Medical record information supervision system of Internet medical platform

Abstract

The invention provides a medical record information supervision system of an internet medical platform. The invention discloses a medical record information supervision system of an internet medical platform. The medical record information supervision system comprises an illness state information acquisition module, an illness state pre-grading module, a diagnosis congestion judgment module, a diagnosis sorting module, a doctor diagnosis module and a diagnosis supervision module. According to the method, the diagnosis sequence of the patient is adjusted according to the descriptor of the patient on the medical platform, so that the patient needing to be diagnosed and treated can be diagnosed online in time, and the diagnosis efficiency of the Internet medical platform is improved on the whole; by recording the illness state information of the patient and the medical record information given by the doctor, whether the doctor diagnoses mistakenly or not is judged, full-link supervision of diagnosis of the Internet medical platform is achieved, and the safety of the Internet medical platform is improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a medical record information supervision system of an Internet medical platform. Background Art

[0002] Internet medical care is a new application of the Internet in the medical industry. It uses the Internet as a carrier and technical means to provide a series of health care services such as health education, medical information query, disease risk assessment, Internet disease consultation, remote consultation, remote treatment, etc. Internet medical care enables diagnosis of illness without leaving home. Patients can describe their own conditions on the Internet medical platform, and doctors will diagnose according to the conditions described by the patients. However, since patients and doctors do not communicate face to face, patients are prone to unclear description of their conditions or malicious questions, which seriously affects the efficiency of diagnosis. At the same time, today's online medical platforms lack effective supervision means, which are prone to diagnostic chaos. Summary of the invention

[0003] In response to the above problems, the present application provides a medical record information supervision system for an Internet medical platform. The present invention adjusts the diagnostic order of patients given by their descriptions on the medical platform, so that patients in need of diagnosis can receive timely online diagnosis, reduce the impact of malicious medical consultation behaviors on the Internet on the medical platform, and improve the overall diagnostic efficiency of the Internet medical platform.

[0004] A medical record information supervision system for an Internet medical platform, comprising:

[0005] The medical condition information acquisition module is used to acquire the medical condition information input by the user in real time, add the medical condition information input by the user to the medical diagnosis database of the user, and establish the medical diagnosis database of the user if the user is undergoing diagnosis for the first time;

[0006] A condition pre-classification module is used to pre-classify the user's condition based on the condition information input by the user;

[0007] The diagnosis congestion detection module is used to obtain the number of users currently waiting for diagnosis, the number of doctors, and the upper limit of each doctor's admissions to determine whether the current Internet medical platform has diagnosis congestion;

[0008] A diagnosis sorting module is used to sort the undiagnosed users when diagnosing congestion;

[0009] The doctor diagnosis module is used to obtain the user's medical record information and the selected condition label input by the doctor, and add the user's medical record information input by the doctor to the user's medical record diagnosis library;

[0010] The medical diagnosis supervision module is used to determine whether the medical diagnosis meets the diagnostic standards based on the patient's medical information and the user's medical record information entered by the doctor, and to reduce the doctor's upper limit on the number of patients he or she can see based on whether the doctor's recent diagnosis meets the diagnostic standards.

[0011] Furthermore, the method for pre-grading the user's condition in the condition pre-grading module is:

[0012] S1. Establish a disease keyword database and establish disease levels corresponding to disease keyword combinations;

[0013] S2, performing word segmentation processing on the medical condition information input by the user;

[0014] S3, extracting the user's disease keywords according to the disease keyword library;

[0015] S4. Determine whether the number of the user's disease keywords is greater than the preset number of disease keywords. If so, determine the user's disease level based on the keywords and output it; if not, the user has no disease level, and send a prompt to the user that there are too few disease description words.

[0016] Furthermore, the specific implementation method of the diagnostic congestion detection module is:

[0017] T1. Obtain the number of undiagnosed patients a, the number of online doctors b, and the upper limit of each doctor’s admissions γ i and the number of patients seen α i , where i is the doctor's number i=1, ..., b;

[0018] T2, preset average diagnosis time

[0019] T3. Calculate the estimated waiting time T of the last user ATE , the calculation method is:

[0020] Where X is a positive integer, which can be obtained by the following formula:

[0021]

[0022] -b <F(X)≤0;

[0023] T4. Determine the estimated waiting time T of the last user ATE Is it greater than the maximum waiting time T? max If it is greater than, it is currently in diagnostic congestion; if it is not greater than, it is not currently in diagnostic congestion.

