CN112927812B - Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium - Google Patents
Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112927812B CN112927812B CN202110343327.9A CN202110343327A CN112927812B CN 112927812 B CN112927812 B CN 112927812B CN 202110343327 A CN202110343327 A CN 202110343327A CN 112927812 B CN112927812 B CN 112927812B
- Authority
- CN
- China
- Prior art keywords
- compliance
- patient
- target
- treatment
- 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
- 238000011269 treatment regimen Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000001684 chronic effect Effects 0.000 claims abstract description 147
- 238000011282 treatment Methods 0.000 claims abstract description 98
- 238000004458 analytical method Methods 0.000 claims abstract description 94
- 238000012549 training Methods 0.000 claims abstract description 53
- 208000017667 Chronic Disease Diseases 0.000 claims description 79
- 238000011161 development Methods 0.000 claims description 27
- 238000004140 cleaning Methods 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 20
- 230000004913 activation Effects 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 12
- 201000010099 disease Diseases 0.000 claims description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 230000003213 activating effect Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 claims description 5
- 230000001225 therapeutic effect Effects 0.000 claims description 5
- 239000003814 drug Substances 0.000 description 28
- 238000007726 management method Methods 0.000 description 18
- 230000037213 diet Effects 0.000 description 10
- 235000005911 diet Nutrition 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 9
- 238000012360 testing method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 229940079593 drug Drugs 0.000 description 6
- KDCGOANMDULRCW-UHFFFAOYSA-N 7H-purine Chemical compound N1=CNC2=NC=NC2=C1 KDCGOANMDULRCW-UHFFFAOYSA-N 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 235000013372 meat Nutrition 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 206010020772 Hypertension Diseases 0.000 description 2
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 description 2
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 231100000749 chronicity Toxicity 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 235000006694 eating habits Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 229940116269 uric acid Drugs 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Bioethics (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of intelligent decision making, and discloses a dynamic intervention method of a treatment strategy, which comprises the following steps: training the medical advice compliance analysis model to be trained by using the patient treatment data training set to obtain the medical advice compliance analysis model; acquiring treatment information including medical advice of a target chronic patient and daily work and rest data of the target chronic patient in a treated period; analyzing and determining the compliance level of the behavior of the target chronic patient to the medical advice in the treated period by using daily work and rest data, medical advice and medical advice compliance analysis models; judging whether to adjust the treatment strategy of the target chronic patient after the treatment period according to the compliance grade; and determining a target treatment strategy of the target chronic patient after the treatment period according to the judgment result. The invention also provides a dynamic intervention device, equipment and a computer readable storage medium of the treatment strategy. The invention can accurately and efficiently detect compliance of an executor with a planned plan.
Description
Technical Field
The present invention relates to the field of intelligent decision making technologies, and in particular, to a method and apparatus for dynamic intervention of a treatment strategy, an electronic device, and a computer readable storage medium.
Background
Along with the development of society, through planning work, study life, medical treatment diagnosis and treatment, be favorable to increasing work efficiency, reach preset study or medical treatment effect, wherein the compliance of executor plays important role to the promotion of work or study, and the compliance of executor needs people to observe and evaluate in fields such as medical at present, and is huge consuming time, and efficiency is lower and the evaluation result of evaluation personnel has subjectivity, can't the compliance of scientific efficient judgement executor.
Disclosure of Invention
The invention provides a dynamic intervention method, a dynamic intervention device, electronic equipment and a computer readable storage medium of a treatment strategy, and aims to accurately and efficiently detect compliance of an executor to a planned plan.
To achieve the above object, the present invention provides a method for dynamic intervention of a therapeutic strategy, the method comprising:
training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
Obtaining treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and a doctor's advice of the treated period;
acquiring daily work and rest data of the target chronic patient in the treated period;
determining a level of compliance of the target chronically ill patient's behavior to the order over the treated period using the daily work and rest data, the order, and the order compliance analysis model analysis;
judging whether to intervene in a pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance grade;
and when the judgment result is that the intervention is not needed, continuing to execute the treatment strategy of the target chronic patient after the treated period, and when the judgment result is that the intervention is needed, performing the intervention on the treatment strategy of the target chronic patient after the treated period according to the preset scene setting rule.
Optionally, the analyzing, using the daily work and rest data, the orders, and the order compliance analysis model, to determine a compliance level of the target chronic patient's behavior to the orders over the treated period includes:
Performing feature extraction and comparison operation on the daily work and rest data and the medical advice by using the medical advice compliance analysis model to obtain compliance scores;
carrying out normalization operation on the compliance score by utilizing a pre-constructed normalization function to obtain a compliance value of the target chronic patient;
when the compliance value is less than a first preset threshold, determining that the compliance level of the target chronic patient is a first level;
and when the compliance value is larger than a second preset threshold value, determining that the compliance level of the target chronic disease patient is a second level, wherein the second preset threshold value is larger than or equal to the first preset threshold value.
Optionally, the determining whether to intervene in the pre-constructed treatment strategy of the target chronically ill patient after the treated period according to the compliance level includes:
determining, when the compliance level is a first level, a treatment strategy that does not interfere with the target chronically ill patient after the treated period;
when the compliance level is a second level, determining a treatment strategy for intervening in the target chronically ill patient after the treated period, the first level being higher than the second level.
Optionally, the
The intervention of the treatment strategy of the target chronic patient after the treated period according to the pre-constructed scene setting rules comprises the following steps:
according to a pre-constructed scene setting rule, when the compliance level of the target chronic disease patient is the first level, automatically intervening the target chronic disease patient;
when the compliance grade of the target chronic patient is the second grade, performing manual intervention on the target chronic patient;
semi-automatic intervention is performed on the target chronic patient when the level of compliance of the target chronic patient is not either of the first level and the second level.
Optionally, the automatically intervening on the target chronic patient includes:
and obtaining a compliance report and a physical condition development condition of the target chronic patient in the treated period, and automatically generating and feeding back the compliance report and the physical condition development condition to the target chronic patient periodically.
Optionally, the doctor's advice compliance analysis model to be trained is a convolutional neural network model constructed based on a Transform model framework.
