CN112037932B - Patient medication behavior intervention method and device, server and storage medium - Google Patents
Patient medication behavior intervention method and device, server and storage medium Download PDFInfo
- Publication number
- CN112037932B CN112037932B CN202010940492.8A CN202010940492A CN112037932B CN 112037932 B CN112037932 B CN 112037932B CN 202010940492 A CN202010940492 A CN 202010940492A CN 112037932 B CN112037932 B CN 112037932B
- Authority
- CN
- China
- Prior art keywords
- medication
- behavior
- intervention
- target
- data
- 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.)
- Active
Links
- 239000003814 drug Substances 0.000 title claims abstract description 404
- 229940079593 drug Drugs 0.000 title claims abstract description 363
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000006399 behavior Effects 0.000 claims abstract description 383
- 230000015654 memory Effects 0.000 claims abstract description 34
- 230000036772 blood pressure Effects 0.000 claims description 17
- 230000003542 behavioural effect Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 230000035622 drinking Effects 0.000 claims description 6
- 208000024891 symptom Diseases 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004590 drinking behavior Effects 0.000 claims description 2
- 208000007271 Substance Withdrawal Syndrome Diseases 0.000 claims 4
- 206010020772 Hypertension Diseases 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 230000000391 smoking effect Effects 0.000 description 7
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000001631 hypertensive effect Effects 0.000 description 4
- 230000003442 weekly effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 230000003205 diastolic effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 206010010164 Hypertension complications Diseases 0.000 description 1
- 206010047513 Vision blurred Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- ZPBWCRDSRKPIDG-UHFFFAOYSA-N amlodipine benzenesulfonate Chemical compound OS(=O)(=O)C1=CC=CC=C1.CCOC(=O)C1=C(COCCN)NC(C)=C(C(=O)OC)C1C1=CC=CC=C1Cl ZPBWCRDSRKPIDG-UHFFFAOYSA-N 0.000 description 1
- 229960004005 amlodipine besylate Drugs 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- 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
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The application discloses a method and a device for intervention of medication behavior of a patient, a server and a storage medium, which are applicable to medical science and technology, wherein the method comprises the following steps: acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-medication behavior data, the preset time period comprises n time periods, and n is a natural number; learning behavior data through a long-short-time memory network LSTM to obtain a medication behavior probability sequence in an n+1th time period; determining the medication behavior type of a target patient in an n+1th time period according to the medication behavior probability sequence; and determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to a target patient based on the target intervention strategy. By adopting the application, the medication compliance of patients can be improved.
Description
Technical Field
The application relates to the technical field of medical and health service Internet, in particular to a method and a device for intervention of medication behavior of a patient, a server and a storage medium.
Background
Poor medication compliance is a common problem in chronic management, and this problem arises mainly from the following: the patient does not know the medication compliance well, and the patient is considered to stop taking the medication after the illness state is improved, for example, the patient suffering from hypertension stops taking the medication once the blood pressure is found to be normal; the clinical doctor has insufficient patient teaching force, the patient does not have knowledge about the patient, and the patient forgets to take medicine, has wrong dosage and the like.
In the prior art, the medication intervention aiming at the patient usually is performed only when the patient stops taking the medication or the patient does not take the medication on time and the body is uncomfortable, and the intervention is not timely. In addition, in order to manage a large number of patients, the medication intervention in the prior art is generally performed by simply aiming at medication classification, so that the intervention effect is poor, and the applicability is poor.
Disclosure of Invention
The application provides a patient medication behavior intervention method and device, a server and a storage medium, which can improve medication compliance of patients and have high applicability.
In a first aspect, the present application provides a method of intervention in a patient medication behavior comprising:
acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-medication behavior data, the preset time period comprises n time periods, and n is a natural number;
Learning the behavior data through a long-short-term memory network LSTM to obtain a medication behavior probability sequence in the (n+1) th time period;
Determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence;
and determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to the target patient based on the target intervention strategy.
With reference to the first aspect, in one possible implementation manner, the learning the behavior data through the long-short-term memory network LSTM includes:
Sequencing the behavior data in the preset duration according to a preset sequence to obtain a sequenced behavior data sequence, and inputting the behavior data sequence into the LSTM;
And learning the medication behavior type of the next time period corresponding to the behavior data of each time period in the n time periods by using the LSTM as a learning task according to the multi-classification problem of the multiple medication behavior types.
With reference to the first aspect, in one possible implementation manner, one medication behavior probability in the medication behavior probability sequence corresponds to one medication behavior type;
the determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence includes:
And determining the medication behavior type corresponding to the maximum medication behavior probability in the medication behavior probability sequence as the medication behavior type of the target patient in the n+1 time period.
With reference to the first aspect, in a possible implementation manner, the determining a target intervention strategy according to the medication behavior type and the non-medication behavior data includes:
Generating a self-management label of the target patient according to the medication behavior type and the non-medication behavior data;
Calculating the matching degree of the self-management label and the strategy label of each intervention strategy in the intervention strategy set to obtain a plurality of matching degree values, wherein the preset intervention strategy set comprises a plurality of intervention strategies, and one intervention strategy carries at least one strategy label;
and determining an intervention strategy corresponding to the maximum value in the plurality of matching degree values as the target intervention strategy.
With reference to the first aspect, in one possible implementation manner, the target intervention strategy includes a medication reminding mode and a medication reminding frequency;
the sending medication reminding information to the target patient based on the target intervention strategy includes:
In a preset time period, sending the medication reminding information to the target patient in the medication reminding mode according to the medication reminding frequency;
the medication reminding mode comprises a text prompt or a voice prompt.
With reference to the first aspect, in one possible implementation manner, the acquiring behavior data of the target patient within a preset duration includes:
Sending a behavior data acquisition prompt to a target patient according to a preset frequency so as to prompt the target patient to feed back behavior data according to a target data acquisition form, wherein the target data acquisition form comprises web page link acquisition or two-dimensional code acquisition;
And receiving the behavior data fed back by the target patient to serve as the behavior data of the target patient in a preset time period.
