CN112309567A - Intelligent management system and method for clinical pharmacist workstation - Google Patents
Intelligent management system and method for clinical pharmacist workstation Download PDFInfo
- Publication number
- CN112309567A CN112309567A CN202011229268.4A CN202011229268A CN112309567A CN 112309567 A CN112309567 A CN 112309567A CN 202011229268 A CN202011229268 A CN 202011229268A CN 112309567 A CN112309567 A CN 112309567A
- Authority
- CN
- China
- Prior art keywords
- patient
- workstation
- clinical
- information
- output
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
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
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G16H20/13—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 delivered from dispensers
-
- 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
Abstract
The invention relates to an intelligent management system and method for a clinical pharmacist workstation, wherein the system comprises a log recording device, an information inquiry device, a normalization processing device, a model calling device, a branch judgment device and a content analysis device, the branch judgment device is used for referring a customized multilayer feedforward neural network to analyze the current multiple symptom types of a patient based on the daily medication information of the patient and automatically judge whether the patient needs to be subjected to branch treatment based on the severity of the multiple symptom types, and the content analysis device is used for inquiring the medication guidance content of each medicine discharged from the patient and provided with the medicine from a medicine knowledge base according to the last department type before the patient is discharged from the hospital when the patient is discharged from the hospital. The clinical pharmacist workstation intelligent management system and the method thereof are intelligent in operation and convenient to operate. Because the intelligent judgment result can be provided in the aspects of patient branch-of-subject judgment and medication guidance content calling, the intelligent level of patient management of a clinical pharmacist workstation is improved.
Description
(I) technical field
The invention relates to the field of hospital intelligent management, in particular to an intelligent management system and method for a clinical pharmacist workstation.
(II) background of the invention
The clinical pharmacist workstation is an informatization system for helping clinical pharmacists to standardize and efficiently finish writing and maintaining daily medicine use conditions of patients, records the medicine use conditions of the patients from admission, transfer to discharge, and is quick and convenient to operate.
The clinical pharmacist workstation is also a set of stable and perfect digital hospital solution which is expected to improve the management level of the hospital and provides more efficient and rapid medical service for patients. After the clinical pharmacist workstation management system is implemented, the system is beneficial to providing great convenience for hospital management and clinical pharmacists, is also beneficial to improving the reasonable medication level of the hospital and reducing the occurrence of wrong medical advice and drug injury events, and enables the hospital to rapidly move to a new step of digital management.
However, due to the reasons of limited research and development time, few applied hospitals, etc., the design of the clinical pharmacist workstation management system in the prior art is still not mature enough, and the intelligence degree still needs to be improved, which is specifically shown in the following aspects: after a patient is brought into a clinical pharmacist workstation for management, whether a patient needs to be transferred or not can not be automatically judged according to the medication information of the patient, so that the decision of transferring the patient still depends on a manual mode seriously; in addition, the medication guidance contents of the same medicine carried by the patient at the time of discharge are the same, and the characteristics that the medication guidance contents of the same medicine are different in different departments are not considered, so that the medication guidance contents given by a clinical pharmacist workstation are not targeted.
Disclosure of the invention
In order to solve the technical problem of difficult identification of various pharmacist workstations, the invention provides an intelligent management system and method for clinical pharmacist workstations, wherein on one hand, a customized multilayer feed-forward neural network is introduced to analyze various symptom types currently suffered by a patient based on daily medication information of the patient and automatically judge whether the patient needs to be forwarded based on the severity of the various symptom types, wherein the more types of medicines used by the patient, the more the number of hidden layers of the multilayer feed-forward neural network; on the other hand, when the patient is discharged, the medicine use guidance content of each medicine discharged with medicines is inquired from the medicine knowledge base according to the department where the patient is located before the discharge, so that the pertinence and the specialty of the medicine use guidance content given by the clinical pharmacist workstation are guaranteed.
The key points of the invention are as follows:
(1) the daily medication information of the patient is called from the pharmacy monitoring log and is subjected to normalization processing, so that reference data which can be input into a multi-layer feedforward neural network to perform auxiliary judgment on the symptoms of the patient are obtained;
(2) judging whether the patient needs to be transferred based on the first output symptom type and the second output symptom type of the multilayer feedforward neural network, thereby realizing the automatic judgment of the patient transfer;
(3) performing data sorting on various conditions of output data and input data of the multilayer feedforward neural network so as to enable the output data and the input data to accord with the model standard of the multilayer feedforward neural network;
(4) the more varieties of the medicine taken by the patient every day, the more complex the medicine taking condition of the patient, the more the number of hidden danger layers of the customized multilayer feedforward neural network is, and the closer the symptom type output by the multilayer feedforward neural network is to the real condition of the patient;
(5) the departments where the patients are located at last before discharge are different, and the medication guidance contents of the same medicine are different, so that the medication guidance contents are more targeted.