Optionally, the to-be-trained doctor's advice compliance analysis model includes a feature extraction network, a multi-layer linear activation layer and a convolutional neural network, training the to-be-trained doctor's advice compliance analysis model by using a pre-constructed patient treatment data training set, to obtain a doctor's advice compliance analysis model, including:
step I, acquiring a patient treatment data training set input by a user, cleaning the patient treatment data training set to obtain cleaning data, importing the cleaning data into the medical advice compliance analysis model to be trained, and performing feature extraction on the cleaning data by utilizing the feature extraction network to obtain a feature sequence set;
step II, activating the characteristic sequence set by utilizing the multi-layer linear activation layer to obtain a prediction evaluation result set;
step III, calculating an error value of a pre-constructed compliance label corresponding to the prediction result set and the patient treatment data training set, and judging whether the error value is larger than a preset error threshold value or not;
step IV: if the error value is larger than the preset error threshold value, adjusting model parameters of the medical advice compliance analysis model to be trained, and returning to the step II;
Step V: and if the error value is not greater than the preset error threshold value, obtaining the doctor's advice compliance analysis model.
In order to solve the above-mentioned problems, the present invention also provides a dynamic intervention device of a therapeutic strategy, the device comprising:
the model construction module is used for training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
the information acquisition module is used for acquiring treatment information of a target chronic disease patient by utilizing a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and medical orders of the treated period, and acquiring daily work and rest data of the target chronic disease patient in the treated period;
a compliance detection module for analyzing and determining a compliance level of the target chronic patient's behavior to the order within the treated period using the daily work and rest data, the order, and the order compliance analysis model;
and the treatment strategy intervention module is used for judging whether to intervene in the pre-built treatment strategy of the target chronic patient after the treated period according to the compliance grade, continuously executing the treatment strategy of the target chronic patient after the treated period when the judgment result is that no intervention is needed, and intervening the treatment strategy of the target chronic patient after the treated period according to the pre-built scene setting rule when the judgment result is that intervention is needed.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform a dynamic intervention method of the treatment strategy.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium including a storage data area storing created data and a storage program area storing a computer program; wherein the computer program when executed by the processor implements a dynamic intervention method of the treatment strategy.
According to the embodiment of the invention, the doctor's advice and daily work and rest data preset by the target chronic patient are analyzed through the doctor's advice compliance analysis model, the compliance level of the chronic patient to the doctor's advice can be rapidly and accurately judged, whether the treatment strategy after the treated period is adjusted is judged through different compliance levels, and then the treatment strategy after the treated period is determined. In the dynamic intervention process of the treatment strategy, the acquired treatment strategy can be adjusted in real time according to the treatment condition of the chronic patient in the previous stage, and the treatment strategy is changed according to the actual daily work and rest condition of the chronic patient. Therefore, the embodiment of the invention can accurately and efficiently detect the compliance of the patient, thereby increasing the accuracy of formulating the treatment strategy.
Drawings
FIG. 1 is a flow chart of a method for dynamic intervention of a treatment strategy according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a detailed implementation of one of the steps in the dynamic intervention method of the treatment strategy according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating another step in the dynamic intervention method of the treatment strategy according to an embodiment of the present invention.
FIG. 4 is a block diagram of a dynamic intervention device of a treatment strategy according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an internal structure of an electronic device for implementing a dynamic intervention method of a treatment strategy according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a dynamic intervention method of a treatment strategy. The execution subject of the dynamic intervention method of the treatment strategy includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the dynamic intervention method of the treatment strategy may be performed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flow chart of a method for dynamic intervention of a treatment strategy according to an embodiment of the invention is shown. In this embodiment, the method for dynamic intervention of a therapeutic strategy includes:
s1, training an order compliance analysis model to be trained by utilizing a pre-constructed patient treatment data training set to obtain the order compliance analysis model.
The patient treatment data in the embodiment of the invention comprises: data such as daily eating habits, work and rest, work content intensity, medicine intake time and medicine amount of chronic patients.
In the embodiment of the invention, the construction principle of the doctor's advice compliance analysis model is as follows: comparing the patient treatment data training set with a pre-constructed medical plan, and obtaining the compliance of the chronic patient to the medical plan according to the degree of compositing the various data in the patient treatment data training set to the medical plan.
The patient treatment data training set is a set of patient treatment data of different patients and stages and is used for training a pre-constructed doctor's advice compliance analysis model to be trained. According to the embodiment of the invention, the accuracy of the doctor's advice compliance analysis model can be increased according to the diversity of data in the patient treatment data training set.
Optionally, the doctor's advice compliance analysis model to be trained is a convolutional neural network model constructed based on a Transform model framework.
In detail, in the embodiment of the present invention, the to-be-trained physician order compliance analysis model includes a feature extraction network, a multi-layer linear activation layer and a convolutional neural network, and the training is performed on the to-be-trained physician order compliance analysis model by using a pre-constructed patient treatment data training set to obtain a physician order compliance analysis model, including:
and step I, acquiring a patient treatment data training set input by a user, cleaning the patient treatment data training set to obtain cleaning data, importing the cleaning data into the medical advice compliance analysis model to be trained, and performing feature extraction on the cleaning data by utilizing the feature extraction network to obtain a feature sequence set.
The cleaning operation is to delete the private data and the repeated data in the patient treatment data training set to obtain clean data, and then quantize the clean data and remove null values to obtain the cleaning data, which is beneficial to increasing the training process of the doctor's advice compliance analysis model to be trained.
The operation process of the embodiment of the invention can be operated through a specific function package in the Python language tool.
And calculating the information such as the medicine intake ratio, the degree of compliance of diet with medical advice and the like according to the patient treatment data. According to the embodiment of the invention, the cleaning data are imported into the medical advice compliance analysis model to be trained, and the cleaning data are subjected to feature extraction by utilizing a feature extraction network in the medical advice compliance analysis model to be trained, so that the medicine intake ratio is obtained: 120% of medicine taking average interval: 5h, the diet accords with the doctor's advice degree: 50% … …).
And II, performing activation operation on the characteristic sequence set by utilizing the multi-layer linear activation layer to obtain a prediction result set.
According to the embodiment of the invention, the cleaning data are imported into the doctor's advice compliance analysis model to be trained, and the multi-layer linear activation layer is utilized, wherein the multi-layer linear activation layer comprises a judgment neural network of which each medicine intake ratio, medicine taking average interval, diet accord with doctor's advice degree and other conditions, and the characteristic sequence set can be comprehensively judged by activating the judgment neural network, so that a prediction evaluation result set of compliance level of the chronic disease patient is obtained.
