a summary that is determined based on the user inputs. The summary may include at least one of age, height, weight, medicine allergies, food allergies, a type of medical condition or a duration of medical condition and associated details. In some embodiments, the summary is provided to the user.

[0070] With reference to the FIG. 4, FIG. 7 illustrates an exemplary process flow diagram of an assistance system 300 for providing medical recommendations according to an embodiment herein. At step 702, model inputs are provided by the Artificial Intelligence (Al) model. The model inputs include demographic details, patient history, complaints/ symptoms. In some embodiments, the demographic details include age, gender, location and social-economic backgrounds. In some embodiments, the patient history includes chronic conditions, short term conditions, medications currently taken, allergies and surgeries. In some embodiments, the complaints/ symptoms include headache, fever, onset, severity, lab data and imaging reports. At step 704, the Artificial Intelligence (Al) model performs a learning process using UMLS, ICDs, open data, Personal Health Record (PHR), predicted symptoms, consultations/ user actions and the model inputs. At step 706, the assistance system 300 provides queries to the user to obtain more medical condition details using an automated adaptive query server 110. The user responses to the queries are constructed as the model inputs. At step 708, a triage is classified for the user using the Artificial Intelligence (Al) model based on the medical conditions of the user and the medical recommendation are provided. At step 710, a report is generated with a reasoning for the medical recommendation.

[0071] FIGS. 8A-B is a flow diagram illustrating a computer-implemented method of generating automated adaptive queries to automatically determine a triage level according to an embodiment herein. At step 802, the method includes receiving, from a user interface, unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user. At step 804, the method includes disambiguating at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the user. At step 806, the method includes performing relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly. At step 808, the method includes automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model that personalizes the updated query based on a medical history and the context of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly. At step 810, the method includes presenting the updated query to the user using a text-based conversation at the user interface and recording, from the user interface, a set of responses of the updated query. At step 812, the method includes determining at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data. At step 814, the method includes automatically generating a second updated query by using the adaptive query generation model with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign. At step 816, the method includes automatically determining a triage level of the user by using a triage determination model with a response to the second updated query. [0072] FIG. 9 illustrates an exploded view of the automated adaptive query server 110 of FIG. 1 having a memory 902 having a set of instructions, a bus 904, a display 906, a speaker 908, and a processor 910 capable of processing the set of instructions to perform any one or more of the methodologies herein, according to an embodiment herein. The processor 910 may also enable digital content to be consumed in the form of a video for output via one or more displays 906 or audio for output via speaker and/or earphones 908. The processor 910 may also carry out the methods described herein and in accordance with the embodiments herein.

[0073] Digital content may also be stored in the memory 902 for future processing or consumption. The memory 902 may also store program-specific information and/or service information (PSI/SI), including information about digital content (e.g., the detected information bits) available in the future or stored from the past. A user of the receiver 900 may view this stored information on display 906 and select an item for viewing, listening, or other uses via input, which may take the form of a keypad, scroll, or another input device (s) or combinations thereof. When digital content is selected, the processor 910 may pass information. The content and PSI/SI may be passed among functions within the receiver using the bus 904. [0074] The embodiments herein can take the form of, an entire hardware embodiment, an entire software embodiment or an embodiment including both hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. Furthermore, the embodiments herein can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0075] The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid-state memory, magnetic tape, a removable computer diskette, a random-access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk - read-only memory (CD-ROM), compact disk - read/write (CD-R/W) and DVD. [0076] A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.

[0077] Input/output (I/O) devices (including but not limited to keyboards, displays, pointing devices, remote controls, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem, and Ethernet cards are just a few of the currently available types of network adapters.

[0078] A representative hardware environment for practicing the embodiments herein is depicted in FIG. 10. This schematic drawing illustrates a hardware configuration of an information handling/computer system in accordance with the embodiments herein. The system comprises at least one processor or central processing unit (CPU) 10. The CPUs 10 are interconnected via system bus 12 to various devices such as a random-access memory (RAM) 14, read-only memory (ROM) 16, and an input/output (RO) adapter 18. The I/O adapter 18 can connect to peripheral devices, such as disk units 11 and tape drives 13, or other program storage devices that are readable by the system. The system can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments herein.

[0079] The system further includes a user interface adapter 19 that connects a keyboard 15, mouse 17, speaker 24, microphone 22, and/or other user interface devices such as a touch screen device (not shown) or remote control to the bus 12 to gather user input. Additionally, a communication adapter 20 connects the bus 12 to a data processing network 25, and a display adapter 21 connects the bus 12 to a display device 23 which may be embodied as an output device such as a monitor, printer, or transmitter, for example.

[0080] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope.