In a second aspect, the present application provides a patient behavioral intervention device comprising:
the behavior data acquisition module is used for acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-medication behavior data, the preset time period comprises n time periods, and n is a natural number;
The probability sequence learning module is used for learning the behavior data through a long-short-time memory network LSTM so as to obtain a medication behavior probability sequence in the (n+1) th time period;
The behavior type determining module is used for determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence;
And the determining and sending module is used for determining a target intervention strategy according to the medication behavior type and the non-medication behavior data and sending medication reminding information to the target patient based on the target intervention strategy.
With reference to the second aspect, in one possible implementation manner, the target intervention strategy includes a medication reminding mode and a medication reminding frequency;
The determining and sending module is used for sending the medication reminding information to the target patient in the medication reminding mode according to the medication reminding frequency in a preset time period;
the medication reminding mode comprises a text prompt or a voice prompt.
With reference to the second aspect, in one possible implementation manner, the probability sequence learning module is configured to:
Sequencing the behavior data in the preset duration according to a preset sequence to obtain a sequenced behavior data sequence, and inputting the behavior data sequence into the LSTM;
And learning the medication behavior type of the next time period corresponding to the behavior data of each time period in the n time periods by using the LSTM as a learning task according to the multi-classification problem of the multiple medication behavior types.
With reference to the second aspect, in one possible implementation manner, one medication behavior probability in the medication behavior probability sequence corresponds to one medication behavior type;
The behavior type determining module is configured to determine a medication behavior type corresponding to a maximum medication behavior probability in the medication behavior probability sequence as a medication behavior type of the target patient in the n+1th time period.
With reference to the second aspect, in one possible implementation manner, the determining sending module includes:
a label generating unit for generating a self-management label of the target patient according to the medication behavior type and the non-medication behavior data;
The matching degree calculating unit is used for calculating the matching degree of the self-management label and the strategy labels of all the intervention strategies in the intervention strategy set to obtain a plurality of matching degree values, wherein the preset intervention strategy set comprises a plurality of intervention strategies, and one intervention strategy carries at least one strategy label;
and the strategy determining unit is used for determining the intervention strategy corresponding to the maximum value in the plurality of matching degree values as the target intervention strategy.
With reference to the second aspect, in one possible implementation manner, the behavior data acquisition module includes:
the system comprises a sending prompt unit, a behavior data acquisition unit and a behavior data acquisition unit, wherein the sending prompt unit is used for sending a behavior data acquisition prompt to a target patient according to a preset frequency so as to prompt the target patient to feed back behavior data according to a target data acquisition form, and the target data acquisition form comprises web page link acquisition or two-dimensional code acquisition;
and the receiving data unit is used for receiving the behavior data fed back by the target patient to serve as the behavior data of the target patient in a preset duration.
In a third aspect, the present application provides a server comprising a processor, a memory and a transceiver, said processor, memory and transceiver being interconnected, wherein said memory is adapted to store a computer program supporting said text encryption apparatus to perform said patient medication behavior intervention method, said computer program comprising program instructions; the processor is configured to invoke the program instructions to perform the patient medication behavior intervention method as described above in the first aspect of the application.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program comprising program instructions; the program instructions, when executed by a processor, cause the processor to perform a patient medication behavior intervention method as described above in the first aspect of the application.
In the application, a medication behavior intervention platform acquires behavior data of a target patient in a preset time period, wherein the behavior data comprises non-medication behavior data, the preset time period comprises n time periods, and n is a natural number; learning behavior data through a long-short-time memory network LSTM to obtain a medication behavior probability sequence in an n+1th time period; determining the medication behavior type of a target patient in an n+1th time period according to the medication behavior probability sequence; and determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to a target patient based on the target intervention strategy. By adopting the application, the medication compliance of patients can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the architecture of a tamper system for medication behavior provided by the present application;
FIG. 2 is a flow chart of the method for intervention in patient medication behavior provided by the present application;
FIG. 3 is another flow chart of the patient behavioral intervention method provided by the present application;
FIG. 4 is a schematic diagram of a patient behavioral intervention device according to the present application;
Fig. 5 is a schematic structural diagram of a server provided by the present application.
Detailed Description
The following description of the embodiments of the present application will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the application are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application provides a patient medication behavior intervention method, which can be used for determining the medication behavior type of a target patient in the n+1th time period by learning the behavior data of the first n time periods through a long short-term memory (LSTM) network model according to the behavior data of the target patient in the first n time periods, determining a target intervention strategy according to the medication behavior type and non-medication behavior data in the behavior data of the first n time periods, and sending medication reminding information to the target patient based on the target intervention strategy, so that the medication compliance of the patient is improved.
The method for intervention of the medication behavior of the patient provided by the application can be applied to a medication behavior intervention system, wherein the system comprises a medication behavior intervention platform and a patient terminal cluster, and please refer to fig. 1, which is a schematic diagram of the architecture of the medication behavior intervention system provided by the application. As shown in fig. 1, the architecture schematic includes a medication behavior intervention platform 100 and a patient terminal cluster 101, where the patient terminal cluster 101 may include a plurality of patient terminals, as shown in fig. 1, specifically may include a patient terminal 101a, a patient terminal 101b, patient terminals 101c, …, and a patient terminal 101n, and the target patient terminal may be any patient terminal in the patient terminal cluster 101, and the description of the present application uses the terminal patient 101a in fig. 1 as the target patient terminal.
Each patient terminal in the medication behavior intervention platform 100 and the patient terminal cluster 101 may be a computer device, including a mobile phone, a tablet computer, a notebook computer, a palm computer, a mobile internet device (MID, mobile INTERNET DEVICE), a Point Of Sale (POS) machine, a wearable device (e.g., a smart watch, a smart bracelet, etc.), and so on.