And III, calculating an error value of a pre-constructed compliance label corresponding to the prediction evaluation result set and the patient treatment data training set, and judging whether the error value is larger than a preset error threshold value.
Further, in an embodiment of the present invention, the calculating the error value of the pre-constructed compliance label corresponding to the predicted evaluation result set and the patient treatment data training set includes:
calculating the error value according to the preset index weighting strategy pair, wherein the function of the error value calculation operation is as follows:
F＝0.2*FRR+0.8*FAR
FRR＝FN/(TP+FN)*100％
FAR＝FP/(TN+FP)*100％
wherein F is an error value, FRR means probability of error of second level as first level, FAR means probability of error of first level as second level, TP is test result compliance as first level, and the compliance label is first level, FP is test result compliance as first level, and the compliance label is second level, FN is test result compliance as second level, and the compliance label is second level, TN is test result compliance as second level, and the compliance label is first level.
Step IV: and if the error value is larger than the preset error threshold value, adjusting the model parameters of the medical advice compliance analysis model to be trained, and returning to the step II.
The obtained error value is compared with a preset threshold, wherein the error threshold can be 0.15, and when the error value is larger than the error threshold, the disqualification of the compliance analysis model to be trained is evaluated, the step II is returned, and the compliance analysis model to be trained is trained again.
Step V: and if the error value is not greater than the preset error threshold value, obtaining the doctor's advice compliance analysis model.
And when the error value is not greater than the error threshold value, evaluating that the training process of the medical advice compliance analysis model to be trained is qualified, and ending the training process to obtain the medical advice compliance analysis model.
S2, acquiring treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and an order of the treated period.
The chronic disease management system is a model constructed according to the existing medical information and the treatment schemes and effects of a plurality of patients, and can provide a long-term medical plan for the chronic disease patients by utilizing the physical conditions of the patients in each stage.
In the embodiment of the invention, the treatment information is a treatment strategy and corresponding notice which are preset by a medical system or a doctor for a chronic patient and comprise each continuous treatment period. For example, taking medicines regularly, avoiding meat fishy smell, reducing oil salt, drinking more water and the like. When the treatment of one treatment period is finished, the next treatment period is started.
S3, acquiring daily work and rest data of the target chronic patient in the treated period.
In the embodiment of the invention, the daily work and rest data mainly comprises the medicine taking condition of the target chronic patient and the daily condition corresponding to the notice. For example, the notes are meat fishy smell, greasy smell, food with high purine smell, taking medicines several times a day, staggering taking medicines and the like, the daily conditions are the conditions of the target chronic patients aiming at the notes, specifically, the taking conditions can be obtained by acquiring the taking time and the medicine quantity of each time of the target chronic patients, and the daily work and rest conditions of the target chronic patients can be obtained by the conditions of the diet, the working force, the sleeping frequency duration and the like of each time of the target chronic patients.
S4, analyzing and determining the compliance level of the behavior of the target chronic disease patient to the medical advice in the treated period by using the daily work and rest data, the medical advice and the medical advice compliance analysis model.
According to the embodiment of the invention, the daily work and rest data of the patient are obtained, and the daily work and rest data are sent to the doctor's advice compliance analysis model for compliance grade assessment, so that the result of compliance grade can be obtained.
In detail, in an embodiment of the present invention, the analyzing, using the daily work and rest data, the medical orders, and the medical order compliance analysis model, to determine a compliance level of the behavior of the target chronic patient to the medical orders during the treated period includes:
performing feature extraction and comparison operation on the daily work and rest data and the medical advice by using the medical advice compliance analysis model to obtain compliance scores;
carrying out normalization operation on the compliance score by utilizing a pre-constructed normalization function to obtain a compliance value of the target chronic patient;
when the compliance value is less than a first preset threshold, determining that the compliance level of the target chronic patient is a first level;
and when the compliance value is larger than a second preset threshold value, determining that the compliance level of the target chronic disease patient is a second level, wherein the second preset threshold value is larger than or equal to the first preset threshold value.
In the embodiment of the invention, the daily work and rest data and the medical advice, which are input by a user and correspond to the target chronic patient in a treated period, are processed by using the medical advice compliance analysis model, and the daily work and rest data and the medical advice are compared to obtain a medicine intake ratio: 120% of medicine taking average interval ratio: 5h/4h, diet meets the doctor's advice degree: 50% … …, and the like, obtaining the compliance score as 850, and performing normalization operation on the compliance score to obtain the compliance value as 0.85, and judging the compliance grade of the target chronic disease patient as the second grade if the compliance value is larger than a preset second threshold value of 0.8.
Wherein the normalization function can convert the result of the compliance analysis model into a decimal of 0 to 1, namely the normalization value.
In detail, in the embodiment of the present invention, the intervention on the treatment strategy of the target chronic patient after the treated period according to the pre-constructed scene setting rule includes:
and step A, automatically intervening the target chronic patients when the compliance grade of the target chronic patients is the first grade according to the preset scene setting rule.
Further, as shown in fig. 3 below, in an embodiment of the present invention, the automatic intervention on the target chronic patient includes:
s41, acquiring a compliance report and a physical condition development condition of the target chronic patient in the treated period, and automatically generating and feeding back the compliance report and the physical condition development condition to the target chronic patient periodically.
In the embodiment of the invention, the physical health data of the target chronic patient is acquired in the treatment period, the compliance report is generated according to the compliance grade of the physical health data, and the physical condition development condition is judged.
B, when the compliance grade of the target chronic patient is the second grade, performing manual intervention on the target chronic patient;
and C, performing semiautomatic intervention on the target chronic patient when the compliance level of the target chronic patient is not any one of the first level and the second level.
Specifically, in the embodiment of the present invention, the scene setting rule is a pre-constructed compliance dividing table that adopts different auxiliary strategies according to the compliance of the target chronic patient. When the compliance of the target chronic patient is the first grade, the target chronic patient can be periodically reminded through intelligent prompt information; when the compliance of the target chronic patient is of the second level, manual intervention of a guardian is required, and the medical treatment plan of the target chronic patient is ensured to be orderly carried out; patient compliance is generally based on the selection of the target chronic patient, and intelligent or manual intervention may be performed on the target chronic patient when the patient compliance is between the first level and the second level.