[0024] Furthermore, the method of diagnosis sorting in the diagnosis sorting module is:

[0025] Z1. Obtain the time when all undiagnosed users input their medical condition information and number the undiagnosed patients according to the time when they input their medical condition information, with the number k=1, ..., K;

[0026] Z2. Substitute the user number k and the user's disease level β into the following formula to obtain the diagnosis ranking parameter I k :

[0027] I k =θ time k+μ(β A -β)

[0028] The user has no disease level, then β=0,θ time is the time coefficient, μ is the disease level coefficient, β A It is the standard disease level;

[0029] Z3, the diagnostic sort parameter I k Sort from small to large, diagnostic sort parameter I k The ranking is the ranking of undiagnosed patients.

[0030] Furthermore, when the user adds condition information by inputting, the condition information added by the user is segmented, the condition keywords added by the user are extracted, the condition level of the user is re-determined, and the diagnosis sorting is performed again.

[0031] Furthermore, the specific supervision method in the disease diagnosis supervision module is:

[0032] The sample disease description words are sent to the natural language model for training, and the expert diagnosis disease label is used as the target condition to obtain a trained natural language model;

[0033] Send the user's medical condition information into the model to obtain the inferred medical condition label;

[0034] Determine whether the inferred condition label and the condition label diagnosed by the doctor are the same. If they are the same, the diagnosis result meets the standard; if they are different, the diagnosis result does not meet the standard;

[0035] Obtain the supervision data of the doctor's recent first supervision quantity, and obtain the diagnosis Ti that meets the standard and the diagnosis F that does not meet the standard i Percentage

[0036] Set the doctor's standard number of patients A, the doctor's maximum number of patients

[0037] Furthermore, when the diagnostic congestion detection module detects that the current Internet medical platform has diagnostic congestion, it will perform diagnostic congestion detection again after a diagnostic interval. If the Internet medical platform has no diagnostic congestion at this time, the user's diagnostic ranking at this time will be maintained, and the user's addition of medical condition information will not change the user's diagnostic ranking. The diagnostic congestion detection module begins to detect in real time whether the Internet medical platform has diagnostic congestion. Subsequent undiagnosed users will be diagnosed and sorted in the order of the time when the medical condition information was input; if the Internet medical platform is still diagnosed and congested at this time, the users will be sorted according to the diagnostic sorting method of the diagnostic sorting module when the diagnostic congestion occurred.

[0038] Furthermore, it also includes a location acquisition module and an emergency rescue module. The location acquisition module is used to obtain the user's current location information, and the emergency rescue module is used to provide emergency rescue to the user. The specific implementation method is:

[0039] An emergency keyword library is set up; the medical condition information input by the user is retrieved, and when the keywords in the emergency keyword library appear in the medical condition information input by the user, communication between the emergency rescue doctor and the user is established, and the user's current location information is obtained.

[0040] This application has the following advantages:

[0041] 1. The present invention adjusts the diagnostic order of patients based on their descriptions on the medical platform, so that patients in need of diagnosis can receive timely online diagnosis, reduce the impact of malicious medical consultation on the Internet on the medical platform, and improve the overall diagnostic efficiency of the Internet medical platform.

[0042] 2. The present invention records the patient's condition information and the medical record information provided by the doctor to determine whether the doctor has made a wrong diagnosis, thereby achieving full-link supervision of the diagnosis on the Internet medical platform and improving the security of the Internet medical platform.

[0043] 3. The present invention sets emergency keywords. When a patient uses a medical platform to input the emergency keywords, the medical platform will trigger an emergency response mode, communicate with the patient and obtain the patient's location information, and provide medical assistance to the patient in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0045] Figure 1A flowchart of a medical record information supervision system of an Internet medical platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, some embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. However, it will be appreciated by those skilled in the art that in the various embodiments of the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented.

[0047] Example 1

[0048] See also Figure 1 , a medical record information supervision system of an Internet medical platform, comprising:

[0049] The medical condition information acquisition module is used to acquire the medical condition information input by the user in real time, and add the medical condition information input by the user to the user's medical record diagnosis library. If the user is making a diagnosis for the first time, a medical record diagnosis library for the user is established. In a specific implementation, the medical condition information input by the user may be text information, picture information, and voice information. When the medical condition information input by the user is not text information, the text in the picture is extracted or the voice is recognized to convert it into text information and then added to the user's medical record diagnosis library. Multiple input methods can be suitable for different groups of people. By establishing the user's medical record diagnosis library, the medical condition can be quickly located when the user consults for the same condition multiple times.