According to an aspect of the present invention, there is provided a clinical pharmacist workstation intelligent management system, the system comprising:
the daily medication information comprises a preset first amount of single drug information, each single drug information comprises a drug name, a single dose, daily administration times and corresponding indications, the preset first amount is the maximum value of the number of different drug types used by the patient on each day, and zero padding operation of difference amount is performed on the single drug information, wherein the maximum value of the number of the different drug types used on a certain day is smaller than the preset first amount;
the information inquiry equipment is connected with the log recording equipment and is used for inquiring the daily medication information of the target patient according to the received patient name;
the normalization processing device is connected with the information inquiry device and is used for performing normalization processing on each single drug information of the daily medication information of the target patient so as to enable the number of bytes occupied by each drug information to be equal and further enable the number of bytes occupied by the daily medication information of the target patient to be equal;
the model calling device is connected with the normalization processing device and used for taking daily medication information of a preset second number of days before the current day of the target patient as a plurality of preset second number of input data of the multilayer feedforward neural network in the morning every day, the output data of the multilayer feedforward neural network comprise a preset third number of symptom types, the preset third number of symptom types are sequentially output according to the severity degree, and the first output symptom type is the most severe symptom type;
the branch-of-subject judging device is connected with the model calling device and is used for receiving the preset third number of symptom types and judging whether the target patient needs to be subjected to branch-of-subject based on the first output symptom type and the second output symptom type;
when the number of the symptom types in the output data of the multilayer feedforward neural network is less than a preset third number, zero padding is carried out on the balance number of the symptom types to serve as the final output data of the multilayer feedforward neural network, and when the number of the single medicine information in the daily medication information of the patient on a certain day is less than a preset first number, zero padding is carried out on the balance number of the single medicine information to serve as the input data of the multilayer feedforward neural network;
the multilayer feedforward neural network comprises a single input layer, a plurality of hidden layers and a single output layer, and the number of the hidden layers of the multilayer feedforward neural network is larger when the preset first number is larger;
wherein, the step of judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises the following specific steps: when the first output symptom type and the second output symptom type conflict with the department type of the target patient in the workstation, the target patient is automatically judged to need to be transferred.
More specifically, in the clinical pharmacist workstation intelligent management system, the system further includes:
the content analysis equipment is used for inquiring the medication instruction content of each medicine with medicine for patient discharge from the medicine knowledge base according to the type of the department where the patient is last before discharge when the patient is discharged;
the types of departments where patients are located at last before discharge are different, and the inquired medication guidance contents of the same medicine are different.
More specifically, in the clinical pharmacist workstation intelligent management system, the system further includes:
and the cloud storage mechanism is connected with the content analysis equipment through a wireless network and is used for storing a medicine knowledge base of the clinical pharmacist workstation.
More specifically, in the clinical pharmacist workstation intelligent management system, the system further includes:
a medication evaluation device for conducting a suitability evaluation of the type of medication being used while the patient is in the station based on the type of disease the patient is currently suffering from to determine whether continued use is required when the patient is brought into the clinical pharmacist workstation for administration.
More specifically, in the clinical pharmacist workstation intelligent management system, the system further includes:
the clinical analysis equipment is used for performing suitability analysis on the selection of clinical medicines of the patient according to personal information of the patient after the patient is brought into a clinical pharmacist workstation for management;
wherein, in the clinical analysis equipment, the personal information of the patient comprises the food allergy history of the patient's past medicines, the degree of understanding of the patient on the medicines, the medication compliance of the patient and the history of adverse drug reactions of the patient.
More specifically, in the clinical pharmacist workstation intelligent management system, the system further includes:
and the login management equipment is used for providing system login service and system logout service for clinical pharmacists of the workstation.
More specifically, in the clinical pharmacist workstation intelligent management system:
the daily medicine information that clinical pharmacist input is received to information receiving element, database storage unit with the information receiving element is connected for utilize the database to store the daily medicine information that clinical pharmacist input.
More specifically, in the clinical pharmacist workstation intelligent management system:
the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises the following steps: when the first output symptom type is not in conflict with the department type of the target patient in the workstation, and the second output symptom type is in conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred;
wherein the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises: when the first output symptom type conflicts with the department type of the target patient in the workstation, and the second output symptom type does not conflict with the department type of the target patient in the workstation, judging that the target patient needs to be transferred;
wherein the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises: and when the first output symptom type and the second output symptom type do not conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred.
More specifically, in the clinical pharmacist workstation intelligent management system:
the model calling equipment comprises a timing trigger unit, a model establishing unit and a model operating unit, wherein the model establishing unit is respectively connected with the timing trigger unit and the model operating unit;
the timing trigger unit is respectively connected with the model establishing unit and the model running unit and is used for driving the model establishing unit and the model running unit to enter a working state from a dormant state every morning;
the model establishing unit is used for establishing the multilayer feedforward neural network when entering a working state, and the model operating unit is used for operating the multilayer feedforward neural network when entering the working state;
the time corresponding to morning of each day triggered by the timing trigger unit is any time point from 0 point of each day to 1 point of each day.