The automatic intervention is to periodically send the compliance report and the physical condition development condition through a pre-constructed program to remind the target chronic patient, and the manual intervention is to send the compliance report and the physical condition development condition to a guardian of the target chronic patient to indirectly remind the target chronic patient. The semiautomatic intervention refers to the manual intervention and the automatic intervention as an arbitrarily selected intervention method.
S5, judging whether to intervene in a pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance grade.
In detail, as shown in fig. 2 below, in the embodiment of the present invention, the determining whether to intervene in the pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance level includes:
s51, when the compliance grade is a first grade, determining a treatment strategy of the target chronic patient after the treated period without intervention;
s52, when the compliance level is a second level, determining a treatment strategy for intervening in the target chronically ill patient after the treated period, the first level being higher than the second level.
In the embodiment of the invention, when the compliance grade is the first grade, the daily work and rest habit of the target chronic patient in the treated period is high in matching with the medical advice of the treated period, and the pre-constructed treatment strategy of the next treatment period is not adjusted at the moment.
When the compliance level is the second level, it indicates that the daily work and rest habits of the target chronically ill patient in the treated cycle are low in matching with the orders of the treated cycle, so that the completion of the treatment plan in the treated cycle is low, and then the treatment strategy after the treated cycle needs to be adjusted.
And S6, when the judgment result is that the intervention is not needed, continuing to execute the treatment strategy of the target chronic patient after the treated period, and when the judgment result is that the intervention is needed, setting rules according to a pre-constructed scene, and performing the intervention on the treatment strategy of the target chronic patient after the treated period.
In the embodiment of the present invention, if the determination result is not adjusted, a target treatment strategy of the target chronic patient after the treated period is obtained from the treatment information.
In the embodiment of the present invention, the scene setting rule is the rule method of automatic intervention, manual intervention, and automatic intervention, and if the judgment result is adjustment, real-time sign data of the target chronic disease patient at each time node in the treated period can be obtained to obtain a stage data set, the stage data set is processed by using a pre-built medical diagnosis system, and the disease development trend of the target chronic disease patient is analyzed to obtain the target treatment strategy.
Preferably, the real-time physical sign data is physical sign data of the chronically ill patient acquired at regular time by the chronicity system. For example, the real-time sign data includes: the patient physical index data detected by various medical examination devices is exemplified by hypertension patients, and includes data such as blood pressure, blood fat, uric acid, protein content and the like.
According to the embodiment of the invention, the stage data set is imported into a pre-constructed chronic disease management system at fixed time, and fluctuation of the implementation sign data in a preset time period is recorded through the chronic disease management system, so that a physical condition fluctuation map is obtained;
judging the disease development trend according to the physical condition fluctuation diagram, and obtaining a medical advice result of the next treatment period according to the disease development trend, namely a target treatment strategy of the target chronic patient after the treatment period.
Preferably, in the embodiment of the present invention, the chronic disease management system determines whether each index is within a preset normal interval and whether the disease development trend is within a preset range, so as to intelligently output a target treatment policy of the target chronic disease patient after the treatment period according to whether each index is abnormal and the disease development trend.
According to the embodiment of the invention, the doctor's advice and daily work and rest data preset by the target chronic patient are analyzed through the doctor's advice compliance analysis model, the compliance level of the chronic patient to the doctor's advice can be rapidly and accurately judged, whether the treatment strategy after the treated period is adjusted is judged through different compliance levels, and then the treatment strategy after the treated period is determined. In the dynamic intervention process of the treatment strategy, the acquired treatment strategy can be adjusted in real time according to the treatment condition of the chronic patient in the previous stage, and the treatment strategy is changed according to the actual daily work and rest condition of the chronic patient. Therefore, the embodiment of the invention can accurately and efficiently detect the compliance of the patient, thereby increasing the accuracy of formulating the treatment strategy.
As shown in fig. 4, a schematic block diagram of a dynamic intervention device of the treatment strategy of the present invention.
The dynamic intervention device 100 of the treatment strategy according to the invention may be installed in an electronic device. Depending on the implemented functionality, the dynamic intervention means of the treatment strategy may comprise a model building module 101, an information acquisition module 102, a compliance detection module 103, a treatment strategy intervention module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the model construction module 101 is configured to train the to-be-trained doctor's advice compliance analysis model by using the pre-constructed patient treatment data training set, so as to obtain the doctor's advice compliance analysis model.
The patient treatment data in the embodiment of the invention comprises: data such as daily eating habits, work and rest, work content intensity, medicine intake time and medicine amount of chronic patients.
In the embodiment of the invention, the construction principle of the doctor's advice compliance analysis model is as follows: comparing the patient treatment data training set with a pre-constructed medical plan, and obtaining the compliance of the chronic patient to the medical plan according to the degree of compositing the various data in the patient treatment data training set to the medical plan.
The patient treatment data training set is a set of patient treatment data of different patients and stages and is used for training a pre-constructed doctor's advice compliance analysis model to be trained. According to the embodiment of the invention, the accuracy of the doctor's advice compliance analysis model can be increased according to the diversity of data in the patient treatment data training set.
Optionally, the doctor's advice compliance analysis model to be trained is a convolutional neural network model constructed based on a Transform model framework.
In detail, in the embodiment of the present invention, the to-be-trained physician order compliance analysis model includes a feature extraction network, a multi-layer linear activation layer, and a convolutional neural network, the to-be-trained physician order compliance analysis model is trained by using a pre-constructed patient treatment data training set, so as to obtain a physician order compliance analysis model, and the model construction module 101 includes functions 1 to 5 for:
function 1, obtaining a patient treatment data training set input by a user, cleaning the patient treatment data training set to obtain cleaning data, importing the cleaning data into the medical advice compliance analysis model to be trained, and performing feature extraction on the cleaning data by utilizing the feature extraction network to obtain a feature sequence set.
The cleaning operation is to delete the private data and the repeated data in the patient treatment data training set to obtain clean data, and then quantize the clean data and remove null values to obtain the cleaning data, which is beneficial to increasing the training process of the medical advice compliance analysis model to be trained, wherein the operation process of the embodiment of the invention can be operated through a specific function package in a Python language tool.