In the patient medication behavior intervention method provided by the application, the medication behavior intervention platform 100 can send a behavior data acquisition prompt to the patient terminal 101a according to a preset frequency so as to prompt a target patient of the patient terminal 101a to feed back the behavior data according to a target data acquisition form. Here, the preset frequency may be once a day, once a week, etc., and the target data acquisition form may include web page link acquisition or two-dimensional code acquisition, which is not limited in the present application. The medication behavior intervention platform 100 receives the behavior data fed back by the patient terminal 101a as the behavior data of the target patient in the first n periods. Here, n is a natural number, and the behavior data may include medication behavior data, which may include medicine data, medication data, withdrawal data, and the like, and non-medication behavior data, which may include patient basic data, lifestyle data, physical symptom data, and the like. The medication behavior intervention platform 100 may learn behavior data of the target patient in the first n time periods through the LSTM, so as to obtain a medication behavior probability sequence of the n+1th time period, and determine a medication behavior type corresponding to a maximum value of the medication behavior probabilities in the medication behavior probability sequence as the medication behavior type of the target patient in the n+1th time period. Then, the medication behavior intervention platform 100 generates a self-management tag according to the medication behavior type and the non-medication behavior data, calculates a matching degree value between the self-management tag and the policy tag of each intervention policy in the preset intervention policy set, determines a target intervention policy according to the matching degree value, and sends medication reminding information to the patient terminal 101a where the target patient is located according to the target intervention policy.
For convenience of description, the following will use the medication behavior intervention platform as an execution subject, and the patient medication behavior intervention method provided by the application is illustrated with reference to fig. 2 to 3.
Referring to fig. 2, a flow chart of the method for intervention of medication behavior of a patient according to the present application is shown. As shown in fig. 2, the method provided by the present application may include the following steps:
s101, acquiring behavior data of a target patient in a preset duration.
In some possible embodiments, the preset duration includes n time periods, where n is a natural number. For example, the preset time period may be one month and the one period may be one week. The behavioral data may include medication behavioral data and non-medication behavioral data. The medication behavior data may include medicine data (such as amlodipine besylate tablet, 5 mg/time, 1 time/day), medicine taking data (such as forgetting to take medicine, forgetting to take medicine 1 time), medicine stopping data (such as if the medicine is stopped). The non-medication behavioral data may include patient basic data (e.g., age, sex, race, height, weight), lifestyle data (e.g., whether smoking, drinking, etc.), and physical symptom data (e.g., blood pressure level changes, dizziness, blurred vision, etc.).
In some possible embodiments, the medication behavior intervention platform sends a behavior data acquisition prompt to the target patient according to a preset frequency to prompt the target patient to feed back the behavior data according to a target data acquisition form, and receives the behavior data fed back by the target patient as the behavior data of the target patient within a preset duration. The target data acquisition form comprises web page link acquisition or two-dimensional code acquisition.
For example, assuming that the preset duration is two months, i.e., eight weeks, and the preset frequency is once a week, the medication behavior intervention platform may send a behavior data acquisition prompt to the hypertensive patient a every friday afternoon seven points in july to eight months. The hypertensive patient A receives the behavior data acquisition prompt, fills in weekly behavior data by accessing a webpage link carried by the behavior data acquisition prompt, and returns the weekly behavior data to the medication behavior intervention platform by clicking a confirmation key of a webpage where the webpage link is located after filling in. The medication behavior intervention platform receives behavior data of a patient with hypertension A from July to July weekly, so as to obtain behavior data of the patient with hypertension A from July to July weekly.
S102, learning behavior data through a long-short-term memory network LSTM to obtain a medication behavior probability sequence in an n+1th time period.
In some possible embodiments, the medication behavior intervention platform may first construct an LSTM network model, sort behavior data within a preset duration according to a preset order to obtain a sorted behavior data sequence, and input the behavior data sequence into the LSTM. The LSTM learns the medication behavior types of the next time period corresponding to the behavior data of each time period in the n time periods by taking the multi-classification problem of the multiple medication behavior types as a learning task, so that a medication behavior probability sequence of the n+1th time period is obtained. The preset sequence can be the sequence from the early to the late, and the medication behavior types can be four types of intentionally stopping medication, forgetting to take the medication 1 time, forgetting to take the medication 2-3 times and forgetting to take the medication more than 3 times, and can be determined according to actual application scenes without limitation. The time period may be one day, one week, etc., and may be specifically determined according to the actual application scenario, which is not limited herein.
For example, the medication behavior intervention platform sorts the behavior data (life behavior data, medication behavior type, etc.) of 4 weeks of 7 months according to the time sequence of the first week, the second week, the third week, and the fourth week to obtain the behavior data sequence. And inputting the behavior data sequence into an LSTM, and learning the behavior types of the second week corresponding to the behavior data of the first week, the … and the fourth week corresponding to the behavior data of the third week by taking the multi-classification problem of four behavior types of intentionally stopping, forgetting to take the medicine 1 time, forgetting to take the medicine 2-3 times and forgetting to take the medicine more than 3 times as learning tasks through the LSTM, thereby obtaining the behavior probability sequence of the fifth week.
In some possible implementations, the bidirectional LSTM provided in the embodiments of the present application includes a plurality of LSTM memory cells, where each parameter in the LSTM memory cell may be determined by the following formulas 1 to 5.
Wherein formulas 1 to 5 satisfy:
it＝σ(Wixt+Uiht-1) (1)
ft＝σ(Wfxt+Ufht-1) (2)
ot＝σ(Woxt+Uoht-1) (3)
In the above formulas 1 to 5, σ (x) is equal to Are nonlinear activation functions.
Wherein σ (x) is a sigmoid function and satisfies: σ (x) = (1+exp (-x)) -1.
