CN113689930A - Medication regimen adjustment method, device, computer equipment and storage medium - Google Patents
Medication regimen adjustment method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113689930A CN113689930A CN202110991094.3A CN202110991094A CN113689930A CN 113689930 A CN113689930 A CN 113689930A CN 202110991094 A CN202110991094 A CN 202110991094A CN 113689930 A CN113689930 A CN 113689930A
- Authority
- CN
- China
- Prior art keywords
- disease
- medication
- database
- disaster
- information
- 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.)
- Pending
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
本申请涉及人工智能领域，还涉及数字医疗领域，可以实现在出现灾情时，可以及时、准确地调整患者的用药方案。涉及一种用药方案调整方法、装置、计算机设备和存储介质，该方法包括：获取目标用户的健康信息，健康信息包括患病症状信息与初始用药方案，确定目标用户的位置区域信息，查询灾情数据库，获取目标用户的位置区域信息对应的灾情信息；将患病症状信息与灾情信息输入疾病变化预测模型进行疾病变化预测，获得疾病变化预测结果；将疾病变化预测结果与初始用药方案输入用药调整模型进行用药方案调整，获得目标用药方案；输出目标用药方案。此外，本申请还涉及区块链技术，目标用药方案可存储于区块链中。
The present application relates to the field of artificial intelligence and also to the field of digital medicine, which can realize timely and accurate adjustment of a patient's medication plan in the event of a disaster. It relates to a method, device, computer equipment and storage medium for adjusting a medication plan. The method includes: acquiring health information of a target user, the health information including disease symptom information and an initial medication plan, determining the location area information of the target user, and querying a disaster situation database , obtain the disaster information corresponding to the location and area information of the target user; input the disease symptom information and disaster information into the disease change prediction model to predict the disease change, and obtain the disease change prediction result; input the disease change prediction result and the initial medication plan into the medication adjustment model Adjust the medication plan to obtain the target medication plan; output the target medication plan. In addition, this application also involves blockchain technology, and the target medication regimen can be stored in the blockchain.
Description
Technical Field
The present application relates to the field of artificial intelligence, and also relates to the field of digital medical treatment, and in particular, to a medication scheme adjustment method, apparatus, computer device, and storage medium.
Background
With the increase of the aging proportion of the population, the population base of potential chronic diseases is continuously expanded, and the society faces increasingly serious chronic disease challenges. The common chronic diseases include diabetes, hypertension, coronary heart disease, chronic kidney disease and the like. The chronic disease patients need to take the medicine regularly, and go to the hospital regularly for the re-diagnosis and the adjustment of the medication scheme. When the disaster occurs in the area where the chronic disease patients are, the panic emotion occurs in the chronic disease patients due to the disaster, so that the disease symptoms of the chronic disease patients are changed, and the medication scheme of the chronic disease patients needs to be adjusted. However, after a disaster occurs, due to the inconvenience of traffic, patients with chronic diseases cannot be guided and adjusted by doctors accurately in time, and the chronic diseases are at increased risk.
Therefore, when a disaster occurs, how to timely and accurately adjust the medication scheme of a patient becomes a problem which needs to be solved urgently.
Disclosure of Invention
The application provides a medication scheme adjusting method, a medication scheme adjusting device, computer equipment and a storage medium, wherein the medication scheme of a patient can be timely and accurately adjusted when a disaster occurs by predicting disease change according to disaster information and disease symptom information of a target user and adjusting the medication scheme according to the obtained disease change prediction information and medication information.
In a first aspect, the present application provides a method of medication regimen adjustment, the method comprising:
acquiring health information of a target user, wherein the health information comprises disease symptom information and an initial medication scheme;
determining the position area information of the target user, inquiring a disaster situation database, and acquiring disaster situation information corresponding to the position area information of the target user, wherein the position area information and the disaster situation information of disaster events are stored in the disaster situation database in a correlated manner;
inputting the diseased symptom information and the disaster information into a disease change prediction model to predict disease changes, and obtaining a disease change prediction result;
inputting the disease change prediction result and the initial medication scheme into a medication adjustment model to adjust the medication scheme to obtain a target medication scheme;
outputting the target medication scheme.
In a second aspect, the present application also provides a medication regimen adjustment device, the device comprising:
the health information acquisition module is used for acquiring the health information of a target user, wherein the health information comprises disease symptom information and an initial medication scheme;
the disaster information acquisition module is used for determining the position area information of the target user, inquiring a disaster database and acquiring disaster information corresponding to the position area information of the target user, wherein the position area information and the disaster information of disaster events are stored in the disaster database in a correlation manner;
the disease change prediction module is used for inputting the diseased symptom information and the disaster information into a disease change prediction model to predict disease changes and obtain a disease change prediction result;
the medication scheme adjusting module is used for inputting the disease change prediction result and the initial medication scheme into a medication scheme adjusting model to adjust the medication scheme to obtain a target medication scheme;
and the medication scheme output module is used for outputting the target medication scheme.