According to another aspect of the present invention, there is also provided a clinical pharmacist workstation intelligent management method, including using an above clinical pharmacist workstation intelligent management system, specifically: the method comprises the steps that a pharmacist records/acquires daily medication information of a target patient through a log recording device, suitability evaluation of medicines used when the target patient is admitted is completed through a medicine evaluation device, suitability evaluation of the medicines after the target patient is admitted is completed through a clinical analysis device, whether the patient managed in a clinical pharmacist workstation needs to be transferred or not is judged through a normalization processing device, a model calling device and a transfer judging device on the basis of an artificial intelligence mode, and specific medication guidance content based on department categories is provided through a content analyzing device when the patient is discharged.
The clinical pharmacist workstation intelligent management system and the method thereof are intelligent in operation and convenient to operate. Because the intelligent judgment result can be provided in the aspects of patient branch-of-subject judgment and medication guidance content calling, the intelligent level of patient management of a clinical pharmacist workstation is improved.
(IV) description of the drawings
Fig. 1 is a flow chart illustrating a key technology of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 2 is a block diagram illustrating a first structure of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 3 is an exemplary diagram illustrating an information display interface of a pharmacy care log within a clinical pharmacist workstation, according to an embodiment of the present invention.
Fig. 4 is a block diagram illustrating a second configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 5 is an exemplary diagram illustrating the establishment of an out-of-hospital medication administration guidance parsing interface of a clinical pharmacist workstation, according to an embodiment of the present invention.
Fig. 6 is an exemplary diagram illustrating operation of a clinical pharmacist workstation discharge medication administration guidance interpretation interface according to an embodiment of the present invention.
Fig. 7 is a block diagram illustrating a third configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 8 is a block diagram illustrating a fourth configuration of an intelligent management system for a clinical pharmacist workstation, according to an embodiment of the present invention.
Fig. 9 is an exemplary diagram illustrating operation of a clinical pharmacist workstation drug initial assessment interface according to an embodiment of the present invention.
Fig. 10 is a block diagram illustrating a fifth configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 11 is an exemplary diagram illustrating operation of a clinical pharmacist workstation clinical analysis interface according to an embodiment of the present invention.
Fig. 12 is a block diagram illustrating a sixth configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention.
Fig. 13 is a diagram illustrating an example of the operation of a login interface of an intelligent management system of a clinical pharmacist workstation, according to an embodiment of the present invention.
Fig. 14 is a diagram illustrating an example of an exit interface operation of the clinical pharmacist workstation intelligent management system, according to an embodiment of the present invention.
(V) detailed description of the preferred embodiments
The invention will be further described with reference to specific examples, but the scope of the invention is not limited thereto:
hospitals refer to medical institutions for carrying out necessary medical examination, treatment measures, nursing techniques, reception services, rehabilitation equipment, treatment and transportation and the like for patients according to laws, regulations and industrial specifications, mainly aiming at rescuing and supporting injuries, the service objects of the medical nursing bed not only comprise patients with symptoms, but also comprise the elderly who cannot take care of themselves or have limited activity and medical nursing dependence, the serious patients who need long-term rehabilitation and frequent observation and examination for forensic evaluation and have medical nursing dependence or unstable illness, or persons with other special conditions, such as healthy persons (e.g. pregnant women, lying-in women, newborns) and fully healthy persons (e.g. persons coming from hospitals for physical examination or oral cleaning), when initially set up, the refuge is provided for people to take refuge, entertainment programs are also provided, the coming people are comfortable, the intention of the people to take refuge is achieved, and the refuge and treatment device gradually becomes a special mechanism for accommodating and treating patients.
Typically, a hospital is made up of a number of institutions, each of which includes more than one clinical pharmacist workstation. In the operation process of the clinical pharmacist workstation, the medication process of a patient, including initial evaluation of pharmacy of the patient during admission, pharmacy monitoring during admission, pharmacy transfer evaluation during transfer, discharge medication guide during discharge and the like, is a pharmacy service flow formed around medication monitoring behaviors of the clinical pharmacist. The inspection, the smelling, the questioning, the cutting and the prescription of the traditional Chinese medicine are used for dispensing the medicine, and the symptom and physical sign, the medical history acquisition, the inspection and the medicine treatment of the western medicine are the key points concerned by the pharmacy monitoring of clinical pharmacists and the basic functions which the clinical pharmacist workstation must have.
Therefore, in the aspect of design requirements, the clinical pharmacist workstation management system meets the professional responsibility requirements of clinical pharmacists, and the pharmacists can directly participate in clinical ward rounds, so that the pharmacy monitoring of patients is realized, various professional pharmacy services are provided for the patients, and the comprehensive application information management system of the electronic pharmacy calendar is completed. However, the clinical pharmacist workstation management system in the prior art still depends on a manual mode in the aspect of the branch judgment and has a deviation in the aspect of the call of the discharge medication instruction content, so that the intellectualization level of the clinical pharmacist workstation management system cannot meet the current requirements of the hospital.
In order to overcome the defects, the invention builds an intelligent management system for the clinical pharmacist workstation, and can solve the technical problems encountered by the clinical pharmacist workstation.