And calculating the information such as the medicine intake ratio, the degree of compliance of diet with medical advice and the like according to the patient treatment data. According to the embodiment of the invention, the cleaning data are imported into the medical advice compliance analysis model to be trained, and the cleaning data are subjected to feature extraction by utilizing a feature extraction network in the medical advice compliance analysis model to be trained, so that the medicine intake ratio is obtained: 120% of medicine taking average interval: 5h, the diet accords with the doctor's advice degree: 50% … …).
And 2, activating the characteristic sequence set by utilizing the multi-layer linear activation layer to obtain a prediction result set.
According to the embodiment of the invention, the cleaning data are imported into the doctor's advice compliance analysis model to be trained, and the multi-layer linear activation layer is utilized, wherein the multi-layer linear activation layer comprises a judgment neural network of which each medicine intake ratio, medicine taking average interval, diet accord with doctor's advice degree and other conditions, and the characteristic sequence set can be comprehensively judged by activating the judgment neural network, so that a prediction evaluation result set of compliance level of the chronic disease patient is obtained.
And 3, calculating an error value of a pre-constructed compliance label corresponding to the prediction evaluation result set and the patient treatment data training set, and judging whether the error value is larger than a preset error threshold value.
Further, in an embodiment of the present invention, the calculating the error value of the pre-constructed compliance label corresponding to the predicted evaluation result set and the patient treatment data training set includes:
calculating the error value according to the preset index weighting strategy pair, wherein the function of the error value calculation operation is as follows:
F＝0.2*FRR+0.8*FAR
FRR＝FN/(TP+FN)*100％
FAR＝FP/(TN+FP)*100％
wherein F is an error value, FRR means probability of error of second level as first level, FAR means probability of error of first level as second level, TP is test result compliance as first level, and the compliance label is first level, FP is test result compliance as first level, and the compliance label is second level, FN is test result compliance as second level, and the compliance label is second level, TN is test result compliance as second level, and the compliance label is first level.
And 4, if the error value is larger than the preset error threshold value, adjusting the model parameters of the medical advice compliance analysis model to be trained, and returning to and executing the function 2.
Comparing the obtained error value with a preset threshold, wherein the error threshold can be 0.15, evaluating that the compliance analysis model to be trained is unqualified when the error value is larger than the error threshold, returning to the execution function 2, and training the compliance analysis model to be trained again.
And 5, if the error value is not greater than the preset error threshold value, obtaining the doctor's advice compliance analysis model.
And when the error value is not greater than the error threshold value, evaluating that the training process of the medical advice compliance analysis model to be trained is qualified, and ending the training process to obtain the medical advice compliance analysis model.
The information obtaining module 102 is configured to obtain treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, where the treatment information includes a treatment policy of a treated period of the target chronic disease patient and an order of the treated period, and obtain daily work and rest data of the target chronic disease patient in the treated period.
The chronic disease management system is a model constructed according to the existing medical information and the treatment schemes and effects of a plurality of patients, and can provide a long-term medical plan for the chronic disease patients by utilizing the physical conditions of the patients in each stage.
In an alternative embodiment of the present invention, the apparatus further comprises: the doctor's advice information acquisition unit, and patient's daily work and rest data acquisition unit is used for:
the medical advice information acquisition unit is used for acquiring treatment information of a target chronic disease patient, wherein the treatment information comprises a treated period of the target chronic disease patient and medical advice of the treated period.
In the embodiment of the invention, the treatment information is a treatment strategy and corresponding notice which are preset by a medical system or a doctor for a chronic patient and comprise each continuous treatment period. For example, taking medicines regularly, avoiding meat fishy smell, reducing oil salt, drinking more water and the like. When the treatment of one treatment period is finished, the next treatment period is started.
And the daily work and rest data acquisition unit is used for acquiring daily work and rest data of the target chronic patient in the treated period.
In the embodiment of the invention, the daily work and rest data mainly comprises the medicine taking condition of the target chronic patient and the daily condition corresponding to the notice. For example, the notes are meat fishy smell, greasy smell, food with high purine smell, taking medicines several times a day, staggering taking medicines and the like, the daily conditions are the conditions of the target chronic patients aiming at the notes, specifically, the taking conditions can be obtained by acquiring the taking time and the medicine quantity of each time of the target chronic patients, and the daily work and rest conditions of the target chronic patients can be obtained by the conditions of the diet, the working force, the sleeping frequency duration and the like of each time of the target chronic patients.
The compliance detection module 103 is configured to determine a level of compliance of the target chronic patient's behavior to the order during the treated period using the daily work and rest data, the order, and the order compliance analysis model analysis.
According to the embodiment of the invention, the daily work and rest data of the patient are obtained, and the daily work and rest data are sent to the doctor's advice compliance analysis model for compliance grade assessment, so that the result of compliance grade assessment can be obtained.
In detail, in the embodiment of the present invention, the compliance level of the target chronic patient's behavior to the medical order in the treated period is determined by the analysis of the daily work and rest data, the medical order, and the medical order compliance analysis model, and the compliance detection module 103 is specifically configured to:
performing feature extraction and comparison operation on the daily work and rest data and the medical advice by using the medical advice compliance analysis model to obtain compliance scores;
carrying out normalization operation on the compliance score by utilizing a pre-constructed normalization function to obtain a compliance value of the target chronic patient;
when the compliance value is less than a first preset threshold, determining that the compliance level of the target chronic patient is a first level;
And when the compliance value is larger than a second preset threshold value, determining that the compliance level of the target chronic disease patient is a second level, wherein the second preset threshold value is larger than or equal to the first preset threshold value.
In the embodiment of the invention, the daily work and rest data and the medical advice, which are input by a user and correspond to the target chronic patient in a treated period, are processed by using the medical advice compliance analysis model, and the daily work and rest data and the medical advice are compared to obtain a medicine intake ratio: 120% of medicine taking average interval ratio: 5h/4h, diet meets the doctor's advice degree: 50% … …, and the like, obtaining the compliance score as 850, and performing normalization operation on the compliance score to obtain the compliance value as 0.85, and judging the compliance grade of the target chronic disease patient as the second grade if the compliance value is larger than a preset second threshold value of 0.8.
Wherein the normalization function can convert the results of the compliance analysis model into a percentage of 0 to 1, i.e., the normalized value.