In a third aspect, the present application further provides a computer device comprising a memory and a processor;
the memory for storing a computer program;
the processor is configured to execute the computer program and to implement the medication regimen adjustment method as described above when executing the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement the medication regimen adjustment method as described above.
The application discloses a medication scheme adjusting method, a medication scheme adjusting device, computer equipment and a storage medium, wherein the disease symptom information and the initial medication scheme of a target user can be obtained by acquiring the health information of the target user; by determining the position area information of the target user, the disaster information of the position of the target user can be obtained by inquiring from a disaster database according to the position area information; disease change prediction is performed by inputting the disease symptom information and the disaster information into a disease change prediction model, so that the disease change prediction is performed according to the disaster information and the disease symptom information of a target user, and a disease change prediction result related to the disaster information can be obtained; the disease change prediction result and the initial medication scheme are input into the medication adjustment model to adjust the medication scheme, so that the initial medication scheme can be adjusted according to the disease change prediction information, and the medication scheme of a patient can be timely and accurately adjusted in case of disasters; by outputting the target medication scheme, the target user can adjust the medication according to the target medication scheme, so that the condition of the target user can be relieved or avoided from aggravating when a disaster occurs.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for adjusting a medication regimen provided in an embodiment of the present application;
FIG. 2 is a schematic illustration of a dosage regimen adjustment provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart diagram of sub-steps of training a disease change prediction model provided by an embodiment of the present application;
FIG. 4 is a schematic flow chart diagram of a substep of generating a disaster and disease relationship feature library provided by an embodiment of the present application;
FIG. 5 is a schematic flow chart diagram of sub-steps of training a medication adjustment model provided by an embodiment of the present application;
FIG. 6 is a schematic block diagram of a medication regimen adjustment device provided by an embodiment of the present application;
fig. 7 is a schematic block diagram of a structure of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
The embodiment of the application provides a medication scheme adjusting method, a medication scheme adjusting device, computer equipment and a storage medium. The medication scheme adjusting method can be applied to a server or a terminal, and can be used for predicting disease change according to disaster information and disease symptom information of a target user and adjusting the medication scheme according to the obtained disease change prediction information and medication information, so that the medication scheme of a patient can be timely and accurately adjusted when a disaster occurs.
The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. The terminal can be electronic equipment such as a smart phone, a tablet computer, a notebook computer, a desktop computer and wearable equipment.
It should be noted that, the embodiment of the present application may acquire and process related data based on an artificial intelligence technique. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
As shown in fig. 1, the medication adjustment method includes steps S10 to S50.
And step S10, acquiring health information of the target user, wherein the health information comprises disease symptom information and an initial medication scheme.
Illustratively, the health information includes disease symptom information and an initial medication regimen of the target user. In the present embodiment, the target user refers to a user with a chronic disease. Among them, chronic diseases may include, but are not limited to, hypertension, diabetes, chronic kidney disease, chronic obstructive pulmonary disease, coronary heart disease, hyperlipidemia, and the like.
Referring to fig. 2, fig. 2 is a schematic diagram of a medication regimen adjustment according to an embodiment of the present application. As shown in fig. 2, disease symptom information and disaster information may be input into the disease change prediction model to predict disease change, and a disease change prediction result may be obtained; then, the disease change prediction result and the initial medication scheme are input into a medication adjustment model to adjust the medication scheme, so that a target medication scheme is obtained. Therefore, the medication scheme of the patient can be timely and accurately adjusted when a disaster occurs, and the condition of the target user is relieved or prevented from aggravating when the disaster occurs.
In some embodiments, the health information of the target user may be collected through a terminal of the target user. Wherein the health information comprises disease symptom information and an initial medication scheme. Wherein, a healthy APP can be installed in the terminal and used for recording the disease symptom information and the initial medication scheme of the target user.
Illustratively, the disease symptom information may include blood pressure values, blood glucose values, blood lipid values, body temperature values, and the like. The information of the diseased symptoms can be acquired by a detection instrument used by a target user. For example, the blood pressure value of the target user is collected through a bluetooth sphygmomanometer, and the blood sugar value of the target user is collected through a bluetooth blood sugar meter; the healthy APP in the terminal can be in communication connection with the Bluetooth sphygmomanometer and the Bluetooth blood glucose meter, and data collected by the Bluetooth sphygmomanometer and the Bluetooth blood glucose meter are obtained. Of course, the target user may input information of disease symptoms such as blood pressure, blood sugar, blood lipid, and body temperature into the healthy APP.