The key of the invention concept is that the daily medication information of the patient is called from the pharmacy monitoring log and is normalized, so as to obtain normalized data which can be input into an input layer of the multilayer feedforward neural network, intelligently analyze a plurality of symptom types currently suffered by the patient by adopting the multilayer feedforward neural network, judge whether the patient needs to be subject to transfer or not based on the severity of the symptom types, meanwhile, the medicine use guidance content of each medicine with medicine discharged from the hospital is inquired from the medicine knowledge base based on the department where the patient is located before the hospital is discharged, the condition that the medicine use guidance contents of the same medicine which are inquired by different hospital discharge departments are the same is avoided, thereby giving out non-artificial intelligent data in two aspects of patient's judgement of going to the branch of academic or vocational study and use the prescription content and call, guarantee to know the accuracy of medical data who separates out, promoted the operating efficiency of clinical pharmacist workstation.
As shown in fig. 1, a key technical flow diagram of an intelligent management system and method for a clinical pharmacist workstation according to an embodiment of the present invention is provided;
in fig. 1, the related art process mainly involves the intelligent analysis of the referral advice and the discharge medication guidance content;
specifically, in the first stage, the parsing process of the referral guidance opinion is as follows: firstly, inquiring daily medication information of a target patient from a database of a clinical pharmacist workstation based on the name of the target patient, namely first day medication information, second day medication information, third day medication information, N-1 day medication information and N day medication information, wherein N is the number of days that the target patient enters the clinical pharmacist workstation, and N is a natural number larger than 1, then normalizing the daily medication information of the target patient to enable the number of bytes occupied by the daily medication information to be equal, thereby obtaining input data which can be input into an input layer of the customized multilayer feedforward neural network, then output data of the customized multilayer feedforward neural network is composed of preset M symptom types, M is a natural number larger than 1 and can be equal to N or not equal to N, and the M symptom types are output according to the severity order, the first output symptom type is the most serious symptom type, and finally, whether the patient needs to be transferred is judged based on the first output symptom type and the second output symptom type, wherein the customization principle of the multilayer feedforward neural network is as follows: the more the daily medication information of the target patient includes the more the variety of medication, the more the number of implicit layers of the customized multilayer feedforward neural network;
specifically, in the second stage, the analysis process of the discharge medication guidance content is as follows: when a patient is discharged, inquiring the medication guiding contents of discharged medicines from the medicine knowledge base according to the final department of the patient before discharge and the names of the medicines discharged with the medicines, wherein the final department of the patient before discharge is different, and the inquired medication guiding contents of the same medicines are different.
Hereinafter, the clinical pharmacist workstation intelligent management system and method of the present invention will be described in detail by way of example.
Example 1:
fig. 2 is a first block diagram illustrating an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, the system including:
the daily medication information comprises a preset first amount of single drug information, each single drug information comprises a drug name, a single dose, daily administration times and corresponding indications, the preset first amount is the maximum value of the number of different drug types used by the patient on each day, and zero padding operation of difference amount is performed on the single drug information, wherein the maximum value of the number of the different drug types used on a certain day is smaller than the preset first amount;
the information inquiry equipment is connected with the log recording equipment and is used for inquiring the daily medication information of the target patient according to the received patient name;
the normalization processing device is connected with the information inquiry device and is used for performing normalization processing on each single drug information of the daily medication information of the target patient so as to enable the number of bytes occupied by each drug information to be equal and further enable the number of bytes occupied by the daily medication information of the target patient to be equal;
the model calling device is connected with the normalization processing device and used for taking daily medication information of a preset second number of days before the patient corresponding to the patient name in the morning every day as a plurality of preset second number of input data of the multilayer feedforward neural network, the output data of the multilayer feedforward neural network comprise preset third number of symptom types, the preset third number of symptom types are sequentially output according to the severity, and the first output symptom type is the most severe symptom type;
the branch-of-subject judging device is connected with the model calling device and is used for receiving the preset third number of symptom types and judging whether the target patient needs to be subjected to branch-of-subject based on the first output symptom type and the second output symptom type;
when the number of the symptom types in the output data of the multilayer feedforward neural network is less than a preset third number, zero padding is carried out on the balance number of the symptom types to serve as the final output data of the multilayer feedforward neural network, and when the number of the single medicine information in the daily medication information of the patient on a certain day is less than a preset first number, zero padding is carried out on the balance number of the single medicine information to serve as the input data of the multilayer feedforward neural network;
the multilayer feedforward neural network comprises a single input layer, a plurality of hidden layers and a single output layer, and the number of the hidden layers of the multilayer feedforward neural network is larger when the preset first number is larger;
wherein, whether the target patient needs to be transferred is judged based on the first output symptom type and the second output symptom type, which specifically comprises the following steps: when the first output symptom type and the second output symptom type conflict with the department type of the target patient in the workstation, the target patient is automatically judged to need to be transferred.
As shown in fig. 3, an exemplary diagram of a display interface of the pharmacy monitoring log information in the clinical pharmacist workstation is provided, and in fig. 3, for a target patient, by clicking an indication, a drug selection, a single dose and a link of each dosing frequency, the recording of the daily dosing information of the target patient is completed, specifically including a drug name, a single dose, a daily dosing frequency and a corresponding indication.