Is a tanh function and satisfies:
in the present application, the behavior data of n time periods are serially connected in a preset time sequence (from early to late) in a sequential manner to form a behavior data sequence, and are input into the LSTM, so that the behavior data input at a certain time t corresponds to a certain time period of the n time periods, and thus, in the above formulas 1 to 5, the variable t may correspond to the time period. x t represents behavior data corresponding to a time period input at the time t. i t,ft and o t represent input gates at time t, respectively, and the memory gate and output gate output a medication behavior probability sequence of the target patient in a next time period of the time period corresponding to the behavior data input at time t. For example, if x t represents the entered behavioral data of the target patient in the first week, o t represents the medication behavior probability sequence of the target patient in the second week. Wherein the input gate, the memory gate and the output gate are collectively referred to as a logic gate of the LSTM memory cell. c t represents the information of the target patient represented by the behavior data input at time t, which may be referred to as the information of the LSTM memory cell at the current time t for convenience of description.
In the LSTM network provided by the present application, there is a weight transfer matrix W of an input x t corresponding to each time period at the current time t and an implicit variable h t-1 corresponding to the last time period of each time period at the last time t-1 in the calculation of the information of the LSTM memory unit at the current time t and the probability output by each logic gate (input gate, output gate, memory gate) in the LSTM memory unit. For example, W i corresponding to i t, W f corresponding to f t, W o corresponding to o t, and W c corresponding to c t, and the like. Wherein, the hidden variable h t-1 can be determined by the output gate of the last time t-1 and the output of the memory unit. Wherein the implicit variable is an invisible state variable and is a parameter relative to the observable variable. The observable variables may include features that can be derived directly from the image to be detected, with implicit variables being variables that are higher than the abstract concept of one layer of these observable variables, and implicit variables being parameters that can be used to control the change of the observable variables.
S103, determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence.
In some possible embodiments, one of the medication behavior probabilities in the medication behavior probability sequence corresponds to one of the medication behaviors, and the medication behavior intervention platform determines the medication behavior corresponding to the maximum medication behavior probability in the medication behavior probability sequence as the medication behavior type of the n+1th time period.
For example, according to step S102, the medication behavior probability sequence of the fifth week is 0.1,0.2,0.1,0.6, and the medication behaviors corresponding to the medication behavior probabilities in the medication behavior probability sequence are the intentional medication stoppage, the medication forgetting to take 1 time, the medication forgetting to take 2-3 times and the medication forgetting to take more than 3 times, respectively, and then the medication behavior intervention platform determines that the medication behavior type of the fifth week is determined by the medication behavior intervention platform corresponding to 0.6 for more than 3 times.
S104, determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to a target patient based on the target intervention strategy.
Before executing step S104, the medication behavior intervention platform obtains a plurality of medication behavior intervention schemes, each intervention scheme including a medication behavior type of the patient, non-medication behavior data, and an intervention policy, and generates a plurality of policy tags, or a combination policy tag, according to the medication behavior type of the patient and the non-medication behavior data in each intervention scheme. For example, the type of medication behavior of the patient with hypertension in the first intervention plan is that the patient forgets to take the medication 1 time, the non-medication behavior data comprise exercise behavior and unchanged blood pressure level, and the combined policy label generated in the mode is that the patient forgets to take the medication 1 time-exercise-unchanged blood pressure level. And then, the medication behavior intervention platform obtains an intervention strategy set according to the intervention strategies in each intervention scheme and the strategy labels carried by the intervention strategies.
It should be noted that, the form of the policy tag generated by the medication behavior intervention platform is the same as the form of the self-management tag, in other words, if the form of the policy tag is a combination tag, the form of the self-management tag is also a combination tag; if the policy tag is in the form of a plurality of tags, the self-managing tag is also in the form of a plurality of tags. The present application is illustrated in the form of a policy tag and a self-managing tag, each of which is a plurality of tags.
In some possible embodiments, the medication behavior intervention platform generates a self-management label of the target patient according to the medication behavior type and the non-medication behavior data, calculates the matching degree of the self-management label and the strategy label of each intervention strategy in the intervention strategy set to obtain a plurality of matching degree values, and the preset intervention strategy set comprises a plurality of intervention strategies, wherein one intervention strategy carries at least one strategy label; and determining the intervention strategy corresponding to the maximum value in the plurality of matching degree values as a target intervention strategy.
Specifically, the medication behavior intervention platform can generate self-management labels according to the medication behavior types, life style data and physical symptom data in the non-medication behavior data. For example, if the type of medication behavior of the target patient is intentional withdrawal, the lifestyle data includes smoking-free behavior and drinking behavior, and the physical symptom data is a large range of blood pressure level variation, the self-management label generated according to the above data may be intentional withdrawal, drinking, and a large range of blood pressure level variation. If the self-management label of the target patient is A, B, C and the policy labels of the ith intervention policy are a, b and c, the matching degree calculation formula between the self-management label and the policy label of the ith intervention policy may be the sum of the matching degrees between the self-management label A, B, C and the policy labels a, b and c of the ith intervention policy, respectively. The matching degree between the single self-management tag and the single policy tag can be obtained through a preset matching degree table (as shown in table 1, table 1 is a matching table of the self-management tag and the policy tag).
TABLE 1
Wherein A, B, C, D, E and … … in the self-management label can respectively indicate that the medicine is stopped intentionally, the medicine is forgotten to be taken more than 3 times, the medicine is forgotten to be taken 2-3 times, the medicine is forgotten to be taken 1 time, the blood pressure change range is large and … …, a, b, c and … … in the policy label can respectively indicate that the medicine is stopped intentionally, the medicine is forgotten to be taken more than 3 times, the medicine is forgotten to be taken 2-3 times and … …, the matching degree between the policy label a and the self-management label A, B, C, D, E is respectively 10, 0 and 5, the matching degree between the policy label b and the self-management label A, B, C, D, E is respectively 10, 0 and 4, and the matching degree between the policy label c and the self-management label A, B, C, D, E is respectively 10, 0 and 0.