It should be noted that the initial medication regimen refers to the current medication regimen of the target user. For example, the initial medication regimen may include information such as the type of medication, the dosage of the medication, the extent of the medication, and the number of times the medication was taken. The target user may fill in the health APP with an initial medication regimen and submit.
For example, when the medication scheme adjustment method is applied to the server, the health APP in the terminal may upload the information on the disease symptoms and the initial medication scheme to the server after detecting the information on the disease symptoms and the initial medication scheme filled by the target user.
In other embodiments, the system can be networked with a medical platform to acquire medical data of a target user; and determining the disease symptom information and the initial medication scheme of the target user according to the medical data. The medical data may include, but is not limited to, personal health profile, prescription, examination report, etc. data of the target user. For example, disease symptom information may be determined from the personal health profile and the examination report; an initial medication regimen is determined based on the prescription.
To further ensure privacy and security of the disease information and the initial medication scheme, the disease information and the initial medication scheme may be stored in a node of a blockchain. When acquiring the disease symptom information and the initial medication scheme of the target user, the information and the initial medication scheme can be read from the block link points.
By acquiring the health information of the target user, the current disease symptoms and the initial medication scheme of the target user can be acquired.
Step S20, determining the location area information of the target user, querying a disaster database, and obtaining disaster information corresponding to the location area information of the target user, where the location area information and the disaster information of the disaster event are stored in the disaster database in a correlated manner.
For example, the location area information may include location coordinates of the target user. For example, the location may be performed by a terminal corresponding to the target user, so as to obtain the location coordinates of the target user. As another example, the location coordinates of the target user may be determined from address information in the personal health profile.
Illustratively, the disaster database can be obtained from data channels such as Weijian Commission, weather bureau, Emergency management department, and the like.
The location area information of the disaster event refers to a location or an area where the disaster occurs. The disaster information can include, but is not limited to, disaster type, disaster level, and disaster duration. Wherein, the disaster types can be natural disasters such as cold tide, storm tide, flood, river flooding, debris flow, earthquake and the like.
Illustratively, the disaster situation database can be queried according to the location area information of the target user, so as to obtain disaster situation information corresponding to the location area information of the target user.
By acquiring the disaster information of the position of the target user, the initial medication scheme can be adjusted subsequently according to the diseased symptom information and the disaster information.
And step S30, inputting the diseased symptom information and the disaster information into a disease change prediction model to predict disease changes, and obtaining a disease change prediction result.
Illustratively, the disease change prediction model may be a multiple linear regression decision tree model. It should be noted that the multiple linear regression decision tree model is a model for predicting the variation trend of the dependent variable according to the independent variable. In the embodiment of the application, the disaster information can be used as an independent variable, the disease symptom information can be used as a dependent variable, and the change trend corresponding to the disease symptom information can be predicted through the disease change prediction model to obtain the disease change prediction result.
Illustratively, the disease change prediction model is a pre-trained model. In the embodiment of the application, the initial disease change prediction model can be trained to be convergent to obtain the trained disease change prediction model based on the diseased database, the disease knowledge base related to disaster information and the disaster database.
Referring to fig. 3, fig. 3 is a schematic flow chart illustrating sub-steps of training a disease change prediction model according to an embodiment of the present application, which may specifically include the following steps S301 to S303.
Step S301, acquiring a diseased database and acquiring a disease knowledge base related to disaster information.
Illustratively, the sick database and the disease knowledge base related to disaster information can be obtained from a medical platform, a chronic disease platform, a hospital platform, and the like. The acquisition mode of the disease database and the disease knowledge base is not limited herein.
Illustratively, the disease knowledge base may include information about disaster types, disaster grades, and effects of disaster duration on various types of diseases of different disaster events. The disease database includes disease data such as the type of disease and the type of symptoms of the patient. The disease database may include disease data of a plurality of patients in different location areas and different time periods, and may also include disease data of a location area of a target user or a plurality of patients during a current disaster.
It should be noted that the establishment of the relational feature library between the diseased data and the disaster information is realized by acquiring the diseased database and acquiring the disease knowledge base related to the disaster information, and further taking the disease knowledge base as a bridge.
And S302, generating a disaster situation and disease relation characteristic library according to the disaster situation database and the diseased database based on the disease knowledge base.
Referring to fig. 4, fig. 4 is a schematic flowchart of a sub-step of generating a disaster situation and disease relation feature library according to an embodiment of the present application, and specifically may include the following steps S3021 and S3022.
Step S3021, respectively performing data cleaning, normalization and feature extraction on the disaster information in the disaster database and the disease data in the disease database to obtain a target disaster database and a target disease database.