Example 2:
fig. 4 is a block diagram illustrating a second configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, further including, in comparison with the configuration of the first embodiment:
the content analysis equipment is used for inquiring the medication instruction content of each medicine with medicine for patient discharge from the medicine knowledge base according to the type of the department where the patient is last before discharge when the patient is discharged;
the types of departments where patients are located at last before discharge are different, and the inquired medication guidance contents of the same medicine are different.
As shown in FIG. 5, an exemplary diagram of the establishment of a discharge medication guide analysis interface at a clinical pharmacist workstation is shown, and in FIG. 5, an analysis interface for establishing a discharge medication guide for a currently discharged patient is selected through the discharge medication guide on the right side of the interface.
Referring to fig. 6, an example of operation of the discharge medication guidance analysis interface of the clinical pharmacist workstation is shown, and in fig. 6, the medication guidance contents of five drugs with drugs discharged from the patient are inquired from the drug knowledge base according to the type of the last department before the patient is discharged and the drug names input by the clinical pharmacist one by one, wherein the five drugs take cefixime capsules as the first.
Example 3:
fig. 7 is a block diagram illustrating a third configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, further including, in comparison with the configuration of the second embodiment:
and the cloud storage mechanism is connected with the content analysis equipment through a wireless network and is used for storing a medicine knowledge base of the clinical pharmacist workstation.
The Cloud storage is a mode of online storage (english: Cloud storage), that is, data is stored in a plurality of virtual servers usually hosted by a third party. A hosting company operates a large-scale data center, and users who need data storage hosting meet the requirements of data storage by purchasing or leasing storage space from the users. The data center operator prepares a virtualized storage resource at the back end according to the requirement of the customer, and provides the storage resource in a storage resource pool (storage pool), so that the customer can use the storage resource pool to store the file or the object by himself. In practice, these resources may be distributed over numerous server hosts.
Example 4:
fig. 8 is a block diagram illustrating a fourth configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, further including, in comparison with the configuration of the first embodiment:
a medication evaluation device for conducting a suitability evaluation of the type of medication being used while the patient is in the station based on the type of disease the patient is currently suffering from to determine whether continued use is required when the patient is brought into the clinical pharmacist workstation for administration.
As shown in fig. 9, a diagram of an example of the operation of a clinical pharmacist workstation drug initial assessment interface is shown, and in fig. 9, a patient initial drug assessment registry is compiled and obtained according to various personal information registered when a patient is brought into the clinical pharmacist workstation, and suitability assessment based on the type of disease currently suffered by the patient is performed based on the patient initial drug assessment registry to determine whether to continue using the system.
Example 5:
fig. 10 is a block diagram showing a fifth configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, further including, in comparison with the configuration of the first embodiment:
the clinical analysis device is used for performing suitability analysis on the selection of clinical medicines of the patient based on personal information of the patient after the patient is brought into a clinical pharmacist workstation for management;
wherein, in the clinical analysis equipment, the personal information of the patient comprises the food allergy history of the patient's past medicines, the degree of understanding of the patient on the medicines, the medication compliance of the patient and the history of adverse drug reactions of the patient.
As shown in fig. 11, a diagram illustrating an operation example of a clinical pharmacist workstation clinical analysis interface is shown, and in fig. 11, after a patient is managed by a clinical pharmacist workstation in a hospital, admission diagnosis information of the patient is formed according to personal information of the patient, and the admission diagnosis information includes relevant data for conducting suitability analysis on selection of clinical drugs of the patient.
Example 6:
fig. 12 is a block diagram illustrating a sixth configuration of an intelligent management system for a clinical pharmacist workstation according to an embodiment of the present invention, further including, in comparison with the configuration of the first embodiment:
and the login management equipment is used for providing system login service and system logout service for clinical pharmacists of the workstation.
As shown in fig. 13, an example of the operation of the login interface of the intelligent management system of the clinical pharmacist workstation is shown, in fig. 13, the login interface includes four selection boxes of a user name, a password, a workstation and a use version, and the login of the clinical pharmacist to the intelligent management system of the clinical pharmacist workstation is realized according to the relevant login information input by the clinical pharmacist in the four selection boxes;
accordingly, as shown in fig. 14, an example of the exit interface operation of the intelligent management system of the clinical pharmacist workstation is shown, and in fig. 14, after the clinical pharmacist completes the operations on the intelligent management system of the clinical pharmacist workstation, the clinical pharmacist workstation is exited from the intelligent management system of the clinical pharmacist workstation by clicking the close button at the upper right corner of the interface.
In the clinical pharmacist workstation intelligent management system according to any of the above embodiments of the present invention:
the daily medicine information that clinical pharmacist input is received to information receiving element, database storage unit with the information receiving element is connected for utilize the database to store the daily medicine information that clinical pharmacist input.
In the clinical pharmacist workstation intelligent management system according to any of the above embodiments of the present invention:
judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises: when the first output symptom type is not in conflict with the department type of the target patient in the workstation, and the second output symptom type is in conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred;
wherein judging whether the target patient needs to be subject to the transfer based on the first output symptom type and the second output symptom type comprises: when the first output symptom type conflicts with the department type of the target patient in the workstation, and the second output symptom type does not conflict with the department type of the target patient in the workstation, judging that the target patient needs to be transferred;
wherein judging whether the target patient needs to be subject to the transfer based on the first output symptom type and the second output symptom type comprises: and when the first output symptom type and the second output symptom type do not conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred.