In detail, in the embodiment of the present invention, the intervention is performed on the treatment strategy of the target chronic patient after the treated period according to the pre-constructed scene setting rule, and the compliance detection module 103 is specifically configured to:
And according to a pre-constructed scene setting rule, automatically intervening the target chronic patient when the compliance level of the target chronic patient is the first level.
Further, as shown in fig. 3 below, in an embodiment of the present invention, the automatic intervention on the target chronic patient includes:
and obtaining a compliance report and a physical condition development condition of the target chronic patient in the treated period, and automatically generating and feeding back the compliance report and the physical condition development condition to the target chronic patient periodically.
In the embodiment of the invention, the physical health data of the target chronic patient is acquired in the treatment period, the compliance report is generated according to the compliance grade of the physical health data, and the physical condition development condition is judged.
When the compliance grade of the target chronic patient is the second grade, performing manual intervention on the target chronic patient;
semi-automatic intervention is performed on the target chronic patient when the level of compliance of the target chronic patient is not either of the first level and the second level.
Specifically, in the embodiment of the present invention, the scene setting rule is a pre-constructed compliance dividing table that adopts different auxiliary strategies according to the compliance of the target chronic patient. When the compliance of the target chronic patient is the first grade, the target chronic patient can be periodically reminded through intelligent prompt information; when the compliance of the target chronic patient is of the second level, manual intervention of a guardian is required, and the medical treatment plan of the target chronic patient is ensured to be orderly carried out; patient compliance is generally based on the selection of the target chronic patient, and intelligent or manual intervention may be performed on the target chronic patient when the patient compliance is between the first level and the second level.
The automatic intervention is to periodically send the compliance report and the intelligent prompt information of the physical condition development condition through a pre-constructed program to remind the target chronic patient, and the manual intervention is to send the compliance report and the intelligent prompt information of the physical condition development condition to a guardian of the target chronic patient to indirectly remind the target chronic patient. The semiautomatic intervention refers to the manual intervention and the automatic intervention as an arbitrarily selected intervention method.
The treatment strategy intervention module 104 is configured to determine whether to intervene in a pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance level, and obtain the treatment strategy of the target chronic patient after the treated period when the determination result is that no intervention is required, and set rules according to a pre-constructed scene when the determination result is that intervention is required, and intervene in the treatment strategy of the target chronic patient after the treated period.
In an alternative embodiment of the present invention, the apparatus further comprises: the device comprises a judgment intervention unit and a target treatment strategy acquisition unit, wherein the judgment intervention unit is used for:
the judgment intervention unit is used for judging whether to intervene in a pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance grade.
In detail, in the embodiment of the present invention, the determining whether to intervene in the pre-constructed treatment strategy of the target chronic patient after the treated period according to the compliance level, and the determining and adjusting unit is specifically configured to:
determining, when the compliance level is a first level, a treatment strategy that does not interfere with the target chronically ill patient after the treated period;
When the compliance level is a second level, determining a treatment strategy for intervening in the target chronically ill patient after the treated period, the first level being higher than the second level.
In the embodiment of the invention, when the compliance grade is the first grade, the daily work and rest habit of the target chronic patient in the treated period is high in matching with the medical advice of the treated period, and the pre-constructed treatment strategy of the next treatment period is not adjusted at the moment.
When the compliance level is the second level, it indicates that the daily work and rest habits of the target chronically ill patient in the treated cycle are low in matching with the orders of the treated cycle, so that the completion of the treatment plan in the treated cycle is low, and then the treatment strategy after the treated cycle needs to be adjusted.
And the target treatment strategy acquisition unit is used for continuously executing the treatment strategy of the target chronic patient after the treated period when the judgment result is that the intervention is not needed, and performing the intervention on the treatment strategy of the target chronic patient after the treated period according to the preset scene setting rule when the judgment result is that the intervention is needed.
In the embodiment of the present invention, if the determination result is not adjusted, a target treatment strategy of the target chronic patient after the treated period is obtained from the treatment information.
In the embodiment of the present invention, the scene setting rule is the rule method of automatic intervention, manual intervention, and automatic intervention, and if the judgment result is adjustment, real-time sign data of the target chronic disease patient at each time node in the treated period can be obtained to obtain a stage data set, the stage data set is processed by using a pre-built medical diagnosis system, and the disease development trend of the target chronic disease patient is analyzed to obtain the target treatment strategy.
Preferably, the real-time physical sign data is physical sign data of the chronically ill patient acquired at regular time by the chronicity system, for example, the real-time sign data includes: the patient physical index data detected by various medical examination devices is exemplified by hypertension patients, and includes data such as blood pressure, blood fat, uric acid, protein content and the like.
According to the embodiment of the invention, the stage data set is imported into a pre-constructed chronic disease management system at fixed time, and fluctuation of the implementation sign data in a preset time period is recorded through the chronic disease management system, so that a physical condition fluctuation map is obtained;
Judging the disease development trend according to the physical condition fluctuation diagram, and obtaining a medical advice result of the next treatment period according to the disease development trend, namely a target treatment strategy of the target chronic patient after the treatment period.
Preferably, in the embodiment of the present invention, the chronic disease management system determines whether each index is within a preset normal interval and whether the disease development trend is within a preset range, so as to intelligently output a target treatment policy of the target chronic disease patient after the treatment period according to whether each index is abnormal and the disease development trend.
According to the embodiment of the invention, the doctor's advice and daily work and rest data preset by the target chronic patient are analyzed through the doctor's advice compliance analysis model, the compliance level of the chronic patient to the doctor's advice can be rapidly and accurately judged, whether the treatment strategy after the treated period is adjusted is judged through different compliance levels, and then the treatment strategy after the treated period is determined. In the dynamic intervention process of the treatment strategy, the acquired treatment strategy can be adjusted in real time according to the treatment condition of the chronic patient in the previous stage, and the treatment strategy is changed according to the actual daily work and rest condition of the chronic patient. Therefore, the embodiment of the invention can accurately and efficiently detect the compliance of the patient, thereby increasing the accuracy of formulating the treatment strategy.
Fig. 5 is a schematic structural diagram of an electronic device for implementing the dynamic intervention method of the treatment strategy according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a dynamic intervention program 12 of a treatment strategy.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of dynamic interventions 12 of treatment strategies, etc., but also for temporarily storing data that have been output or are to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects the respective components of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory 11 (e.g., a dynamic intervention program to execute a therapeutic strategy, etc.), and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 5 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The dynamic intervention program 12 of the treatment strategy stored by the memory 11 in the electronic device 1 is a combination of a plurality of computer programs, which, when run in the processor 10, can implement:
training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
obtaining treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and a doctor's advice of the treated period;
Acquiring daily work and rest data of the target chronic patient in the treated period;
determining a level of compliance of the target chronically ill patient's behavior to the order over the treated period using the daily work and rest data, the order, and the order compliance analysis model analysis;
judging whether to intervene in a pre-established treatment strategy of the target chronic patient after the treated period according to the compliance grade;
and when the judgment result is that the intervention is not needed, continuing to execute the treatment strategy of the target chronic patient after the treated period, and when the judgment result is that the intervention is needed, performing the intervention on the treatment strategy of the target chronic patient after the treated period according to the preset scene setting rule.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Further, the computer-usable 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 from the use of blockchain nodes, and the like.
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
obtaining treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and a doctor's advice of the treated period;
acquiring daily work and rest data of the target chronic patient in the treated period;
determining a level of compliance of the target chronically ill patient's behavior to the order over the treated period using the daily work and rest data, the order, and the order compliance analysis model analysis;
Judging whether to intervene in a pre-established treatment strategy of the target chronic patient after the treated period according to the compliance grade;
and when the judgment result is that the intervention is not needed, continuing to execute the treatment strategy of the target chronic patient after the treated period, and when the judgment result is that the intervention is needed, performing the intervention on the treatment strategy of the target chronic patient after the treated period according to the preset scene setting rule.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any accompanying diagram representation in the claims should not be considered as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A method of dynamic intervention of a therapeutic strategy, the method comprising:
training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
obtaining treatment information of a target chronic disease patient by using a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and an order of the treated period;
Acquiring daily work and rest data of the target chronic patient in the treated period;
determining a level of compliance of the target chronically ill patient's behavior to the order over the treated period using the daily work and rest data, the order, and the order compliance analysis model analysis;
judging whether to intervene in a pre-established treatment strategy of the target chronic patient after the treated period according to the compliance grade;
and when the judgment result is that intervention is not needed, continuing to execute the treatment strategy of the target chronic patient after the treated period, when the judgment result is that intervention is needed, acquiring real-time sign data of the target chronic patient at each time node in the treated period, obtaining a stage data set, processing the stage data set by using a pre-built medical diagnosis system, analyzing the disease development trend of the target chronic patient, acquiring a target treatment strategy, performing intervention on the treatment strategy of the target chronic patient after the treated period according to a pre-built scene setting rule, and outputting the target treatment strategy after the treated period.
2. The method of dynamic intervention of a treatment strategy of claim 1, wherein the analyzing using the daily work and rest data, the orders, and the order compliance analysis model to determine a level of compliance of the behavior of the target chronically ill patient with the orders over the treated period comprises:
performing feature extraction and comparison operation on the daily work and rest data and the medical advice by using the medical advice compliance analysis model to obtain compliance scores;
carrying out normalization operation on the compliance score by utilizing a pre-constructed normalization function to obtain a compliance value of the target chronic patient;
when the compliance value is less than a first preset threshold, determining that the compliance level of the target chronic patient is a first level;
and when the compliance value is larger than a second preset threshold value, determining that the compliance level of the target chronic patient is a second level, wherein the second preset threshold value is larger than or equal to the first preset threshold value.
3. The method of dynamic intervention of a treatment strategy of claim 1, wherein said determining whether to intervene in a pre-constructed treatment strategy of said target chronically ill patient after said treated period based on said compliance level comprises:
Determining, when the compliance level is a first level, a treatment strategy that does not interfere with the target chronically ill patient after the treated period;
when the compliance level is a second level, determining a treatment strategy for intervening in the target chronically ill patient after the treated period, the first level being higher than the second level.
4. A method of dynamic intervention of a treatment strategy according to claim 3, wherein said intervention of a treatment strategy of said target chronically ill patient after said treated cycle according to pre-constructed scene set rules comprises:
according to a pre-constructed scene setting rule, when the compliance level of the target chronic disease patient is the first level, automatically intervening the target chronic disease patient;
when the compliance grade of the target chronic patient is the second grade, performing manual intervention on the target chronic patient;
semi-automatic intervention is performed on the target chronic patient when the level of compliance of the target chronic patient is not either of the first level and the second level.
5. The method of dynamic intervention for a therapeutic strategy as in claim 4, wherein said automatically intervening on said target chronically ill patient comprises:
And obtaining a compliance report and a physical condition development condition of the target chronic patient in the treated period, and automatically generating and feeding back the compliance report and the physical condition development condition to the target chronic patient periodically.
6. The method of dynamic intervention of a treatment strategy of claim 1, wherein the order compliance analysis model to be trained is a convolutional neural network model constructed based on a fransform model framework.
7. The method of claim 1, wherein the order compliance analysis model to be trained includes a feature extraction network, a plurality of linear activation layers, and a convolutional neural network, wherein training the order compliance analysis model to be trained using the pre-constructed patient treatment data training set to obtain the order compliance analysis model comprises:
step I, acquiring a patient treatment data training set input by a user, cleaning the patient treatment data training set to obtain cleaning data, importing the cleaning data into the medical advice compliance analysis model to be trained, and performing feature extraction on the cleaning data by utilizing the feature extraction network to obtain a feature sequence set;
Step II, activating the characteristic sequence set by utilizing the multi-layer linear activation layer to obtain a prediction result set;
step III, calculating an error value of a pre-constructed compliance label corresponding to the prediction result set and the patient treatment data training set, and judging whether the error value is larger than a preset error threshold value or not;
step IV: if the error value is larger than the preset error threshold value, adjusting model parameters of the medical advice compliance analysis model to be trained, and returning to the step II;
step V: and if the error value is not greater than the preset error threshold value, obtaining the doctor's advice compliance analysis model.