Illustratively, data cleansing may include, but is not limited to, checking data for consistency, handling invalid and missing values, and the like. And the data cleaning is used for removing useless data in the disaster database and the diseased database. Normalization is used to eliminate the dimensional effect between data metrics to account for comparability between data metrics. For example, the data can be normalized by min-max normalization, Z-score normalization, and the like. Feature extraction refers to vectorizing data. For example, vectorization processing may be performed on data by a bert (bidirectional Encoder responses from transform) model, a word2vec model, a glove model, and an ELMo model.
Illustratively, data cleaning, normalization and feature extraction can be performed on disaster information in the disaster database to obtain a target disaster database. The disease data in the disease database can be respectively subjected to data cleaning, normalization and feature extraction to obtain a target disease database. The specific processes of data cleaning, normalization and feature extraction are not limited herein.
Data accuracy of the target disaster database and the target disease database can be ensured by respectively carrying out data cleaning, normalization and feature extraction on the disaster information in the disaster database and the disease data in the disease database.
Step S3022, clustering the target disaster database and the target disease database according to the disease data of different disease types in the disease knowledge base to obtain the disaster and disease relation feature database.
It should be noted that, in the embodiment of the present application, the target disaster database and the target disease database may be clustered according to the disease data of different disease types, so that a relational feature library between the disease data and the disaster information may be established.
In some embodiments, clustering the target disaster database and the target disease database according to the disease data of different disease types in the disease knowledge base to obtain a disaster and disease relationship feature database may include: clustering disaster information related to a single disease type in a target disaster database to obtain a first disaster and disease relation characteristic database; clustering disease data related to a single disaster type in a target diseased database to obtain a second disaster and disease relation characteristic database; and fusing the first disaster situation and disease relation characteristic library and the second disaster situation and disease relation characteristic library to obtain a disaster situation and disease relation characteristic library.
For example, the target disaster database and the target disease database may be clustered based on a preset clustering algorithm. Clustering algorithms may include, but are not limited to, aggregate clustering, decomposed clustering, density-based clustering, artificial neural networks, subspace clustering, and federated clustering, among others.
Illustratively, disaster information related to a single disease type in the target disaster database is clustered to obtain a first disaster and disease relation feature database. For example, disaster information related to hypertension may be clustered, disaster information related to chronic kidney disease may be clustered, and disaster information related to chronic obstructive pulmonary disease may be clustered. Thereby obtaining a first disaster situation and disease relation characteristic library; the first disaster and disease relation feature library comprises the incidence relation between various disease types and disaster information.
Illustratively, disease data related to a single disaster type in the target diseased database is clustered to obtain a second disaster and disease relation characteristic database. For example, disease data related to cold tides may be clustered, and disease data related to storm tides may be clustered; therefore, a second disaster situation and disease relation characteristic library can be obtained, wherein the second disaster situation and disease relation characteristic library comprises the incidence relations between various disaster situation types and disease data.
Illustratively, the fusion process may include operations of merging, deduplication, and the like. For example, the first disaster and disease relational feature library and the second disaster and disease relational feature library are merged, and the repeated data are removed to obtain the disaster and disease relational feature library. The disaster and disease relation feature library comprises the incidence relation between various disaster information and various disease data.
Based on the disease knowledge base, the disaster situation and disease relation feature base is generated according to the disaster situation database and the disease database, and then the initial disease change prediction model can be trained according to the disaster situation and disease relation feature base, so that the disease change prediction model learns how to predict the disease change of the disease symptom information according to the disaster situation information.
And S303, performing iterative training on the disease change prediction model according to the disaster situation and disease relation feature library until the disease change prediction model is converged to obtain a trained disease change prediction model.
Illustratively, the iterative training process of the disease change prediction model is: determining training data of each round according to the disaster situation and disease relation feature library, inputting the training data of the current round into a disease change prediction model for training, and obtaining a training result corresponding to the training data of the current round; determining a loss function value corresponding to a training result based on a preset loss function; and if the loss function value is larger than the preset loss value threshold, adjusting parameters of the disease change prediction model, carrying out next round of training until the obtained loss function value is smaller than or equal to the loss value threshold, and ending the training to obtain the trained disease change prediction model.
The training result may include disease change prediction information corresponding to the current round of training data.
For example, the predetermined loss function may include, but is not limited to, an absolute loss function, a logarithmic loss function, a quadratic loss function, an exponential loss function, and the like. The loss value threshold may be set according to actual conditions, and specific values are not limited herein.
Illustratively, the parameters of the disease change prediction model may be adjusted by a gradient descent algorithm. The specific process of adjusting the parameters is not limited herein. It can be understood that the parameters of the disease change prediction model are adjusted according to the convergence algorithm, so that the disease change prediction model can be converged quickly, and the training efficiency is improved.