And in the clinical pharmacist workstation intelligent management system of any of the above embodiments of the present invention:
the model calling equipment comprises a timing trigger unit, a model establishing unit and a model operating unit, wherein the model establishing unit is respectively connected with the timing trigger unit and the model operating unit;
the timing trigger unit is respectively connected with the model establishing unit and the model running unit and is used for driving the model establishing unit and the model running unit to enter a working state from a dormant state every morning;
the model establishing unit is used for establishing the multilayer feedforward neural network when entering a working state, and the model operating unit is used for operating the multilayer feedforward neural network when entering the working state;
the time corresponding to morning of each day triggered by the timing trigger unit is any time point from 0 point of each day to 1 point of each day.
Meanwhile, in order to overcome the defects, the invention also provides an intelligent management method for the clinical pharmacist workstation, which comprises the following steps of using the intelligent management system for the clinical pharmacist workstation, and specifically comprising the following steps: the method comprises the steps that a pharmacist records/acquires daily medication information of a target patient through a log recording device, suitability evaluation of medicines used when the target patient is admitted is completed through a medicine evaluation device, suitability evaluation of the medicines after the target patient is admitted is completed through a clinical analysis device, whether the patient managed in a clinical pharmacist workstation needs to be transferred or not is judged through a normalization processing device, a model calling device and a transfer judging device on the basis of an artificial intelligence mode, and specific medication guidance content based on department categories is provided through a content analyzing device when the patient is discharged.
In addition, a Feedforward Neural Network (FNN), referred to as a feedforward network for short, is one of artificial neural networks. The feed forward network employs a unidirectional multi-layer structure. Where each layer contains a number of neurons. In such a neural network, each neuron may receive a signal of a neuron of a previous layer and output to a next layer. The 0 th layer is called an input layer, the last layer is called an output layer, and other intermediate layers are called hidden layers (or hidden layers and hidden layers). The hidden layer may be one layer or multiple layers according to design requirements or application requirements.
The feedforward network has simple structure and wide application, can approach any continuous function and square integrable function with any precision, and can accurately realize the training of any and limited sample sets. From a system perspective, the feedforward neural network is a static nonlinear mapping. The intelligent analysis of each item of application data can be completed through the feedforward neural network, and further, the method can be used in various application fields needing artificial intelligence.
In a specific classification of the feedforward neural network, a single-layer feedforward neural network is the simplest artificial neural network, and only includes one output layer, and a value (output value) of a node on the output layer is directly obtained by multiplying an input value by a weight value. The multi-layer feedforward neural network has an input layer, one or more hidden layers in the middle and an output layer, wherein each layer of the multi-layer feedforward neural network is equivalent to a single-layer feedforward neural network. Through the requirements of various application fields, all layers of the multilayer feedforward neural network are improved, so that the customized design of the multilayer feedforward neural network is realized, for example, in the invention, the intelligent analysis of various symptom types of a patient is realized through the self-adaptive selection of the number of hidden layers, and then the intelligent judgment of whether the patient needs to be transferred is realized.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.
Although the present invention has been described with reference to the above embodiments, it should be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be subject to the scope defined by the claims of the present application.
Claims (10)
1. An intelligent management system for a clinical pharmacist workstation, the system comprising:
the daily medication information comprises a preset first amount of single drug information, each single drug information comprises a drug name, a single dose, daily administration times and corresponding indications, the preset first amount is the maximum value of the number of different drug types used by the patient on each day, and zero padding operation of difference amount is performed on the single drug information, wherein the maximum value of the number of the different drug types used on a certain day is smaller than the preset first amount;
the information inquiry equipment is connected with the log recording equipment and is used for inquiring the daily medication information of the target patient according to the received patient name;
the normalization processing device is connected with the information inquiry device and is used for performing normalization processing on each single drug information of the daily medication information of the target patient so as to enable the number of bytes occupied by each drug information to be equal and further enable the number of bytes occupied by the daily medication information of the target patient to be equal;
the model calling device is connected with the normalization processing device and used for taking daily medication information of a preset second number of days before the patient corresponding to the patient name in the morning every day as a plurality of preset second number of input data of the multilayer feedforward neural network, the output data of the multilayer feedforward neural network comprise preset third number of symptom types, the preset third number of symptom types are sequentially output according to the severity, and the first output symptom type is the most severe symptom type;
the branch-of-subject judging device is connected with the model calling device and is used for receiving the preset third number of symptom types and judging whether the target patient needs to be subjected to branch-of-subject based on the first output symptom type and the second output symptom type;
when the number of the symptom types in the output data of the multilayer feedforward neural network is less than a preset third number, the balance number of the symptom types is filled with zero to serve as the final output data of the multilayer feedforward neural network, and when the number of the single medicine information in the daily medication information of the patient on a certain day is less than a preset first number, the balance number of the single medicine information is filled with zero to serve as the input data of the multilayer feedforward neural network;
the multilayer feedforward neural network comprises a single input layer, a plurality of hidden layers and a single output layer, and the number of the hidden layers of the multilayer feedforward neural network is larger when the preset first number is larger;
judging whether the patient corresponding to the patient name needs to be subject to transfer or not based on the first output symptom type and the second output symptom type, specifically: and when the first output symptom type and the second output symptom type conflict with the department type of the patient name in the corresponding workstation, automatically judging that the target patient needs to be transferred.