For example, assuming that the self-management label of hypertensive patient X includes forgetting to take the drug 2-3 times, drinking, and the blood pressure level varies widely, the policy label of the ith intervention policy includes intentional withdrawal, smoking, and the blood pressure level varies widely. The medication behavior intervention platform obtains the matching degree between the self-management label forgetting to take the medicine for 2-3 times and the policy label intentionally stopping the medicine, smoking and having a large blood pressure level change range respectively by searching a preset matching degree table (shown in table 1) as 0, 0 and 3, the matching degree between the self-management label drinking wine and the policy label intentionally stopping the medicine, smoking and having a large blood pressure level change range is 0, 0 and 2, and the matching degree between the self-management label blood pressure level change range and the policy label intentionally stopping the medicine, smoking and having a large blood pressure level change range is 5, 1 and 10 respectively, so that the matching degree between the self-management label and the policy label of the ith intervention policy is 21. According to the method, the matching degree between the self-management label and the strategy label of each intervention strategy in the intervention strategy set is calculated, so that a plurality of matching degree values are obtained, and the intervention strategy corresponding to the maximum value in the plurality of matching degree values is determined as the target intervention strategy.
In some possible embodiments, the target intervention strategy includes a medication alert mode and a medication alert frequency. And the medication behavior intervention platform sends medication reminding information to the target patient in a medication reminding mode according to the medication reminding frequency in a preset time period, wherein the medication reminding mode comprises a text prompt or a voice prompt. Alternatively, the text prompt may include a short message prompt, a mail prompt, an APP prompt, etc., and the voice prompt may include a telephone prompt.
For example, the medication intervention platform sends a short message in the form of a short message to the hypertensive patient a at nine morning and seven evening points of each day, including a reminder of medication and aspects of hypertension complications.
According to the application, the medication behavior intervention platform can obtain the medication behavior probability sequence of the target patient in the n+1th time period through the LSTM according to the behavior data of the target patient in the n time periods, further determine the medication behavior of the target patient in the n+1th time period, determine the target intervention strategy according to the non-medication behavior data of the target patient in the n time periods and the medication behavior of the n+1th time period, and send medication reminding information to the target patient based on the target intervention strategy, so that the intervention is more timely, and the medication compliance of the patient is improved.
Fig. 3 is another flow chart of the intervention method of the medication behavior of the patient according to the present application. As shown in fig. 3, the method provided by the present application may include the following steps:
s201, acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-drug behavior data, and the preset time period comprises n time periods.
S202, learning behavior data through a long-short-term memory network LSTM to obtain a medication behavior probability sequence in an n+1th time period.
S203, determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence.
In some possible embodiments, the implementation manners performed in the steps S201 to S203 may be referred to the implementation manners provided in the steps S101 to S103 in the embodiment shown in fig. 2, which are not described herein.
S204, determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, wherein the target intervention strategy comprises a medication reminding mode and a medication reminding frequency.
In some possible embodiments, prior to performing step S204, the medication behavior intervention platform may construct a knowledge graph of a disease from clinical medical knowledge and behavior data of the patient of the disease, the knowledge graph comprising a plurality of intervention strategies for the patient of the disease, each intervention strategy comprising at least one combination signature of the patient, wherein the combination signature may be represented by an entity-attribute form. The entities may include lifestyle, disease metrics, medication behavior types, etc., and the attributes of lifestyle entities may include smoking, drinking, exercise, etc. Here, the patient with hypertension is exemplified as the condition measurement index, the condition measurement index may be a blood pressure level change, the attribute of the blood pressure level change includes a systolic lower limit value, a systolic upper limit value, a diastolic lower limit value and a diastolic upper limit value, and the attribute of the medication behavior type may include intentional medication stop, medication forgetting 1 time, medication forgetting 2-3 times and medication forgetting more than 3 times. Here, the attributes of the entity may be expressed in the form of scores, for example, attributes of the medication behavior type: the medicine is stopped intentionally, the medicine is forgotten to be taken 1 time, the medicine is forgotten to be taken 2-3 times and the medicine is forgotten to be taken more than 3 times, and the scores of 0,3, 2 and 1 can be respectively used for representing. And then, traversing the combined label of each intervention strategy in the knowledge graph by the medication behavior intervention platform according to the non-medication behavior data and the medication behavior type of the target patient until the intervention strategy with the highest matching degree with the non-medication behavior data and the medication behavior type of the target patient is found, and determining the intervention strategy as the target intervention strategy.
S205, sending medication reminding information to a target patient in a medication reminding mode according to the medication reminding frequency in a preset time period.
The preset time period and the medication reminding frequency can be determined by the time and the taking frequency of the medicine taken by the patient, and in addition, the medication reminding information comprises information for reminding the patient of taking the medicine, non-medication behavior data of the target patient and the patient teaching content provided by the medication behavior type.
For example, if the target patient takes the medication three times a day before meals, the non-medication performance data includes smoking, and the type of medication performance in the next week is intentional withdrawal, the medication performance intervention platform alerts the target patient to take the medication in the form of a phone call at eight morning, ten noon, and six evening, respectively, and teaches the target patient of medication compliance.
According to the application, the medication behavior intervention platform can obtain the medication behavior probability sequence of the target patient in the n+1th time period through the LSTM according to the behavior data of the target patient in the n time periods, further determine the medication behavior of the target patient in the n+1th time period, and determine the target intervention strategy according to the non-medication behavior data of the target patient in the n time periods and the medication behavior of the n+1th time period. The target intervention strategy comprises a medication reminding frequency and a medication reminding mode, and in a preset time period, medication reminding information is sent to a target patient in the medication reminding mode according to the medication reminding frequency, so that the intervention is more timely, and the medication compliance of the patient is improved. In addition, the target intervention strategies are determined according to the behavior data of the patient, and the medication reminding information in the target intervention strategies comprises the suffering teaching content, so that personalized intervention on the medication behavior of the patient is realized, the pressure of doctors is reduced, and the quality of chronic disease management is improved.