Through iterative training of the disease change prediction model according to the disaster situation and disease relation feature library, the trained disease change prediction model can have the function of predicting disease change.
For example, as shown in fig. 2, disease symptom information and disaster information may be input into a disease change prediction model to predict disease changes, and a disease change prediction result may be obtained.
For example, the disease change prediction result may include a change trend of the target user's disease. E.g., trends over one day, trends over three days, etc.
The disease change prediction is carried out by inputting the disease symptom information and the disaster information into the disease change prediction model, so that the disease change prediction is carried out according to the disaster information and the disease symptom information of the target user, and the disease change prediction result related to the disaster information can be obtained.
And step S40, inputting the disease change prediction result and the initial medication scheme into a medication adjustment model for medication scheme adjustment to obtain a target medication scheme.
It should be noted that the medication adjustment model may be a multiple linear regression decision tree model. In the embodiment of the present application, the medication adjustment model is used to adjust the initial medication regimen according to the disease change prediction result. Wherein, the medication adjustment model is a pre-trained model. For example, the initial medication adjustment model may be trained to converge based on the disease database and the disease knowledge base associated with disease changes, resulting in a trained medication adjustment model.
Referring to fig. 5, fig. 5 is a schematic flowchart illustrating sub-steps of training a medication adjustment model according to an embodiment of the present application, which may specifically include the following steps S401 to S403.
Step S401, acquiring a medication knowledge base related to disease change.
Illustratively, the knowledge base of medication related to disease changes may be obtained from a medical platform, a chronic disease platform, a hospital platform, or the like. The medication knowledge base comprises medication information corresponding to different stages and symptoms of various diseases.
And S402, generating a disease change and medication relation characteristic library according to the medication knowledge base and the diseased database.
In some embodiments, generating the disease change and medication relation feature library from the medication knowledge base and the disease database may include: based on different disease types in the disease database, clustering the medication information related to a single disease type in the medication knowledge base to obtain a disease change and medication relation feature base.
For example, the medication information related to a single disease type in the medication knowledge base may be clustered based on a clustering algorithm to obtain a disease change and medication relation feature base. For example, for hypertension, medication information related to hypertension can be clustered, and medication information corresponding to different stages and symptoms of hypertension can be obtained. For example, in the case of chronic obstructive pulmonary disease, medication information related to chronic obstructive pulmonary disease can be clustered to obtain medication information corresponding to different stages and symptoms of chronic obstructive pulmonary disease.
The disease change and medication relation characteristic library is generated according to the medication knowledge library and the disease database, and then the medication adjustment model can be iteratively trained according to the disease change and medication relation characteristic library, so that the trained medication adjustment model has the function of adjusting a medication scheme according to the disease change information.
And S403, performing iterative training on the medication adjustment model according to the disease change and medication relation feature library until the medication adjustment model converges to obtain a trained medication adjustment model.
Illustratively, the iterative training process of the medication adjustment model is as follows: determining training data of each round according to the disease change and the medication relation feature library, inputting the current round of training data into a medication adjustment model for training, and obtaining a training result corresponding to the current round of training data; determining a loss function value corresponding to a training result based on a preset loss function; and if the loss function value is larger than the preset loss function threshold, adjusting the parameters of the medication adjustment model, carrying out the next round of training until the obtained loss function value is smaller than or equal to the loss threshold, and finishing the training to obtain the trained medication adjustment model.
For example, the training results may include medication adjustment information corresponding to the current round of training data.
For example, the predetermined loss function may include, but is not limited to, an absolute loss function, a logarithmic loss function, a quadratic loss function, an exponential loss function, and the like. The loss function threshold may be set according to actual conditions, and specific values are not limited herein.
Illustratively, the parameters of the medication adjustment model may be adjusted by a gradient descent algorithm. The specific process of adjusting the parameters is not limited herein.
For example, as shown in fig. 2, the disease change prediction result and the initial medication scheme may be input into a medication adjustment model for medication scheme adjustment to obtain a target medication scheme.
Illustratively, the target medication regimen may include the type of medication, the dosage of the medication, the extent of medication, the number of times of medication, and medication notes, among others.
The disease change prediction result and the initial medication scheme are input into the medication adjustment model to adjust the medication scheme, so that the initial medication scheme can be adjusted according to the disease change prediction information, and the medication scheme of a patient can be timely and accurately adjusted in case of disasters.
And step S50, outputting the target medication scheme.
It should be noted that after obtaining the target medication scheme, the target medication scheme also needs to be output so that the target user can take medicine according to the target medication scheme.
For example, when the medication scheme adjustment method is applied to the server, the server may transmit the target medication scheme to the terminal of the target user. For example, the target medication is displayed in the health APP of the terminal. For another example, the target medication scheme may be sent to the terminal of the target user by way of short message, email, instant message, and the like.