2. The clinical pharmacist workstation intelligent management system of claim 1, wherein said system further comprises:
the content analysis equipment is used for inquiring the medication guiding content of each medicine with medicine when the patient is discharged from the hospital from the medicine knowledge base according to the type of the department where the patient is last before being discharged from the hospital;
the types of departments where patients are located at last before discharge are different, and the inquired medication guidance contents of the same medicine are different.
3. The clinical pharmacist workstation intelligent management system of claim 2, wherein said system further comprises:
and the cloud storage mechanism is connected with the content analysis equipment through a wireless network and is used for storing a medicine knowledge base of the clinical pharmacist workstation.
4. The clinical pharmacist workstation intelligent management system of claim 1, wherein said system further comprises:
a medication evaluation device for conducting a suitability evaluation of the type of medication being used while the patient is in the station based on the type of disease the patient is currently suffering from to determine whether continued use is required when the patient is brought into the clinical pharmacist workstation for administration.
5. The clinical pharmacist workstation intelligent management system of claim 1, wherein said system further comprises:
the clinical analysis equipment is used for performing suitability analysis on the selection of clinical medicines of the patient according to personal information of the patient after the patient is brought into a clinical pharmacist workstation for management;
wherein, in the clinical analysis equipment, the personal information of the patient comprises the food allergy history of the patient's past medicines, the degree of understanding of the patient on the medicines, the medication compliance of the patient and the history of adverse drug reactions of the patient.
6. The clinical pharmacist workstation intelligent management system of claim 1, wherein said system further comprises:
and the login management equipment is used for providing system login service and system logout service for clinical pharmacists of the workstation.
7. The clinical pharmacist workstation intelligent management system of claim 1, wherein:
the daily medicine information that clinical pharmacist input is received to information receiving element, database storage unit with the information receiving element is connected for utilize the database to store the daily medicine information that clinical pharmacist input.
8. The clinical pharmacist workstation intelligent management system of claim 1, wherein:
the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises the following steps: when the first output symptom type is not in conflict with the department type of the target patient in the workstation, and the second output symptom type is in conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred;
wherein the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises: when the first output symptom type conflicts with the department type of the target patient in the workstation, and the second output symptom type does not conflict with the department type of the target patient in the corresponding workstation, judging that the target patient needs to be transferred;
wherein the judging whether the target patient needs to be transferred based on the first output symptom type and the second output symptom type comprises: and when the first output symptom type and the second output symptom type do not conflict with the department type of the target patient in the workstation, judging that the target patient does not need to be transferred.
9. The clinical pharmacist workstation intelligent management system of claim 1, wherein:
the model calling equipment comprises a timing trigger unit, a model establishing unit and a model operating unit, wherein the model establishing unit is respectively connected with the timing trigger unit and the model operating unit;
the timing trigger unit is respectively connected with the model establishing unit and the model running unit and is used for driving the model establishing unit and the model running unit to enter a working state from a dormant state every morning;
the model establishing unit is used for establishing the multilayer feedforward neural network when entering a working state, and the model operating unit is used for operating the multilayer feedforward neural network when entering the working state;
the time corresponding to morning of each day triggered by the timing trigger unit is any time point from 0 point of each day to 1 point of each day.