Claims

CLAIMS I/We Claim:

1. A method for generating automated adaptive queries to automatically determine a triage level, comprising: receiving, from a user interface of at least one user device (104A-N), unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user; disambiguating, at the automated adaptive query server (110), at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model to obtain a context of the user; performing, at the automated adaptive query server (110), relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly; characterized in that; automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model (112) that personalizes the updated query based on a medical history and the context of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly; presenting the updated query to the user using a text-based conversation at the user interface of at least one user device (104A-N) and recording, from the user interface of at least one user device (104A-N), a set of responses of the updated query; determining, at the automated adaptive query server (110), at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data; automatically generating a second updated query by using the adaptive query generation model (112) with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign; and automatically determining, at the automated adaptive query server (110), a triage level of the user by using a triage determination model with a response to the second updated query.

2. The method as claimed in claim 1 , further comprising performing (a) generating a triage case sheet or triage protocol for the triage inquiry when the triage level is below the predetermined threshold, and (b) repeating the method of claim 1 until the triage level exceeds the predetermined threshold.

3. The method as claimed in claim 1, further comprising analyzing the context of the named entities and relations extracted from the unstructured text to determine a presence or an absence of negation in the response from the user.

4. The method as claimed in claim 1, wherein the adaptive query generation model (112) is trained by utilizing a learning process that incorporates at least one of Unified Medical Language System (UMLS), International Classification of Diseases (ICD), personal health record, historical consultations of users.

5. The method as claimed in claim 1, further comprising generating, using the adaptive query generation model (112), at least one multiple choice question that comprises a plurality of choices to describe the current or past state of the user the user interface of at least one user device (104A-N) comprises, and providing the at least one multiple choice question to the user in a conversational chat-box at the user interface of at least one user device (104A-N), wherein the conversational chat-box provides a visual cue or multi-lingual support for the user to describe the current or past state of the user.

6. The method as claimed in claim 1 , wherein the triage determination model comprises a Bayesian probabilistic causation model that is trained by: obtaining at least one of (a) real-world data of patients generated by a hospital, (b) publicly available clinical data that comprises symptoms, expert surveys data, triage and clinical pathways in a digitized form; determining probabilities associated with the historical pathways and outcomes; and training the Bayesian probabilistic causation model by dynamically constructing a knowledge graph that captures relationships between the flagging sign and triage levels as probabilities.

7. A system for generating automated adaptive queries to automatically determine a triage level, wherein the system comprises of: a distributed cloud (108) comprising an automated adaptive query server (110) that comprises a processor and a memory that are configured to perform: receiving, from a user interface of at least one user device (104A-N), unstructured text input from the user, wherein the unstructured text is provided by the user in response to a query and comprises current or past state of the user; disambiguating at least one of distinct entities and distinct concepts from the unstructured text using a natural language processing (NLP) model; performing relation extraction between the distinct entities and distinct concepts using the NLP model to detect a manifestation of at least one anomaly; characterized in that; automatically generating an updated query based on the manifestation of the at least one anomaly using an adaptive query generation model (112) that personalizes the updated query based on a medical history of the user, wherein the updated query inquires the user for additional information associated with the manifestation of the at least one anomaly; presenting the updated query to the user using a text-based conversation at the user interface of at least one user device (104A-N) and recording, from the user interface of at least one user device (104A-N), a set of responses of the updated query; determining at least one flagging sign based on the set of responses by comparing the set of responses with a predetermined threshold or a reference data; automatically generating a second updated query by using the adaptive query generation model (112) with the flagging sign, wherein the second updated query inquires the user for additional information associated with the flagging sign; and automatically determining a triage level of the user by using a triage determination model with a response to the second updated query.

8. The system as claimed in claim 1 , further comprising performing (a) generating a triage case sheet or triage protocol for the triage inquiry when the triage level is below the predetermined threshold, and (b) repeating the method of claim 1 until the triage level exceeds the predetermined threshold, wherein the context of the named entities and relations extracted from the unstructured text are analyzed to determine a presence or an absence of negation in the response from the user.

9. The system as claimed in claim 1, further comprising generating, using the adaptive query generation model (112), at least one multiple choice question that comprises a plurality of choices to describe the current or past state of the user the user interface of at least one user device (104A-N) comprises, and providing the at least one multiple choice question to the user in a conversational chat-box at the user interface of at least one user device (104A-N), wherein the conversational chat-box provides a visual cue or multi-lingual support for the user to describe the current or past state of the user.

10. The system as claimed in claim 1, wherein the triage determination model comprises a Bayesian probabilistic causation model that is trained by: obtaining at least one of (a) real-world data of patients generated by a hospital, (b) publicly available clinical data that comprises symptoms, expert surveys data, triage and clinical pathways in a digitized form; determining probabilities associated with the historical pathways and outcomes; and training the Bayesian probabilistic causation model by dynamically constructing a knowledge graph that captures relationships between the flagging sign and triage levels as probabilities.