For example, when the medication scheme adjustment method is applied to the terminal of the target user, the terminal may display the target medication scheme in the health APP.
To further ensure privacy and security of the target medication regimen, the target medication regimen may be stored in a blockchain node.
By outputting the target medication scheme, the target user adjusts the medication according to the target medication scheme, so that the condition of the target user can be relieved or avoided from aggravating, and meanwhile, the panic of the target user can be relieved.
In some embodiments, the embodiments of the present application may further include: determining the disease type of a target user; acquiring a disease rehabilitation scheme corresponding to the disease type, wherein the disease rehabilitation scheme comprises at least one of a measurement scheme, a diet scheme, a movement scheme and a development and education scheme; and outputting a disease rehabilitation program.
For example, medical data of the target user may be acquired through the medical platform, and the disease type of the target user may be determined according to the medical data. The medical data may include personal health records, prescriptions, examination reports, etc.
It should be noted that, in the embodiment of the present application, a disease rehabilitation program corresponding to each disease may be predefined, and the disease and the corresponding disease rehabilitation program may be stored in an associated manner. The disease may include a variety of types, among others.
For example, a disease rehabilitation program corresponding to a disease type may be obtained based on a preset correspondence between a disease and a disease rehabilitation program. Wherein the disease rehabilitation protocol comprises at least one of a measurement protocol, a diet protocol, an exercise protocol, and a education protocol.
For example, the measurement scheme may include information on the time and number of times the target user measures blood pressure, blood glucose, body temperature, and the like. The dietary regimen may include the type and amount of food ingested per meal by the target user. The exercise program may include the type of exercise and exercise time that the target user needs to perform daily, and so on. The education program is an article pushed to a target user, and can comprise disease risk control, diet guidance, exercise guidance, blood pressure monitoring, blood sugar monitoring, psychological counseling, complications and other types of articles.
Illustratively, when the disease rehabilitation scheme is output, the disease rehabilitation scheme can be sent to the terminal of the target user in a short message mode, an email mode, an instant message mode and the like; disease rehabilitation programs can also be shown directly in the healthy APP of the terminal.
By acquiring the disease rehabilitation scheme corresponding to the disease type of the target user, the disease rehabilitation scheme can be pushed to the target user according to the disease type in a targeted manner, and the rehabilitation of the target user is effectively promoted.
According to the medication scheme adjusting method provided by the embodiment, the current disease symptoms and the initial medication scheme of the target user can be obtained by obtaining the health information of the target user; by acquiring disaster information of the position of the target user, the initial medication scheme can be adjusted subsequently according to the diseased symptom information and the disaster information; based on the disease knowledge base, a disaster situation and disease relation feature base is generated according to the disaster situation database and the disease database, and then an initial disease change prediction model can be trained according to the disaster situation and disease relation feature base, so that the disease change prediction model learns how to predict the disease change of the disease symptom information according to the disaster situation information; the disease change and medication relation characteristic library is generated according to the medication knowledge library and the disease database, and then the medication adjustment model can be iteratively trained according to the disease change and medication relation characteristic library, so that the trained medication adjustment model has the function of adjusting a medication scheme according to the disease change information; the disease change prediction result and the initial medication scheme are input into the medication adjustment model to adjust the medication scheme, so that the initial medication scheme can be adjusted according to the disease change prediction information, and the medication scheme of a patient can be timely and accurately adjusted in case of disasters; by outputting the target medication scheme, the target user adjusts the medication according to the target medication scheme, so that the condition of the target user can be relieved or avoided from aggravating, and meanwhile, the panic of the target user can be relieved; by acquiring the disease rehabilitation scheme corresponding to the disease type of the target user, the disease rehabilitation scheme can be pushed to the target user according to the disease type in a targeted manner, and the rehabilitation of the target user is effectively promoted.
Referring to fig. 6, fig. 6 is a schematic block diagram of a medication scheme adjusting apparatus 1000 according to an embodiment of the present application, which is used for executing the medication scheme adjusting method. Wherein, the medication scheme adjusting device can be configured in a server or a terminal.
As shown in fig. 6, the medication schedule adjustment apparatus 1000 includes: a health information acquisition module 1001, a disaster information acquisition module 1002, a disease change prediction module 1003, a medication scheme adjustment module 1004, and a medication scheme output module 1005.
A health information obtaining module 1001, configured to obtain health information of a target user, where the health information includes disease symptom information and an initial medication scheme.
The disaster information obtaining module 1002 is configured to determine location area information of the target user, query a disaster database, and obtain disaster information corresponding to the location area information of the target user, where the location area information and the disaster information of the disaster event are stored in the disaster database in an associated manner.