10. The intelligent management system for clinical pharmacist workstations, wherein the method for using the management system is as follows: the method comprises the steps that a pharmacist records/acquires daily medication information of a target patient through a log recording device, suitability evaluation of medicines used when the target patient is admitted is completed through a medicine evaluation device, suitability evaluation of the medicines after the target patient is admitted is completed through a clinical analysis device, whether the patient managed in a clinical pharmacist workstation needs to be transferred or not is judged through a normalization processing device, a model calling device and a transfer judging device on the basis of an artificial intelligence mode, and specific medication guidance content based on department categories is provided through a content analyzing device when the patient is discharged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011229268.4A CN112309567B (en) | 2020-11-06 | 2020-11-06 | Intelligent management system and method for clinical pharmacist workstation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011229268.4A CN112309567B (en) | 2020-11-06 | 2020-11-06 | Intelligent management system and method for clinical pharmacist workstation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112309567A true CN112309567A (en) | 2021-02-02 |
| CN112309567B CN112309567B (en) | 2021-06-01 |
Family
ID=74325136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011229268.4A Active CN112309567B (en) | 2020-11-06 | 2020-11-06 | Intelligent management system and method for clinical pharmacist workstation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112309567B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116759060A (en) * | 2023-08-17 | 2023-09-15 | 北京大学第三医院（北京大学第三临床医学院） | Intelligent management method, system, equipment and medium for clinical pharmacy |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779446A (en) * | 2016-12-28 | 2017-05-31 | 上海市静安区石门二路街道社区卫生服务中心 | A kind of family doctor's administration of home patient system |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| CN110265098A (en) * | 2019-05-07 | 2019-09-20 | 平安科技（深圳）有限公司 | A kind of case management method, apparatus, computer equipment and readable storage medium storing program for executing |
| US20200135337A1 (en) * | 2017-05-12 | 2020-04-30 | The Regents Of The University Of Michigan | Individual and cohort pharmacological phenotype prediction platform |
| US20200160969A1 (en) * | 2018-11-21 | 2020-05-21 | Enlitic, Inc. | Accession number correction system |
| CN111445976A (en) * | 2020-03-24 | 2020-07-24 | 屹嘉智创(厦门)科技有限公司 | Intelligent rational medication system and method |
-
2020
- 2020-11-06 CN CN202011229268.4A patent/CN112309567B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779446A (en) * | 2016-12-28 | 2017-05-31 | 上海市静安区石门二路街道社区卫生服务中心 | A kind of family doctor's administration of home patient system |
| US20200135337A1 (en) * | 2017-05-12 | 2020-04-30 | The Regents Of The University Of Michigan | Individual and cohort pharmacological phenotype prediction platform |
| CN109087691A (en) * | 2018-08-02 | 2018-12-25 | 科大智能机器人技术有限公司 | A kind of OTC drugs recommender system and recommended method based on deep learning |
| US20200160969A1 (en) * | 2018-11-21 | 2020-05-21 | Enlitic, Inc. | Accession number correction system |
| CN110265098A (en) * | 2019-05-07 | 2019-09-20 | 平安科技（深圳）有限公司 | A kind of case management method, apparatus, computer equipment and readable storage medium storing program for executing |
| CN111445976A (en) * | 2020-03-24 | 2020-07-24 | 屹嘉智创(厦门)科技有限公司 | Intelligent rational medication system and method |
Non-Patent Citations (2)
| Title |
|---|
| 俞鹏天等: "基于临床药师工作实践构建电子药历管理平台", 《中国医院药学杂志》 * |
| 马葵芬等: "药学门诊信息化系统的构建与应用", 《中国医院药学杂志》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116759060A (en) * | 2023-08-17 | 2023-09-15 | 北京大学第三医院（北京大学第三临床医学院） | Intelligent management method, system, equipment and medium for clinical pharmacy |
| CN116759060B (en) * | 2023-08-17 | 2024-01-30 | 北京大学第三医院（北京大学第三临床医学院） | Intelligent management method, system, equipment and medium for clinical pharmacy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112309567B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111145844B (en) | Comprehensive medical supervision platform | |
| US7379885B1 (en) | System and method for obtaining, processing and evaluating patient information for diagnosing disease and selecting treatment | |
| Berlin et al. | A taxonomic description of computer-based clinical decision support systems | |
| Palmer | Process-based measures of quality: the need for detailed clinical data in large health care databases | |
| US8494868B2 (en) | Method and system for a seamless interface between an emergency medical dispatch system and a nurse triage system | |
| JP4224136B2 (en) | Computerized medical diagnostic system using list-based processing | |
| CN111128333A (en) | One-stop intelligent diagnosis and intelligent medical management system | |
| CN112735610A (en) | Post-hospital follow-up system and follow-up method | |
| CN112309567B (en) | Intelligent management system and method for clinical pharmacist workstation | |
| Finkelstein et al. | Practice‐level effects of interventions to improve asthma care in primary care settings: the pediatric asthma care patient outcomes research team | |
| WO2021179694A1 (en) | Drug recommendation method, apparatus, computer device, and storage medium | |
| CN109887586A (en) | A kind of order matching process, electronic equipment and computer readable storage medium | |
| Poh et al. | Role of the pharmacist during the COVID-19 pandemic: a time to rethink strategies | |
| CN112365940A (en) | System and method for screening subjects | |
| CN113161016A (en) | Intelligent medical service system, method and storage medium | |
| US20160292366A1 (en) | System and method of combining medicinal product information of medicaments | |
| US20070038037A1 (en) | Method and apparatus for symptom-based order protocoling within the exam ordering process | |
| Phillips | Telephone follow-up for patients eligible for cardiac rehab: A systematic review | |
| JP2016212559A (en) | Medical information management and medical information management method using medical information management system | |
| Coleman et al. | Integrated pharmacy and PrEP navigation services to support PrEP uptake: a quality improvement project | |
| Le et al. | Experience with a managed care approach to HIV infection: effectiveness of an interdisciplinary team | |
| US20210150444A1 (en) | Automated Healthcare Provider Quality Reporting System (PQRS) | |
| CN113657809A (en) | Hospital portrait construction method, device, equipment and storage medium | |
| Gauthier-Wetzel | Barcode Medication Administration Software Technology Use in the Emergency Department and Medication Error Rates | |
| US20080071571A1 (en) | Methods and systems for using practice management data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |