CN116110615A - Digital medical system for intervention in chronic pain - Google Patents
Digital medical system for intervention in chronic pain Download PDFInfo
- Publication number
- CN116110615A CN116110615A CN202310385718.6A CN202310385718A CN116110615A CN 116110615 A CN116110615 A CN 116110615A CN 202310385718 A CN202310385718 A CN 202310385718A CN 116110615 A CN116110615 A CN 116110615A
- Authority
- CN
- China
- Prior art keywords
- intervention
- patient
- treatment
- result
- data acquisition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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
Abstract
The invention provides a digital medical system for intervention of chronic pain, which relates to the technical field of digital therapy and comprises a patient data acquisition end, a diagnosis intervention end and a cloud server, wherein the patient data acquisition end and the diagnosis intervention end are connected in a remote communication way through the cloud server, and a doctor provides intervention treatment for a patient through data interaction between the patient data acquisition end and the diagnosis intervention end; the patient data acquisition end is used for receiving the treatment scheme sent by the diagnosis intervention end and generating an evaluation result according to the self-health data input by the patient; the diagnosis intervention end is used for receiving the evaluation result of the patient, generating a calculation result through a preset decision support model, and sending the calculation result to the patient data acquisition end as a treatment scheme. Solves the problems that the pain change condition and the body change of a patient with chronic pain can not be dynamically estimated in the prior art, the dosage of physical treatment and medicines can be dynamically adjusted, and the noninvasive psychological treatment and the motion therapy can be provided.
Description
Technical Field
The invention relates to the technical field of digital therapy, in particular to a digital medical system for intervention of chronic pain.
Background
The digital therapy alliance (Digital Therapeutics Alliance, DTA) is the largest industry alliance in the field of digital therapy, and digital therapies are well defined in its report: digital therapy (Digital therapeutics, DTx) is a therapy based on a software program that provides evidence-based therapeutic intervention to a patient to prevent, manage or treat a disease. Digital therapy can be used alone, in combination with drugs, or in combination with other therapies to improve the health of patients, equivalent to conventional drugs and treatment methods.
The current social chronic diseases have the greatest influence on human life, and are focused on chronic cardiovascular and cerebrovascular diseases and chronic pain diseases, wherein the chronic pain diseases seriously affect the life quality and the mind of patients. In hundreds of years of human research history on chronic pain diseases, various methods for treating and recovering the chronic pain diseases are invented, and mainly comprise two types of physical treatment and drug treatment: physical therapy such as electric therapy, hydromagnetic therapy, etc.; the medicine treatment method mainly comprises oral medicine and smearing medicine, wherein the oral medicine refers to oral analgesic medicine, and the smearing medicine refers to external medicine with various plaster or smearing properties, etc.
However, both physical therapy and drug therapy have their own drawbacks, such as expensive material treatment equipment, need to be operated by specialized staff, and adverse reactions occur to more or less oral analgesic in drug therapy, and the applied drug cannot well reach diseased parts due to skin obstruction, and wastes medicinal materials. It is necessary to adjust the treatment method in time according to the condition of the patient. Therefore, how to dynamically evaluate the pain change condition and the body change of the chronic pain patient, and dynamically generate a corresponding treatment scheme by combining the self-evaluation result of the patient, and ensure that the health condition of the patient is continuously monitored for a long time, becomes a problem to be solved.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a digital medical system for intervention of chronic pain, which solves the problems that the pain change condition and the body change of a patient suffering from chronic pain cannot be dynamically evaluated, the dosage of physical therapy and medicine is dynamically adjusted, and noninvasive psychological therapy and exercise therapy are provided in the prior art.
In order to achieve the above purpose, the invention adopts the following technical scheme:
there is provided a digital medical system for intervention in chronic pain, comprising:
a patient data acquisition end;
diagnosing an intervention end;
a cloud server;
the patient data acquisition end and the diagnosis intervention end are connected in a remote communication mode through a cloud server, and a doctor provides intervention treatment for a patient through data interaction between the patient data acquisition end and the diagnosis intervention end;
the patient data acquisition end is used for receiving the treatment scheme sent by the diagnosis intervention end and generating an evaluation result according to the self-health data input by the patient;
the diagnosis intervention end is used for receiving an evaluation result of a patient, generating a calculation result through a preset decision support model, and sending the calculation result to the patient data acquisition end as a treatment scheme.
Preferably, the diagnosis intervention end comprises a data processing unit, a remote consultation unit, a result acquisition unit and a scheme output unit;
the result acquisition unit is used for receiving the evaluation result of the patient; the data processing unit is used for processing the evaluation result through a built-in decision support model to obtain a calculation result; the scheme output unit is used for outputting the calculation result to a patient data acquisition end; the remote consultation unit is used for carrying out audio and video communication with the patient data acquisition end.
Preferably, the data interaction process between the patient data acquisition end and the diagnosis intervention end is specifically:
step 1: the patient acquires doctor's advice information in advance;
step 2: health evaluation is carried out through the patient data acquisition end by combining self health data and doctor advice information, and an evaluation result is generated;
step 3: the diagnosis intervention end receives the evaluation result, takes the evaluation result as input into a decision support model, and outputs a model calculation result as a treatment scheme;
step 4: and 2, the patient data acquisition end receives the treatment scheme sent by the diagnosis intervention end, records the treatment result generated after the treatment scheme is executed as self-health data, and repeats the step 2.
Preferably, the order information includes a medication regimen, a physical therapy regimen, a psychological therapy regimen, and a motor rehabilitation regimen.
Preferably, in the step 2, the self-health data includes subjective assessment of pain, pain location, exercise tolerance assessment of the patient.
Preferably, the specific calculation process of the decision support model is as follows:
input: training data set D, feature set A, threshold e
And (3) outputting: decision tree T
If all the instances in D belong to the same class C k T is a single-node tree, C is taken as k As the class mark of the node, outputting T; if A is the empty set, T is a single-node tree, and class C with the largest instance number in D is selected k As the class mark of the node, outputting T;
otherwise, calculating the information gain ratio of the feature A to the data set D, and selecting the feature Ag with the largest information gain ratio; if the information gain ratio of Ag is smaller than the threshold value e, setting T as a single-node tree, and setting class C with the largest number of instances in D k As the class mark of the node, outputting T;
if the information gain ratio of Ag is greater than the threshold e, for each possible value a of Ag i In A way g =a i Dividing D into several non-empty subsets D i D is to i The class with the largest number of examples is used as a mark to construct a child node, and the node and the child node form a tree T and output the T.
Preferably, the step 3 further includes the following:
step a: performing risk diversion processing on the evaluation result according to the intervention threshold value, and if a high risk evaluation result is obtained, entering a step b; if the low risk assessment result is obtained, entering a step c;
step b: the doctor receives the high risk assessment result to perform online intervention, and adjusts the doctor's advice and the decision support model;
step c: and directly substituting the low risk assessment result into the decision support model.
Preferably, the method for online intervention by the physician in step b receives the high risk assessment result is specifically to learn about the condition of the patient through image-text and audio-video consultation.
Preferably, in the step 4, when the patient records the treatment result generated after the treatment plan is executed as self-health data, the method specifically includes the following steps:
step 41: training a deep neural network model in advance, and constructing a pathology data set;
step 42: then any treatment result in a treatment period in the pathological data set is extracted and substituted into a pre-recognition network, and the maximum value is taken as the credibility of the treatment result after softmax activation treatment;
step 43: and for the treatment results with the credibility higher than the set threshold, the treatment results are listed into a pathological data set, the characteristic identification is carried out on the treatment results by adopting a lightweight convolution module, the characteristic identification result is output, the loss of the characteristic identification result and the label is calculated, the loss is transmitted reversely, and the layer of credible sample network is trained.
Preferably, the backbone network of the deep neural network model is a first convolution module formed by stacking a plurality of convolution layers, and the pre-recognition network comprises a second convolution module for carrying out feature recognition on treatment results and a full-connection layer.
The beneficial effects of the invention are as follows:
the system carries out remote monitoring through a network, carries out remote interaction with doctors, combines a decision support model in a mode of remotely acquiring health information, generates a corresponding treatment scheme according to health data of a patient, and remotely transmits the treatment scheme to a patient receiving end, achieves the effect of dynamically guiding the medication of the patient in an on-line remote data transmission mode, continuously monitors the frequency and treatment parameters of physical treatment, guides a user to carry out exercise rehabilitation treatment, continuously monitors the treatment effect, and can provide comprehensive treatment of noninvasive psychological treatment and exercise treatment; meanwhile, the data with high credibility in the treatment results are screened according to the deep neural network model, the influence of the low credibility treatment results on the accuracy of the self-health data is eliminated, the high credibility results are returned to the training deep neural network model, the identification accuracy of the deep neural network on the credibility treatment results is improved, and meanwhile the anti-interference performance of the deep neural network in the identification process can be improved.
Drawings
FIG. 1 is a schematic diagram of a digital medical system for intervention in chronic pain in accordance with the present invention;
FIG. 2 is a flow chart of a data interaction process between the patient data acquisition side and the diagnostic intervention side of FIG. 1;
fig. 3 is a step chart of the digital medical system for intervention in chronic pain according to the present invention, in which the treatment result generated after the treatment regimen is performed is recorded as self-health data.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, there is provided a digital medical system for intervention in chronic pain, comprising:
a patient data acquisition end;
diagnosing an intervention end;
a cloud server;
the patient data acquisition end and the diagnosis intervention end are connected in a remote communication mode through a cloud server, and a doctor provides intervention treatment for a patient through data interaction between the patient data acquisition end and the diagnosis intervention end;
the patient data acquisition end is used for receiving the treatment scheme sent by the diagnosis intervention end and generating an evaluation result according to the self-health data input by the patient;
the diagnosis intervention end is used for receiving an evaluation result of a patient, generating a calculation result through a preset decision support model, and sending the calculation result to the patient data acquisition end as a treatment scheme.
More specifically, the diagnosis intervention end comprises a data processing unit, a remote consultation unit, a result acquisition unit and a scheme output unit;
the result acquisition unit is used for receiving the evaluation result of the patient; the data processing unit is used for processing the evaluation result through a built-in decision support model to obtain a calculation result; the scheme output unit is used for outputting the calculation result to a patient data acquisition end; the remote consultation unit is used for carrying out audio and video communication with the patient data acquisition end.
The remote consultation unit can achieve the effect through the existing commonly-used built-in audio and video software, and further, the corresponding audio and video software is also built in the patient data acquisition end, so that the purpose of audio conversation or video communication with the remote consultation unit can be achieved.
More specifically, as shown in fig. 2, the data interaction process between the patient data acquisition end and the diagnostic intervention end is specifically:
step 1: the patient acquires doctor's advice information in advance;
step 2: health evaluation is carried out through the patient data acquisition end by combining self health data and doctor advice information, and an evaluation result is generated;
step 3: the diagnosis intervention end receives the evaluation result, takes the evaluation result as input into a decision support model, and outputs a model calculation result as a treatment scheme;
step 4: and 2, the patient data acquisition end receives the treatment scheme sent by the diagnosis intervention end, records the treatment result generated after the treatment scheme is executed as self-health data, and repeats the step 2.
The system carries out remote monitoring through a network, carries out remote interaction with doctors, guides patients to take medicines in a mode of remotely acquiring health information, continuously monitors the frequency and treatment parameters of physical treatment, guides users to carry out sports rehabilitation treatment, continuously monitors the treatment effect, can dynamically adjust the physical treatment and the medicine dosage, and provides comprehensive therapy of noninvasive psychological treatment and sports therapy; in step 4, the method also includes reminding the user to perform treatment and evaluation at regular time according to the treatment scheme and the frequency of the evaluation scheme, wherein the reminding content includes sound reminding, treatment guiding reminding, dosage and notice of taking medicine, physical treatment method and parameters, evaluation list and description of the evaluation list.
More specifically, the order information includes a medication regimen, a physical therapy regimen, a psychological therapy regimen, and a motor rehabilitation regimen.
The content of the drug treatment scheme specifically comprises drug names, single doses, use frequency and use methods; the content of the physical treatment scheme specifically comprises treatment names, treatment parameters, treatment parts and use frequency; the content of the psychological treatment specifically comprises a treatment method and treatment frequency; the content of the rehabilitation therapy specifically comprises a movement method and movement frequency; the content of the patient condition specifically comprises the current medical history, the past history and the physical examination condition related to the pain.
More specifically, in the step 2, the self-health data includes subjective assessment of pain, pain location and exercise tolerance assessment of the patient.
Subjective assessment of pain includes a numerical scale, with numbers 0-10 representing different degrees of pain, 0 being painless, 10 being the most intense pain, giving the patient himself a number that best represents his pain level, interpretation of the numbers: 0 pain-free, 1-3 mild pain, 4-6 moderate pain, 7-10 severe pain; the influence degree of pain on activities is evaluated, wherein the influence degree comprises four activities of deep breathing, cough, turning over and getting-out activities, the activities are not influenced by pain, the activities are limited due to pain, and the activities can not be completed due to limited pain; the painful site is selected one or more sites through the 3D human body; the exercise tolerance is tested by walking for 6 minutes, namely, a distance of 30 meters is adopted, the patient walks to and fro at the full power of 30 meters, and a walking distance of 6 minutes is recorded.
More specifically, the specific calculation process of the decision support model is as follows:
input: training data set D, feature set A, threshold e
And (3) outputting: decision tree T
If all the instances in D belong to the same class C k T is a single-node tree, C is taken as k As the class mark of the node, outputting T; if A is the empty set, T is a single-node tree, and class C with the largest instance number in D is selected k As the class mark of the node, outputting T;
otherwise, calculating the information gain ratio of the feature A to the data set D, and selecting the feature Ag with the largest information gain ratio; if the information gain ratio of Ag is smaller than the threshold value e, setting T as a single-node tree, and setting class C with the largest number of instances in D k As the class mark of the node, outputting T;
if the information gain ratio of Ag is greater than the threshold e, for each possible value a of Ag i In A way g =a i Dividing D into several non-empty subsets D i D is to i The class with the largest number of examples is used as a mark to construct a child node, and the node and the child node form a tree T and output the T.
For the ith child node, with D i For training set, use A- { A g And performing recursive call on the decision support model by taking the final output T as a final result.
More specifically, the step 3 further includes the following:
step a: performing risk diversion processing on the evaluation result according to the intervention threshold value, and if a high risk evaluation result is obtained, entering a step b; if the low risk assessment result is obtained, entering a step c;
step b: the doctor receives the high risk assessment result to perform online intervention, and adjusts the doctor's advice and the decision support model;
step c: and directly substituting the low risk assessment result into the decision support model.
More specifically, the method for online intervention by the traditional Chinese medicine in the step b for receiving the high risk assessment result is specifically to know the condition of the patient through the image-text and audio-video consultation mode.
As shown in fig. 3, more specifically, in the step 4, when the patient records the treatment result generated after the treatment plan is executed as self-health data, the method specifically includes the following steps:
step 41: training a deep neural network model in advance, and constructing a pathology data set;
step 42: then any treatment result in a treatment period in the pathological data set is extracted and substituted into a pre-recognition network, and the maximum value is taken as the credibility of the treatment result after softmax activation treatment;
step 43: and for the treatment results with the credibility higher than the set threshold, the treatment results are listed into a pathological data set, the characteristic identification is carried out on the treatment results by adopting a lightweight convolution module, the characteristic identification result is output, the loss of the characteristic identification result and the label is calculated, the loss is transmitted reversely, and the layer of credible sample network is trained.
Because the patient himself has incorrect operation or error feeling on the detecting instrument, the treatment result judged by the patient himself has errors with the actual treatment result, the errors can be in the usable range in general, however, the errors with larger partial deviation can influence the accuracy of the finally generated self-health data, for example, the patient himself walks normally in a round trip, the condition of detecting the too low blood oxygen value can be caused by the reasons of improper use of the instrument, the error operation of the instrument and the like, and the judgment condition of the risk diversion treatment process of the evaluation result can be influenced if the result is recorded, the deep neural network model is introduced to judge the treatment result, and the accuracy of the subsequently generated self-health data is further ensured; the set threshold is set according to the past self-health data of the patient, if the patient walks normally in a self-induced round trip, the set threshold of blood oxygen value data is more than or equal to 95%, the data with high reliability in the treatment result is screened according to the deep neural network model, the influence of the low-reliability treatment result on the accuracy of the self-health data is eliminated, the high-reliability result is returned to the training deep neural network model, the identification accuracy of the deep neural network on the reliability treatment result is improved, and the anti-interference performance of the deep neural network in the identification process can be improved.
More specifically, the backbone network of the deep neural network model is a first convolution module formed by stacking a plurality of convolution layers, and the pre-recognition network comprises a second convolution module for carrying out feature recognition on the treatment result and a full-connection layer.
And identifying a second convolution module adopted for identifying the high-reliability samples, wherein the second convolution module is formed by stacking a plurality of convolution layers, and the network scale and the parameter quantity of the second convolution module are smaller than those of the first convolution module.
In view of the above-mentioned, it is desirable,
it will be apparent to those skilled in the art that while preferred embodiments of the present invention have been described, additional variations and modifications may be made to these embodiments once the basic inventive concepts are known to those skilled in the art. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention. It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. A digital medical system for intervention in chronic pain, comprising:
a patient data acquisition end;
diagnosing an intervention end;
a cloud server;
the patient data acquisition end and the diagnosis intervention end are connected in a remote communication mode through a cloud server, and a doctor provides intervention treatment for a patient through data interaction between the patient data acquisition end and the diagnosis intervention end;
the patient data acquisition end is used for receiving the treatment scheme sent by the diagnosis intervention end and generating an evaluation result according to the self-health data input by the patient;
the diagnosis intervention end is used for receiving an evaluation result of a patient, generating a calculation result through a preset decision support model, and sending the calculation result to the patient data acquisition end as a treatment scheme.
2. The digital medical system for intervention in chronic pain according to claim 1, wherein: the diagnosis intervention end comprises a data processing unit, a remote consultation unit, a result acquisition unit and a scheme output unit;
the result acquisition unit is used for receiving the evaluation result of the patient; the data processing unit is used for processing the evaluation result through a built-in decision support model to obtain a calculation result; the scheme output unit is used for outputting the calculation result to a patient data acquisition end; the remote consultation unit is used for carrying out audio and video communication with the patient data acquisition end.
3. The digital medical system for intervention in chronic pain according to claim 1, wherein the data interaction process between the patient data acquisition side and the diagnostic intervention side is specifically:
step 1: the patient acquires doctor's advice information in advance;
step 2: health evaluation is carried out through the patient data acquisition end by combining self health data and doctor advice information, and an evaluation result is generated;
step 3: the diagnosis intervention end receives the evaluation result, takes the evaluation result as input into a decision support model, and outputs a model calculation result as a treatment scheme;
step 4: and 2, the patient data acquisition end receives the treatment scheme sent by the diagnosis intervention end, records the treatment result generated after the treatment scheme is executed as self-health data, and repeats the step 2.
4. A digital medical system for intervention in chronic pain according to claim 3, wherein: the order information includes a medication regimen, a physical therapy regimen, a psychological therapy regimen, and a motor rehabilitation regimen.
5. A digital medical system for intervention in chronic pain according to claim 3, wherein: in the step 2, the self-health data comprise subjective pain assessment, pain parts and exercise tolerance assessment of the patient.
6. A digital medical system for intervention in chronic pain according to claim 3, wherein: the concrete calculation process of the decision support model is as follows:
input: training data set D, feature set A, threshold e
And (3) outputting: decision tree T
If all the instances in D belong to the same class C k T is a single-node tree, C is taken as k As the class mark of the node, outputting T; if A is the empty set, T is a single-node tree, and class C with the largest instance number in D is selected k As the class mark of the node, outputting T;
otherwise, calculating the information gain ratio of the feature A to the data set D, and selecting the feature Ag with the largest information gain ratio; if the information gain ratio of Ag is smaller than the threshold value e, setting T as a single-node tree, and setting class C with the largest number of instances in D k As the class mark of the node, outputting T;
if the information gain ratio of Ag is greater than the threshold e, for each possible value a of Ag i In A way g =a i Dividing D into several non-empty subsets D i D is to i The class with the largest number of examples is used as a mark to construct a child node, and the node and the child node form a tree T and output the T.
7. A digital medical system for intervention in chronic pain according to claim 3, wherein: the step 3 further comprises the following steps:
step a: performing risk diversion processing on the evaluation result according to the intervention threshold value, and if a high risk evaluation result is obtained, entering a step b; if the low risk assessment result is obtained, entering a step c;
step b: the doctor receives the high risk assessment result to perform online intervention, and adjusts the doctor's advice and the decision support model;
step c: and directly substituting the low risk assessment result into the decision support model.
8. The digital medical system for intervention in chronic pain according to claim 7, wherein: the method for online intervention by the traditional Chinese medicine receiving the high risk assessment result in the step b is specifically that the condition of the patient is known through an image-text and audio-video consultation mode.
9. A digital medical system for intervention in chronic pain according to claim 3, wherein: in the step 4, when the patient records the treatment result generated after executing the treatment scheme as self-health data, the method specifically comprises the following steps:
step 41: training a deep neural network model in advance, and constructing a pathology data set;
step 42: then any treatment result in a treatment period in the pathological data set is extracted and substituted into a pre-recognition network, and the maximum value is taken as the credibility of the treatment result after softmax activation treatment;
step 43: and for the treatment results with the credibility higher than the set threshold, the treatment results are listed into a pathological data set, the characteristic identification is carried out on the treatment results by adopting a lightweight convolution module, the characteristic identification result is output, the loss of the characteristic identification result and the label is calculated, the loss is transmitted reversely, and the layer of credible sample network is trained.
10. The digital medical system for intervention in chronic pain according to claim 9, wherein: the backbone network of the deep neural network model is a first convolution module formed by stacking a plurality of convolution layers, and the pre-recognition network comprises a second convolution module for carrying out feature recognition on treatment results and a full-connection layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385718.6A CN116110615B (en) | 2023-04-12 | 2023-04-12 | Digital medical system for intervention in chronic pain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310385718.6A CN116110615B (en) | 2023-04-12 | 2023-04-12 | Digital medical system for intervention in chronic pain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116110615A true CN116110615A (en) | 2023-05-12 |
| CN116110615B CN116110615B (en) | 2023-06-30 |
Family
ID=86260123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310385718.6A Active CN116110615B (en) | 2023-04-12 | 2023-04-12 | Digital medical system for intervention in chronic pain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116110615B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834989A (en) * | 2015-03-27 | 2015-08-12 | 首都医科大学附属北京世纪坛医院 | Multi-disease chronic disease information management system |
| CN106960121A (en) * | 2017-03-16 | 2017-07-18 | 广州家庭医生在线移动新媒体科技有限公司 | A kind of online health diagnosis and treatment method, system and client |
| CN107229814A (en) * | 2016-03-24 | 2017-10-03 | 深圳中迈数字医疗技术有限公司 | The method and system intervened according to chronic's information |
| CN107833632A (en) * | 2017-09-20 | 2018-03-23 | 上海林康医疗信息技术有限公司 | A kind of management system for being used for slow sick Service Operation |
| CN113539485A (en) * | 2021-09-02 | 2021-10-22 | 河南省尚德尚行网络技术有限公司 | Medical data processing method and device |
| CN115662560A (en) * | 2022-10-31 | 2023-01-31 | 单亦文 | Internet-based intelligent hospital management method and system |
-
2023
- 2023-04-12 CN CN202310385718.6A patent/CN116110615B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104834989A (en) * | 2015-03-27 | 2015-08-12 | 首都医科大学附属北京世纪坛医院 | Multi-disease chronic disease information management system |
| CN107229814A (en) * | 2016-03-24 | 2017-10-03 | 深圳中迈数字医疗技术有限公司 | The method and system intervened according to chronic's information |
| CN106960121A (en) * | 2017-03-16 | 2017-07-18 | 广州家庭医生在线移动新媒体科技有限公司 | A kind of online health diagnosis and treatment method, system and client |
| CN107833632A (en) * | 2017-09-20 | 2018-03-23 | 上海林康医疗信息技术有限公司 | A kind of management system for being used for slow sick Service Operation |
| CN113539485A (en) * | 2021-09-02 | 2021-10-22 | 河南省尚德尚行网络技术有限公司 | Medical data processing method and device |
| CN115662560A (en) * | 2022-10-31 | 2023-01-31 | 单亦文 | Internet-based intelligent hospital management method and system |
Non-Patent Citations (1)
| Title |
|---|
| 陈桂宏;蔡庆玲;: "基于Spark的疾病诊疗自助服务平台设计", 医学信息学杂志, no. 08, pages 31 - 34 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116110615B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200418B (en) | Intelligent home diagnosis and therapy system and method based on mobile Internet | |
| Warnock et al. | Chest physiotherapy compared to no chest physiotherapy for cystic fibrosis | |
| US8905925B2 (en) | Cardiac rehabilitation using patient monitoring devices | |
| WO2017166074A1 (en) | Data processing method and device | |
| US20040068197A1 (en) | Dyspnea monitor, and telemedicine system and method | |
| CN107708548A (en) | System and method for the quantization and prediction of cigarette smoking | |
| CN101426422A (en) | System and method of assessing analgesic adequacy using biopotental variability | |
| WO2007044877A2 (en) | Automated patient monitoring and counseling system | |
| CN110547868B (en) | Continuous anesthesia device | |
| Gay et al. | A mobile rehabilitation application for the remote monitoring of cardiac patients after a heart attack or a coronary bypass surgery | |
| CN114177414A (en) | Intelligent adult anesthesia target control method and system based on electroencephalogram signal monitoring | |
| KR20210066271A (en) | Order system using medical deep learning in the field of anesthesia | |
| US20180070875A1 (en) | Determining Stem Cell Treatment Effectiveness By Monitoring Physical Progress | |
| Reed et al. | Effect of high-intensity interval training in patients with atrial fibrillation: a randomized clinical trial | |
| CN114177417A (en) | Anesthesia target control intelligent infusion pump controller based on electroencephalogram parameter feedback | |
| Ahmed | An intelligent healthcare service to monitor vital signs in daily life–a case study on health-iot | |
| WO2023123437A1 (en) | Anesthesia control system, anesthesia system, and non-transitory computer readable medium | |
| CN105447334A (en) | Hypertension diagnosing, treating and managing system based on Android platform | |
| CN116110615B (en) | Digital medical system for intervention in chronic pain | |
| CN104200638A (en) | Intelligent home diagnosis and treatment system and method based on mobile internet | |
| CN113597646A (en) | System, method and program for erectile dysfunction patients | |
| KR101808836B1 (en) | Learning apparatus, learning system, and learning method for using the same | |
| CN115551579B (en) | System and method for assessing ventilated patient condition | |
| WO2022187686A1 (en) | System and method for personalized biofeedback from a wearable device | |
| Alibhai et al. | Protocol for a phase III RCT and economic analysis of two exercise delivery methods in men with PC on ADT |
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 |