A disease change prediction module 1003, configured to input the disease symptom information and the disaster information into a disease change prediction model to perform disease change prediction, so as to obtain a disease change prediction result.
And a medication scheme adjusting module 1004, configured to input the disease change prediction result and the initial medication scheme into a medication scheme adjusting model for medication scheme adjustment, so as to obtain a target medication scheme.
A medication scheme output module 1005 for outputting the target medication scheme.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus and the modules described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The apparatus described above may be implemented in the form of a computer program which is executable on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present disclosure.
Referring to fig. 7, the computer device includes a processor and a memory connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.
The internal memory provides an environment for the execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any of the methods of medication regimen adjustment.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:
acquiring health information of a target user, wherein the health information comprises disease symptom information and an initial medication scheme; determining the position area information of the target user, inquiring a disaster situation database, and acquiring disaster situation information corresponding to the position area information of the target user, wherein the position area information and the disaster situation information of disaster events are stored in the disaster situation database in a correlated manner; inputting the diseased symptom information and the disaster information into a disease change prediction model to predict disease changes, and obtaining a disease change prediction result; inputting the disease change prediction result and the initial medication scheme into a medication adjustment model to adjust the medication scheme to obtain a target medication scheme; outputting the target medication scheme.
In one embodiment, the processor is further configured to, before implementing inputting the disease symptom information and the disaster information into a disease change prediction model for disease change prediction and obtaining a disease change prediction result, implement:
acquiring a diseased database and acquiring a disease knowledge base related to disaster information; based on the disease knowledge base, generating a disaster and disease relation characteristic base according to the disaster database and the diseased database; and performing iterative training on the disease change prediction model according to the disaster situation and disease relation feature library until the disease change prediction model converges to obtain a trained disease change prediction model.
In one embodiment, the processor, when implementing generating the disaster situation and disease relation feature library from the disaster situation database and the disease database based on the disease knowledge base, is configured to implement:
respectively carrying out data cleaning, normalization and feature extraction on the disaster information in the disaster database and the disease data in the diseased database to obtain a target disaster database and a target diseased database; and clustering the target disaster situation database and the target disease database according to different types of disease data in the disease knowledge base to obtain the disaster situation and disease relation characteristic base.
In one embodiment, the disaster information in the disaster database includes a disaster type, and the disease data in the diseased database includes a disease type; the processor is used for clustering the target disaster situation database and the target disease database according to the disease data of different disease types in the disease knowledge base to obtain the disaster situation and disease relation feature base, and is used for realizing that:
clustering disaster information related to a single disease type in the target disaster database to obtain a first disaster and disease relation characteristic database; clustering disease data related to a single disaster type in the target diseased database to obtain a second disaster and disease relation characteristic database; and fusing the first disaster situation and disease relation characteristic library and the second disaster situation and disease relation characteristic library to obtain the disaster situation and disease relation characteristic library.
In one embodiment, the processor is further configured to, prior to implementing the medication regimen adjustment of the disease change prediction result and the initial medication regimen input medication adjustment model to obtain a target medication regimen:
acquiring a medicine use knowledge base related to disease change; generating a disease change and medication relation feature library according to the medication knowledge base and the diseased database; and performing iterative training on the medication adjustment model according to the disease change and medication relation feature library until the medication adjustment model converges to obtain a trained medication adjustment model.
In one embodiment, the processor, in implementing generating the disease change and medication relation feature library from the medication knowledge base and the disease database, is configured to implement:
and clustering the medication information related to the single disease type in the medication knowledge base based on different disease types in the diseased database to obtain the disease change and medication relation characteristic base.
In one embodiment, the processor is further configured to implement:
determining the disease type of the target user; acquiring a disease rehabilitation scheme corresponding to the disease type, wherein the disease rehabilitation scheme comprises at least one of a measurement scheme, a diet scheme, a movement scheme and a development and education scheme; outputting the disease rehabilitation program.
The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, where the computer program includes program instructions, and the processor executes the program instructions to implement any one of the medication scheme adjustment methods provided in the embodiments of the present application.