Based on the description of the method embodiment, the application also provides a patient medication behavior intervention device, which can be the medication behavior intervention platform in the method embodiment. Fig. 4 is a schematic structural diagram of a device for intervention in medication behavior of a patient according to the present application. As shown in fig. 4, the patient medication intervention device 4 may comprise: a behavior data acquisition module 41, a probability sequence learning module 42, a behavior type determination module 43, and a determination transmission module 44.
The behavior data acquisition module 41 is configured to acquire behavior data of a target patient within a preset duration, where the behavior data includes non-medication behavior data, and the preset duration includes n time periods, where n is a natural number;
the probability sequence learning module 42 is configured to learn the behavior data through a long short-time memory network LSTM, so as to obtain a medication behavior probability sequence in the n+1th time period;
A behavior type determining module 43, configured to determine a medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence;
The determining and sending module 44 is configured to determine a target intervention policy according to the medication behavior type and the non-medication behavior data, and send medication reminding information to the target patient based on the target intervention policy.
In some possible embodiments, the target intervention strategy includes a medication reminding mode and a medication reminding frequency;
The determining and sending module 44 is configured to send the medication reminding information to the target patient in the medication reminding manner according to the medication reminding frequency in a preset time period;
the medication reminding mode comprises a text prompt or a voice prompt.
In some possible embodiments, the probability sequence learning module 42 is configured to:
Sequencing the behavior data in the preset duration according to a preset sequence to obtain a sequenced behavior data sequence, and inputting the behavior data sequence into the LSTM;
And learning the medication behavior type of the next time period corresponding to the behavior data of each time period in the n time periods by using the LSTM as a learning task according to the multi-classification problem of the multiple medication behavior types.
In some possible embodiments, one medication behavior probability in the medication behavior probability sequence corresponds to one medication behavior type;
the behavior type determining module 43 is configured to determine a medication behavior type corresponding to a maximum medication behavior probability in the medication behavior probability sequence as the medication behavior type of the target patient in the n+1th time period.
In some possible embodiments, the determining sending module 44 includes:
A label generating unit 441 configured to generate a self-management label of the target patient based on the medication behavior type and the non-medication behavior data;
A matching degree calculating unit 442, configured to calculate a matching degree of the self-management tag and a policy tag of each intervention policy in an intervention policy set to obtain a plurality of matching degree values, where the preset intervention policy set includes a plurality of intervention policies, and one intervention policy carries at least one policy tag;
the policy determining unit 443 is configured to determine an intervention policy corresponding to a maximum value of the plurality of matching degree values as the target intervention policy.
In some possible embodiments, the behavior data acquisition module 41 includes:
A sending prompt unit 411, configured to send a behavioral data acquisition prompt to a target patient according to a preset frequency, so as to prompt the target patient to feed back behavioral data according to a target data acquisition form, where the target data acquisition form includes web page link acquisition or two-dimensional code acquisition;
And the receiving data unit 412 is configured to receive the behavior data fed back by the target patient as the behavior data of the target patient within a preset duration.
It will be appreciated that the patient medication intervention device 4 is configured to implement the steps performed by the medication intervention platform of the embodiment of fig. 2 and 3. With respect to the specific implementation of the functional blocks and the corresponding advantageous effects included in the patient medication behavior intervention device 4 of fig. 4, reference may be made to the foregoing specific description of the embodiments of fig. 2 and 3, which are not repeated here.
The patient medication intervention device 4 of the embodiment shown in fig. 4 described above may be implemented as a server 500 shown in fig. 5. Fig. 5 is a schematic structural diagram of a server according to the present application. As shown in fig. 5, the server 500 may include: one or more processors 501, memory 502, and a transceiver 503. The processor 501, the memory 502, and the transceiver 503 are connected via a bus 504. Wherein the transceiver 503 is configured to receive or transmit data, and the memory 502 is configured to store a computer program, the computer program including program instructions; the processor 501 is configured to execute program instructions stored in the memory 502 and perform the following operations:
acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-medication behavior data, the preset time period comprises n time periods, and n is a natural number;
Learning the behavior data through a long-short-term memory network LSTM to obtain a medication behavior probability sequence in the (n+1) th time period;
Determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence;
and determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to the target patient based on the target intervention strategy.
In some possible embodiments, the processor 501 learns the behavior data through a long-short-time memory network LSTM, and specifically performs the following operations:
Sequencing the behavior data in the preset duration according to a preset sequence to obtain a sequenced behavior data sequence, and inputting the behavior data sequence into the LSTM;
And learning the medication behavior type of the next time period corresponding to the behavior data of each time period in the n time periods by using the LSTM as a learning task according to the multi-classification problem of the multiple medication behavior types.
In some possible embodiments, one medication behavior probability in the medication behavior probability sequence corresponds to one medication behavior type;
The processor 501 determines the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence, and specifically performs the following operations:
And determining the medication behavior type corresponding to the maximum medication behavior probability in the medication behavior probability sequence as the medication behavior type of the target patient in the n+1 time period.
In some possible embodiments, the processor 501 determines a target intervention policy according to the medication behavior type and the non-medication behavior data, and specifically performs the following operations:
Generating a self-management label of the target patient according to the medication behavior type and the non-medication behavior data;
Calculating the matching degree of the self-management label and the strategy label of each intervention strategy in the intervention strategy set to obtain a plurality of matching degree values, wherein the preset intervention strategy set comprises a plurality of intervention strategies, and one intervention strategy carries at least one strategy label;
and determining an intervention strategy corresponding to the maximum value in the plurality of matching degree values as the target intervention strategy.
In some possible embodiments, the target intervention strategy includes a medication reminding mode and a medication reminding frequency;
the processor 501 sends medication reminding information to the target patient based on the target intervention strategy, specifically performs the following operations:
In a preset time period, sending the medication reminding information to the target patient in the medication reminding mode according to the medication reminding frequency;
the medication reminding mode comprises a text prompt or a voice prompt.
In some possible embodiments, the processor 501 acquires behavior data of the target patient within a preset time period, and specifically performs the following operations:
Sending a behavior data acquisition prompt to a target patient according to a preset frequency so as to prompt the target patient to feed back behavior data according to a target data acquisition form, wherein the target data acquisition form comprises web page link acquisition or two-dimensional code acquisition;
And receiving the behavior data fed back by the target patient to serve as the behavior data of the target patient in a preset time period.
Furthermore, it should be noted here that: the present application further provides a computer readable storage medium, in which a computer program executed by the aforementioned patient behavior intervention device 4 is stored, and the computer program includes program instructions, when executed by the processor, can execute the description of the patient behavior intervention method in the corresponding embodiment of fig. 2 or fig. 3, and therefore, the description will not be repeated here. In addition, the description of the beneficial effects of the same method is omitted. For technical details not disclosed in the embodiments of the computer-readable storage medium according to the present application, please refer to the description of the method embodiments of the present application. As an example, program instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network, where the multiple computing devices distributed across multiple sites and interconnected by a communication network may constitute a blockchain system.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of computer programs, which may be stored on a computer-readable storage medium, and which, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random-access Memory (Random Access Memory, RAM), or the like.
The methods and related devices provided by the present application are described with reference to the method flowcharts and/or structure diagrams provided by the present application, and each flow and/or block of the method flowcharts and/or structure diagrams, and combinations of flows and/or blocks in the flow charts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or structures.
The foregoing disclosure is illustrative of the present application and is not to be construed as limiting the scope of the application, which is defined by the appended claims.
Claims (8)
1. A method of behavioral intervention in a patient comprising:
acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprises non-medication behavior data, the preset time period comprises n time periods, n is a natural number, the behavior data also comprises medication behavior data, the medication behavior data comprises medicine data, medicine taking data and medicine stopping data, the medicine taking data comprises 1 time of forgetting to take medicine, 2-3 times of forgetting to take medicine and more than 3 times of forgetting to take medicine, and the medicine stopping data comprises intentional medicine stopping;
The method comprises the steps of learning the medication behavior type of the next time period corresponding to the behavior data of each time period in n time periods by taking a multi-classification problem of multiple medication behavior types as a learning task through a long-short-term memory network LSTM so as to obtain a medication behavior probability sequence of the n+1th time period, wherein the medication behavior types comprise an intentional medicine stopping type, a medicine forgetting type 1, a medicine forgetting type 2-3 times and a medicine forgetting type more than 3 times, and the method comprises the following steps: the method comprises the steps of sequencing behavior data of 4 weeks according to time sequences of a first week, a second week, a third week and a fourth week to obtain a behavior data sequence, inputting the behavior data sequence into an LSTM, learning a second week of the behavior data of the 4 weeks, a third week of the behavior data of the second week, a fourth week of the behavior data of the third week and a fourth week of the behavior data of the third week by taking multi-classification problems of four drug behavior types including intentional drug withdrawal, drug withdrawal forgetting 1 time, drug withdrawal forgetting 2-3 times and drug withdrawal forgetting more than 3 times as learning tasks through the LSTM, and obtaining a fifth week of the behavior probability sequence;
Determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence, wherein one medication behavior probability in the medication behavior probability sequence corresponds to one medication behavior type;
Determining a target intervention strategy according to the medication behavior type and the non-medication behavior data, and sending medication reminding information to the target patient based on the target intervention strategy, wherein the method comprises the following steps: generating a self-management tag of the target patient according to the medication behavior type, the non-medication behavior data and the physical symptom data, including: if the medication behavior type of the target patient is intentional withdrawal, the non-medication behavior data comprise smoking-free behavior and drinking behavior, and the physical symptom data are large in blood pressure level change range, the self-management label generated according to the data is intentional withdrawal, drinking and large in blood pressure level change range; calculating the matching degree of the self-management label and the strategy label of each intervention strategy in the intervention strategy set to obtain a plurality of matching degree values, wherein the matching degree values comprise: if the self-management label of the target patient is A, B, C and the policy labels of the ith intervention policy are a, b and c, the matching degree calculation formula between the self-management label and the policy label of the ith intervention policy is the sum of the matching degrees between the self-management label A, B, C and the policy labels a, b and c of the ith intervention policy respectively, the intervention policy set comprises a plurality of intervention policies, and one intervention policy carries at least one policy label; and determining an intervention strategy corresponding to the maximum value in the plurality of matching degree values as the target intervention strategy, and sending medication reminding information to the target patient based on the target intervention strategy.
2. The method of claim 1, wherein said determining the type of medication behavior of the target patient during the n+1 time period from the sequence of medication behavior probabilities comprises:
And determining the medication behavior type corresponding to the maximum medication behavior probability in the medication behavior probability sequence as the medication behavior type of the target patient in the n+1th time period.
3. The method of claim 1, wherein the target intervention strategy comprises a medication reminding mode and a medication reminding frequency;
The sending medication reminding information to the target patient based on the target intervention strategy comprises the following steps:
In a preset time period, sending the medication reminding information to the target patient in the medication reminding mode according to the medication reminding frequency;
The medication reminding mode comprises a text prompt or a voice prompt.
4. A method according to any one of claims 1-3, wherein the obtaining behavioral data of the subject patient over a predetermined period of time comprises:
Sending a behavior data acquisition prompt to a target patient according to a preset frequency to prompt the target patient to feed back behavior data according to a target data acquisition form, wherein the target data acquisition form comprises web page link acquisition or two-dimensional code acquisition;
And receiving behavior data fed back by the target patient to serve as the behavior data of the target patient in a preset duration.
5. A patient behavioral intervention device for performing the method of any of claims 1-4, comprising:
the behavior data acquisition module is used for acquiring behavior data of a target patient in a preset time period, wherein the behavior data comprise non-medication behavior data, the preset time period comprises n time periods, and n is a natural number;
the probability sequence learning module is used for learning the behavior data through a long short-time memory network LSTM so as to obtain a medication behavior probability sequence in the (n+1) th time period;
The behavior type determining module is used for determining the medication behavior type of the target patient in the n+1th time period according to the medication behavior probability sequence;
and the determining and sending module is used for determining a target intervention strategy according to the medication behavior type and the non-medication behavior data and sending medication reminding information to the target patient based on the target intervention strategy.
6. The device of claim 5, wherein the target intervention strategy comprises a medication reminding mode and a medication reminding frequency;
The determining and sending module is used for sending the medication reminding information to the target patient in the medication reminding mode according to the medication reminding frequency in a preset time period;
The medication reminding mode comprises a text prompt or a voice prompt.
7. A server comprising a processor, a memory and a transceiver, the processor, the memory and the transceiver being interconnected, wherein the transceiver is adapted to receive or transmit data, the memory is adapted to store program code, and the processor is adapted to invoke the program code to perform the method of intervention in medication behavior of a patient according to any of claims 1-4.
8. A computer readable storage medium, characterized in that it stores a computer program that is executed by a processor to implement the patient medication behavior intervention method of any of claims 1-4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940492.8A CN112037932B (en) | 2020-09-09 | 2020-09-09 | Patient medication behavior intervention method and device, server and storage medium |
| PCT/CN2020/124261 WO2021151329A1 (en) | 2020-09-09 | 2020-10-28 | Patient medication behavior intervention method and apparatus, and server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940492.8A CN112037932B (en) | 2020-09-09 | 2020-09-09 | Patient medication behavior intervention method and device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112037932A CN112037932A (en) | 2020-12-04 |
| CN112037932B true CN112037932B (en) | 2024-10-18 |
Family
ID=73585117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010940492.8A Active CN112037932B (en) | 2020-09-09 | 2020-09-09 | Patient medication behavior intervention method and device, server and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112037932B (en) |
| WO (1) | WO2021151329A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927812B (en) * | 2021-03-30 | 2024-03-19 | 平安科技（深圳）有限公司 | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium |
| CN113658658A (en) * | 2021-08-18 | 2021-11-16 | 童心堂健康科技(北京)有限公司 | Medication strategy determination method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391941A (en) * | 2017-07-26 | 2017-11-24 | 上海科瓴医疗科技有限公司 | A kind of method and system for improving compliance |
| CN108597609A (en) * | 2018-05-04 | 2018-09-28 | 华东师范大学 | A kind of doctor based on LSTM networks is foster to combine health monitor method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019022779A1 (en) * | 2017-07-28 | 2019-01-31 | Google Llc | System and method for predicting and summarizing medical events from electronic health records |
| CN109360625B (en) * | 2018-11-12 | 2021-11-23 | 四川骏逸富顿科技有限公司 | Prediction system and prediction method for Internet medium-short term medication consultation business volume |
| CN110752002B (en) * | 2019-10-17 | 2022-07-05 | 清华大学 | Medicine dosage prediction device |
| CN110812241A (en) * | 2019-10-18 | 2020-02-21 | 平安科技（深圳）有限公司 | Medication reminding method based on time sequence clustering and related equipment |
-
2020
- 2020-09-09 CN CN202010940492.8A patent/CN112037932B/en active Active
- 2020-10-28 WO PCT/CN2020/124261 patent/WO2021151329A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391941A (en) * | 2017-07-26 | 2017-11-24 | 上海科瓴医疗科技有限公司 | A kind of method and system for improving compliance |
| CN108597609A (en) * | 2018-05-04 | 2018-09-28 | 华东师范大学 | A kind of doctor based on LSTM networks is foster to combine health monitor method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021151329A1 (en) | 2021-08-05 |
| CN112037932A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Steimle et al. | Multi-model Markov decision processes | |
| US11862339B2 (en) | Model optimization and data analysis using machine learning techniques | |
| US11165723B2 (en) | Methods and systems for a bimodal auto-response mechanism for messaging applications | |
| US10332631B2 (en) | Integrated medical platform | |
| US11604568B2 (en) | Intelligent user interface and application rendering | |
| CN112037932B (en) | Patient medication behavior intervention method and device, server and storage medium | |
| CN113722371B (en) | Medicine recommendation method, device, equipment and storage medium based on decision tree | |
| WO2016040359A1 (en) | Structuring multi-sourced medical information into a collaborative health record | |
| CN111933302A (en) | Medicine recommendation method and device, computer equipment and storage medium | |
| CN109255721A (en) | Insurance recommended method, equipment, server and readable medium based on Cost Forecast | |
| CN109584086B (en) | Method for predicting hospitalization rationality based on prediction model and related products | |
| De Wit et al. | Understanding drivers of resistance toward implementation of web-based self-management tools in routine cancer care among oncology nurses: cross-sectional survey study | |
| CN113707262B (en) | Medicine use recommendation method, device, computer equipment and storage medium | |
| CN109544372B (en) | Artificial intelligence-based outpatient chronic disease qualification monitoring method and related device | |
| Pierotti | What is PDGM? | |
| CN113360941A (en) | Medical data processing method and device based on digital twins and computer equipment | |
| US20230315989A1 (en) | Readmission model based on social determinants of health | |
| CN113724810B (en) | Data processing method, device, equipment and readable storage medium | |
| CN112016979B (en) | User grouping method, apparatus, device and computer readable storage medium | |
| US11862034B1 (en) | Variable content customization for coaching service | |
| CN113076486A (en) | Medicine information pushing method and device, computer equipment and storage medium | |
| Stark et al. | Building Habits in the Digital Age: Incorporating Psychological Needs and Knowledge from Practitioners to Inform the Design of Digital Therapeutics | |
| Anderson et al. | Nursing opinion leadership: a preliminary model derived from philosophic theories of rational belief | |
| CN118737369B (en) | Personalized medication recommendation method, device and storage medium based on multitask learning | |
| CN114004707B (en) | Data processing method, system, device and storage medium for health insurance business |
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 |