[0050] The condition pre-classification module is used to pre-classify the user's condition according to the condition information input by the user. It should be added that the method for pre-classifying the user's condition in the condition pre-classification module is:

[0051] S1. Establish a disease keyword database and establish disease levels corresponding to disease keyword combinations;

[0052] S2, performing word segmentation processing on the medical condition information input by the user;

[0053] S3, extracting the user's disease keywords according to the disease keyword library;

[0054] S4. Determine whether the number of the user's disease keywords is greater than the preset number of disease keywords. If so, determine the user's disease level based on the keywords and output it; if not, the user has no disease level, and send a prompt to the user that there are too few disease description words.

[0055] The diagnostic congestion detection module is used to obtain the number of users currently waiting for diagnosis, the number of doctors, and the upper limit of each doctor's consultation to determine whether the current Internet medical platform has diagnostic congestion. It should be added that diagnostic congestion means that the current doctors' consultations are relatively saturated. At this time, if malicious users appear to ask questions, it will affect the time of normal users and reduce the efficiency of doctors' consultations.

[0056] The diagnosis sorting module is used to sort the diagnosis of undiagnosed users when there is diagnosis congestion. It should be added that when there is no diagnosis congestion, users are sorted according to the time when their medical information is input, which can reduce the system's resource consumption.

[0057] The doctor diagnosis module is used to obtain the user's medical record information and the selected disease label input by the doctor, and add the user's medical record information input by the doctor to the user's medical record diagnosis library, and classify the disease into different disease labels;

[0058] The medical diagnosis supervision module is used to determine whether the medical diagnosis meets the diagnostic standards based on the patient's medical information and the user's medical record information entered by the doctor, and to reduce the doctor's upper limit on the number of patients he or she can see based on whether the doctor's recent diagnosis meets the diagnostic standards.

[0059] The present invention adjusts the diagnostic order of patients based on their descriptions on the medical platform, so that patients in need of diagnosis can receive timely online diagnosis, reduce the impact of malicious medical inquiries on the Internet on the medical platform, and improve the overall diagnostic efficiency of the Internet medical platform.

[0060] Furthermore, the specific implementation method of the diagnostic congestion detection module is:

[0061] T1. Obtain the number of undiagnosed patients a, the number of online doctors b, and the upper limit of each doctor’s admissions γ i and the number of patients seen α i , where i is the doctor's number i=1, ..., b;

[0062] T2, preset average diagnosis time Average diagnosis time The preset can be done by collecting the historical diagnosis time and taking the average value;

[0063] T3. Calculate the estimated waiting time T of the last user ATE , the calculation method is:

[0064] Where X is a positive integer, which can be obtained by the following formula:

[0065]

[0066] -b <F(X)≤0;

[0067] T4. Determine the estimated waiting time T of the last user ATE Is it greater than the maximum waiting time T? max If it is greater than, it is currently in diagnostic congestion; if it is not greater than, it is not currently in diagnostic congestion.

[0068] It should be added that the diagnostic sorting method in the diagnostic sorting module is:

[0069] Z1. Obtain the time when all undiagnosed users input their medical condition information and number the undiagnosed patients according to the time when they input their medical condition information, with the number k=1, ..., K;

[0070] Z2. Substitute the user number k and the user's disease level β into the following formula to obtain the diagnosis ranking parameter I k :

[0071] I k =θ time k+μ(β A -β)

[0072] The user has no disease level, then β=0,θ time is the time coefficient, μ is the disease level coefficient, β A is the standard disease level. It should be added that the time coefficient θ time and the disease level coefficient μ are artificially set parameters, and the standard disease level β A is the highest disease level corresponding to the disease keyword combination in the disease key library. When the weight of the disease level needs to be strengthened, the disease level coefficient μ can be increased. The time coefficient θ time Same reason.

[0073] Z3, the diagnostic sort parameter I k Sort from small to large, diagnostic sort parameter I k The ranking is the ranking of undiagnosed patients.

[0074] It should be added that when the user adds medical information by inputting, the medical information added by the user is segmented, the medical keywords added by the user are extracted and the user's medical condition level is re-judged, and the diagnosis sorting is performed again. The user can improve the ranking of the diagnosis sorting by adding meaningful medical information. Meaningful means that the added medical information contains medical keywords in the medical keyword library. This method enables the user to actively add medical information that is helpful for diagnosis, thereby improving the doctor's diagnostic accuracy to a certain extent. When it is the doctor's turn to diagnose the user, the user has already entered most of the medical information, saving the doctor's time waiting for the user to enter the medical information during diagnosis, and significantly improving the diagnosis efficiency of the Internet medical platform.

[0075] It should be added that the specific supervision methods in the disease diagnosis supervision module are:

[0076] The sample disease description words are sent to the natural language model for training, and the expert diagnosis disease label is used as the target condition to obtain a trained natural language model;

[0077] Send the user's medical condition information into the model to obtain the inferred medical condition label;

[0078] Determine whether the inferred condition label and the condition label diagnosed by the doctor are the same. If they are the same, the diagnosis result meets the standard; if they are different, the diagnosis result does not meet the standard;

[0079] Obtain the supervision data of the doctor's recent first supervision quantity, and obtain the diagnosis Ti that meets the standard and the diagnosis F that does not meet the standard i Percentage

[0080] Set the doctor's standard number of patients A, the upper limit of the doctor's number of patients

[0081] It should be added that the first supervision number is the number of diagnosis results that the doctor is referenced for. When the doctor's recent first supervision number of diagnosis results all meet the standards, the doctor has no diagnosis upper limit. The diagnosis upper limit changes dynamically based on the doctor's recent diagnosis results. The size of the first supervision number affects the accuracy of the change in the range of the upper limit of consultations.

[0082] The present invention records the patient's condition information and the medical record information provided by the doctor to determine whether the doctor has made a wrong diagnosis, thereby achieving full-link supervision of diagnosis on the Internet medical platform and improving the security of the Internet medical platform.

[0083] It should be added that when the diagnostic congestion detection module detects that the current Internet medical platform has diagnostic congestion, it will perform diagnostic congestion detection again after a diagnostic interval. If the Internet medical platform has no diagnostic congestion at this time, the user's diagnostic ranking at this time will be maintained, and the user's addition of medical condition information will not change the user's diagnostic ranking. The diagnostic congestion detection module begins to detect in real time whether the Internet medical platform has diagnostic congestion. Subsequent undiagnosed users will be sorted in the order of the time when they entered their medical condition information. If the Internet medical platform is still congested at this time, the users will be sorted according to the diagnostic ranking method of the diagnostic ranking module when there is diagnostic congestion.

[0084] Furthermore, it also includes a location acquisition module and an emergency rescue module. The location acquisition module is used to obtain the user's current location information, and the emergency rescue module is used to provide emergency rescue to the user. The specific implementation method is:

[0085] An emergency keyword library is set up; the medical condition information input by the user is retrieved, and when the keywords in the emergency keyword library appear in the medical condition information input by the user, communication between the emergency rescue doctor and the user is established, and the user's current location information is obtained.

[0086] It should be added that, in specific implementations, users can fill in relevant location information in advance, so that when users need emergency assistance, the user's location can be located more accurately and quickly, thereby enhancing the timeliness of assistance.

[0087] The present invention sets emergency keywords. When a patient uses a medical platform to input the emergency keywords, the medical platform will trigger an emergency response mode, communicate with the patient and obtain the patient's location information, so as to provide medical assistance to the patient in a timely manner.

[0088] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the claims attached to this application. Parts not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. A medical record information supervision system for an Internet medical platform, characterized in that: include: The medical condition information acquisition module is used to acquire the medical condition information input by the user in real time, add the medical condition information input by the user to the medical diagnosis database of the user, and establish the medical diagnosis database of the user if the user is undergoing diagnosis for the first time; A condition pre-classification module is used to pre-classify the user's condition based on the condition information input by the user; The diagnosis congestion detection module is used to obtain the number of users currently waiting for diagnosis, the number of doctors, and the upper limit of each doctor's admissions to determine whether the current Internet medical platform has diagnosis congestion; A diagnosis sorting module is used to sort the undiagnosed users when diagnosing congestion; The doctor diagnosis module is used to obtain the user's medical record information and the selected condition label input by the doctor, and add the user's medical record information input by the doctor to the user's medical record diagnosis library; The medical diagnosis supervision module is used to determine whether the medical diagnosis meets the diagnostic standards based on the patient's medical information and the user's medical record information entered by the doctor, and to reduce the doctor's upper limit on the number of patients he or she can see based on whether the doctor's recent diagnosis meets the diagnostic standards.

2. The medical record information supervision system of an Internet medical platform as claimed in claim 1, characterized in that: The method for pre-grading the user's condition in the condition pre-grading module is: S1. Establish a disease keyword database and establish disease levels corresponding to disease keyword combinations; S2, performing word segmentation processing on the medical condition information input by the user; S3, extracting the user's disease keywords according to the disease keyword library; S4, determining whether the user's condition keywords are greater than the preset number of condition keywords, if greater, determining the user's condition level based on the keywords and outputting the result; If it is not greater, the user has no disease level, and a prompt will be sent to the user that there are too few disease description words.

3. The medical record information supervision system of an Internet medical platform as claimed in claim 2, characterized in that: The specific implementation method of the diagnostic congestion detection module is: T1. Get the number of undiagnosed patients a, the number of online doctors b, and the upper limit of each doctor’s admissions γ i and the number of patients seen α i , where i is the doctor's number i=1, ..., b; T2, preset average diagnosis time T3. Calculate the estimated waiting time T of the last user ATE , the calculation method is: Where X is a positive integer, which can be obtained by the following formula: -b <F(X)≤0; T4. Determine the estimated waiting time T of the last user ATE Is it greater than the maximum waiting time T? max If it is greater than, it is currently in diagnostic congestion; if it is not greater than, it is not currently in diagnostic congestion.

4. The medical record information supervision system of an Internet medical platform as claimed in claim 3, characterized in that: The diagnostic sorting method in the diagnostic sorting module is: Z1. Obtain the time when all undiagnosed users input their medical condition information and number the undiagnosed patients according to the time when they input their medical condition information, with the number k=1, ..., K; Z2. Substitute the user number k and the user's disease level β into the following formula to obtain the diagnosis ranking parameter I k : I k =θ time k+μ(β A -b) The user has no disease level, then β=0,θ time is the time coefficient, μ is the disease level coefficient, β A It is the standard disease level; Z3, the diagnostic sort parameter I k Sort from small to large, diagnostic sort parameter I k The ranking is the ranking of undiagnosed patients.

5. The medical record information supervision system of an Internet medical platform as claimed in claim 4, characterized in that: When the user adds condition information by inputting, the condition information added by the user is segmented, the condition keywords added by the user are extracted, the condition level of the user is re-determined, and the diagnosis sorting is performed again.

6. The medical record information supervision system of an Internet medical platform as claimed in claim 5, characterized in that: The specific supervision methods in the disease diagnosis supervision module are: The sample disease description words are sent to the natural language model for training, and the expert diagnosis disease label is used as the target condition to obtain a trained natural language model; Send the user's medical condition information into the trained natural language model to obtain the inferred medical condition label; Determine whether the inferred condition label and the condition label diagnosed by the doctor are the same. If they are the same, the diagnosis result meets the standard; if they are different, the diagnosis result does not meet the standard; Obtain the doctor's recent first supervision data and obtain the diagnosis T that meets the standard i F i Percentage Set the doctor's standard number of patients A, the upper limit of the doctor's number of patients 7. The medical record information supervision system of an Internet medical platform as claimed in claim 6, characterized in that: When the diagnosis congestion detection module detects that the current Internet medical platform has diagnosis congestion, it will perform diagnosis congestion detection again after a diagnosis interval. If the Internet medical platform has no diagnosis congestion at this time, the diagnosis order of the user at this time will be maintained, and the user's addition of medical condition information will not change the user's diagnosis order. The diagnosis congestion detection module begins to detect in real time whether the Internet medical platform has diagnosis congestion. Subsequent undiagnosed users will be diagnosed and sorted in the order of the time when the medical condition information was input; if the Internet medical platform is still diagnosed and congested at this time, the users will be sorted according to the diagnosis sorting method when the diagnosis sorting module has diagnosis congestion.

8. The medical record information supervision system of an Internet medical platform as claimed in claim 7, characterized in that: It also includes a location acquisition module and an emergency rescue module. The location acquisition module is used to obtain the user's current location information, and the emergency rescue module is used to provide emergency rescue to the user. The specific implementation method is: An emergency keyword library is set up; the medical condition information input by the user is retrieved, and when the keywords in the emergency keyword library appear in the medical condition information input by the user, communication between the emergency rescue doctor and the user is established, and the user's current location information is obtained.

Images