For example, the program is loaded by a processor and may perform the following steps:
acquiring health information of a target user, wherein the health information comprises disease symptom information and an initial medication scheme; determining the position area information of the target user, inquiring a disaster situation database, and acquiring disaster situation information corresponding to the position area information of the target user, wherein the position area information and the disaster situation information of disaster events are stored in the disaster situation database in a correlated manner; inputting the diseased symptom information and the disaster information into a disease change prediction model to predict disease changes, and obtaining a disease change prediction result; inputting the disease change prediction result and the initial medication scheme into a medication adjustment model to adjust the medication scheme to obtain a target medication scheme; outputting the target medication scheme.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital Card (SD Card), a Flash memory Card (Flash Card), and the like provided on the computer device.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110991094.3A CN113689930A (en) | 2021-08-26 | 2021-08-26 | Medication regimen adjustment method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110991094.3A CN113689930A (en) | 2021-08-26 | 2021-08-26 | Medication regimen adjustment method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113689930A true CN113689930A (en) | 2021-11-23 |
Family
ID=78583102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110991094.3A Pending CN113689930A (en) | 2021-08-26 | 2021-08-26 | Medication regimen adjustment method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689930A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118335283A (en) * | 2024-05-22 | 2024-07-12 | 北京大学人民医院 | Rehabilitation plan adjustment method, device, equipment and medium based on user portrait |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111063413A (en) * | 2019-12-30 | 2020-04-24 | 广州享药户联优选科技有限公司 | Method and device for adjusting medication scheme based on medication condition |
| CN111383754A (en) * | 2018-12-28 | 2020-07-07 | 医渡云（北京）技术有限公司 | Medical decision method, medical decision device, electronic device, and storage medium |
| CN112349420A (en) * | 2020-10-24 | 2021-02-09 | 武汉东湖大数据交易中心股份有限公司 | Method and system for constructing disease prediction model based on meteorological data |
-
2021
- 2021-08-26 CN CN202110991094.3A patent/CN113689930A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111383754A (en) * | 2018-12-28 | 2020-07-07 | 医渡云（北京）技术有限公司 | Medical decision method, medical decision device, electronic device, and storage medium |
| CN111063413A (en) * | 2019-12-30 | 2020-04-24 | 广州享药户联优选科技有限公司 | Method and device for adjusting medication scheme based on medication condition |
| CN112349420A (en) * | 2020-10-24 | 2021-02-09 | 武汉东湖大数据交易中心股份有限公司 | Method and system for constructing disease prediction model based on meteorological data |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118335283A (en) * | 2024-05-22 | 2024-07-12 | 北京大学人民医院 | Rehabilitation plan adjustment method, device, equipment and medium based on user portrait |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Choi et al. | Smartphone applications to support sleep self-management: review and evaluation | |
| US9367666B2 (en) | Mapping cognitive to functional ability | |
| US20170147777A1 (en) | Method and apparatus for predicting health data value through generation of health data pattern | |
| JP2024513618A (en) | Methods and systems for personalized prediction of infections and sepsis | |
| US20200075167A1 (en) | Dynamic activity recommendation system | |
| US20070094048A1 (en) | Expert knowledge combination process based medical risk stratifying method and system | |
| JP2018524137A (en) | Method and system for assessing psychological state | |
| WO2019070200A1 (en) | A healthcare information management system | |
| Oti et al. | IoT-based healthcare system for real-time maternal stress monitoring | |
| CN113679348A (en) | Blood glucose prediction method, blood glucose prediction device, blood glucose prediction apparatus, and storage medium | |
| US12417831B2 (en) | Systems and methods for creating and selecting models for predicting medical conditions | |
| CN113658704A (en) | Diabetes risk prediction device, device and storage medium | |
| US20230090138A1 (en) | Predicting subjective recovery from acute events using consumer wearables | |
| CN112542242B (en) | Data conversion/symptom scoring | |
| US20240006052A1 (en) | System implementing generative adversarial network adapted to prediction in behavioral and/or physiological contexts | |
| CN113990482A (en) | Health data processing system and method | |
| CN120565117B (en) | Patient disease evolution relation prediction method and system based on time sequence diagram neural network | |
| US8428965B2 (en) | System for clinical research and clinical management of cardiovascular risk using ambulatory blood pressure monitoring and actigraphy | |
| CN118841187A (en) | Patient compliance assessment system | |
| Melnykova et al. | Anomalies detecting in medical metrics using machine learning tools | |
| Potter et al. | Integrating intensive longitudinal data (ILD) to inform the development of dynamic theories of behavior change and intervention design: A case study of scientific and practical considerations | |
| CN113689930A (en) | Medication regimen adjustment method, device, computer equipment and storage medium | |
| Cheng et al. | Classification models for pulmonary function using motion analysis from phone sensors | |
| Gosciak et al. | Bias delayed is bias denied? Assessing the effect of reporting delays on disparity assessments | |
| CN114649071A (en) | Real world data-based peptic ulcer treatment scheme prediction system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221025 Address after: Room 2601 (Unit 07), Qianhai Free Trade Building, No. 3048, Xinghai Avenue, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Ping An Smart Healthcare Technology Co.,Ltd. Address before: 1-34 / F, Qianhai free trade building, 3048 Xinghai Avenue, Mawan, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong 518000 Applicant before: Ping An International Smart City Technology Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211123 |