8. A dynamic intervention device of a treatment strategy, the device comprising:
the model construction module is used for training the medical advice compliance analysis model to be trained by utilizing the pre-constructed patient treatment data training set to obtain the medical advice compliance analysis model;
the information acquisition module is used for acquiring treatment information of a target chronic disease patient by utilizing a pre-constructed chronic disease management system, wherein the treatment information comprises a treatment strategy of a treated period of the target chronic disease patient and medical orders of the treated period, and acquiring daily work and rest data of the target chronic disease patient in the treated period;
A compliance detection module for analyzing and determining a compliance level of the target chronic patient's behavior to the order within the treated period using the daily work and rest data, the order, and the order compliance analysis model;
the treatment strategy intervention module is used for judging whether to intervene in the pre-built treatment strategy of the target chronic disease patient after the treated period according to the compliance grade, continuously executing the treatment strategy of the target chronic disease patient after the treated period when the judgment result is that no intervention is needed, acquiring real-time sign data of the target chronic disease patient at each time node in the treated period when the judgment result is that intervention is needed, obtaining a stage data set, processing the stage data set by utilizing a pre-built medical diagnosis system, analyzing the disease development trend of the target chronic disease patient, obtaining a target treatment strategy, intervening the treatment strategy of the target chronic disease patient after the treated period according to a pre-built scene setting rule, and outputting the target treatment strategy after the treated period.
9. An electronic device, the electronic device comprising:
At least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of dynamic intervention of a treatment strategy as claimed in any of claims 1 to 7.
10. A computer-readable storage medium comprising a storage data area storing created data and a storage program area storing a computer program; a method of dynamic intervention of a treatment strategy according to any of claims 1 to 7, wherein the computer program, when executed by a processor, is implemented.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110343327.9A CN112927812B (en) | 2021-03-30 | 2021-03-30 | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium |
| PCT/CN2021/096523 WO2022205601A1 (en) | 2021-03-30 | 2021-05-27 | Dynamic intervention method and apparatus for treatment strategy, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110343327.9A CN112927812B (en) | 2021-03-30 | 2021-03-30 | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112927812A CN112927812A (en) | 2021-06-08 |
| CN112927812B true CN112927812B (en) | 2024-03-19 |
Family
ID=76176630
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110343327.9A Active CN112927812B (en) | 2021-03-30 | 2021-03-30 | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112927812B (en) |
| WO (1) | WO2022205601A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116881335B (en) * | 2023-07-24 | 2024-06-04 | 郑州华商科技有限公司 | Multi-mode data intelligent analysis system and method |
| CN116795896B (en) * | 2023-08-29 | 2023-10-27 | 中南大学湘雅医院 | Big data-based rehabilitation exercise strategy generation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009390A (en) * | 2017-09-02 | 2018-05-08 | 成都市双流区贸园医院有限公司 | A kind of chronic disease medical order compliance management method and system |
| CN111899844A (en) * | 2020-09-28 | 2020-11-06 | 平安科技（深圳）有限公司 | Sample generation method and device, server and storage medium |
| CN111933278A (en) * | 2020-08-29 | 2020-11-13 | 青海省疾病预防控制中心 | Chronic disease management system based on artificial intelligence |
| CN112102956A (en) * | 2020-10-13 | 2020-12-18 | 杭州健海科技有限公司 | Method and system for improving compliance of diabetic patient |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8566121B2 (en) * | 2005-08-29 | 2013-10-22 | Narayanan Ramasubramanian | Personalized medical adherence management system |
| US20170124281A1 (en) * | 2015-10-29 | 2017-05-04 | Cerner Innovation, Inc. | Systems and Methods for Analyzing Medication Adherence Patterns |
-
2021
- 2021-03-30 CN CN202110343327.9A patent/CN112927812B/en active Active
- 2021-05-27 WO PCT/CN2021/096523 patent/WO2022205601A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009390A (en) * | 2017-09-02 | 2018-05-08 | 成都市双流区贸园医院有限公司 | A kind of chronic disease medical order compliance management method and system |
| CN111933278A (en) * | 2020-08-29 | 2020-11-13 | 青海省疾病预防控制中心 | Chronic disease management system based on artificial intelligence |
| CN111899844A (en) * | 2020-09-28 | 2020-11-06 | 平安科技（深圳）有限公司 | Sample generation method and device, server and storage medium |
| CN112102956A (en) * | 2020-10-13 | 2020-12-18 | 杭州健海科技有限公司 | Method and system for improving compliance of diabetic patient |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022205601A1 (en) | 2022-10-06 |
| CN112927812A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112927812B (en) | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium | |
| WO2022141927A1 (en) | Health intervention system, server, and health management system | |
| EP3307165A1 (en) | Method and system for assessing mental state | |
| CN103440421B (en) | medical data processing method and system | |
| WO2019041711A1 (en) | Chronic disease follow-up monitoring system and method based on health examination all-in-one machine | |
| EP3117354B1 (en) | Optimization of alarm settings for alarm consultancy using alarm regeneration | |
| WO2019041710A1 (en) | Chronic disease management system and method based on health examination all-in-one machine | |
| CN113674858A (en) | Online medical prescription medication intelligent checking method, device, equipment and storage medium | |
| CN111696662A (en) | Disease prediction method, device and storage medium | |
| CN116483976A (en) | Registration department recommendation method, device, equipment and storage medium | |
| CN117393109B (en) | Scene-adaptive diet monitoring method, device, equipment and storage medium | |
| CN117877681A (en) | Method and device for monitoring and early warning daily diet data of heart failure patient | |
| CN115316340B (en) | Yak dzo fattening method, device, equipment and medium based on biochemical indexes | |
| CN113470825B (en) | Venous thromboembolism prediction system, method, equipment and medium | |
| CN116403693A (en) | Method, device, equipment and storage medium for dispatching questionnaire | |
| CN115565673A (en) | Medical prediction system for postoperative wound infection based on big data | |
| CN114388125A (en) | Human-computer interaction-based physique identification method and system and storage medium | |
| US11081217B2 (en) | Systems and methods for optimal health assessment and optimal preventive program development in population health management | |
| CN114864094A (en) | Intensive care unit intelligent control method, equipment and medium | |
| CN107480295A (en) | The modification method of user data | |
| CN117838072B (en) | Cardiovascular disease monitoring method, device, equipment and storage medium of intelligent mattress | |
| CN115762812B (en) | Digital diagnosis and treatment method, system, equipment and medium for stroke patient | |
| CN114722977B (en) | Medical object classification method and device, electronic equipment and storage medium | |
| CN117809841B (en) | Skin special patient management method and system based on large model technology | |
| CN116913486A (en) | Medical service intelligent scheduling method and device, electronic equipment and storage medium |
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 |