Medical supervision platform

Abstract

The invention provides a medical supervision platform. A patient personal information base and a pathology big database are established; the doctor inquires the patient according to the information of the patient information base and makes corresponding diagnosis; the supervision module compares and checks the diagnosis content of the proofreading doctor through big data; after checking, doctor diagnosis is input into a patient information base, and corresponding medical resources are allocated; the patient personal information base comprises basic information of patients, past medical history, medicine allergy history, examination results and uncomfortable symptoms, the pathology big database comprises disease names, disease indications, medicine principles and treatment modes, the platform can improve the accuracy and rationality of medical diagnosis, and by checking a medicine treatment scheme of a doctor, the medical diagnosis accuracy and rationality can be improved. And the treatment mode, the medicine type and the dosage are ensured to meet medical standards and patient requirements. The proofreading steps are helpful for reducing the risk of drug treatment and improving the treatment effect of patients.

Description

Technical Field

[0001] This invention proposes a medical monitoring platform, which belongs to the field of medical technology. Background Technology

[0002] A healthcare oversight platform is an information technology system used to manage and monitor healthcare processes, improving healthcare quality and safety. This platform can integrate multiple healthcare information sources, including patient records, physician diagnoses, drug information, and pathology data, to achieve better healthcare management and decision-making.

[0003] Chinese Patent Publication No. CN111145844B discloses an integrated medical supervision platform, comprising a supervision server and a supervision terminal. The supervision server includes: a patient data acquisition module for acquiring patient medical data; a hospital data acquisition module for acquiring hospital medical data; a pharmacy data acquisition module for acquiring pharmacy sales data; a database for storing patient medical data, hospital medical data, and pharmacy sales data; and a data integration and analysis module for integrating and statistically analyzing patient medical data, hospital medical data, and pharmacy sales data to generate statistical reports. This integrated medical supervision platform can collect and monitor data from multiple stakeholders, including patients, drug distributors, manufacturers, and hospitals, making supervision more comprehensive, providing data support for regulatory authorities, and enabling more scientific decision-making.

[0004] Existing medical supervision platforms can only supervise physical objects such as medical devices and medicines. However, when patients in hospitals have difficulty expressing themselves, doctors cannot fully understand the patient's past medical history. Doctors' manual diagnosis is also prone to oversights or omissions, which can delay diagnosis and treatment. Summary of the Invention

[0005] This invention provides a medical supervision platform, including the establishment of a patient personal information database and a pathology database;

[0006] Physicians conduct patient interviews and prescribe corresponding diagnoses based on information from the patient database;

[0007] The monitoring module verifies doctors' diagnoses using big data comparison.

[0008] After verification, the doctor's diagnosis is entered into the patient's information database and the corresponding medical resources are allocated.

[0009] Specifically, by establishing a patient information database and a large pathology database, doctors can obtain useful reference information. During consultations, doctors can access the patient information database to understand the patient's medical history and personal information. Doctors prescribe corresponding diagnoses based on the patient's symptoms and medical history. The monitoring module uses big data to compare and verify the doctor's diagnoses. It can check whether the doctor's diagnosis matches the information in the pathology database to reduce diagnostic errors. If the monitoring module finds problems with the doctor's diagnosis, the doctor needs to verify and correct it. Once the diagnosis is confirmed, it can be entered into the patient information database for future reference. The platform can automatically allocate medical resources, such as surgery time, bed, and medication, based on the diagnosis results and the patient's needs to ensure that the patient receives timely treatment.

[0010] Furthermore, the patient personal information database includes basic patient information, past medical history, drug allergy history, examination results, and symptoms, while the pathology database includes disease names, disease indications, drug mechanisms, and treatment methods.

[0011] Specifically, the use of patient information databases and pathology databases can reduce medical errors caused by incomplete or incorrect information. Patients can manually enter basic information during hospital consultations via mobile devices or the hospital's system, creating a personal information database and generating a personal electronic medical record. Corresponding hospital test results are automatically synchronized to this database. Doctors can more easily access and verify patient information based on this database, reducing the risk of missed or misdiagnosed diagnoses and improving medical efficiency. The database can accelerate medical processes, enabling doctors to make decisions and diagnoses more quickly. It can also automate processes such as medical resource allocation, thereby improving the effective use of medical resources. Patients can access their own information, understand their health status, and participate more actively in medical decision-making and self-management.

[0012] Furthermore, the doctor's diagnosis includes extracting pathological features directly related to the disease diagnosis based on the test results and symptoms in the patient's personal information database, making a corresponding disease diagnosis based on the pathological features, and making a corresponding treatment diagnosis based on the results of the disease diagnosis.

[0013] Furthermore, treatment diagnosis includes the treatment method, type of drug, and dosage.

[0014] Specifically, doctors extract relevant pathological features based on the patient's symptoms in the patient's information database, combined with the patient's test results and past medical history. Based on these pathological features, doctors make a corresponding disease diagnosis, which is the specific name of the disease. At the same time, doctors make corresponding treatment decisions based on the disease diagnosis, and different treatment methods are used for different diseases.

[0015] Furthermore, the monitoring module includes feature data collection, disease verification, and drug verification. Feature data collection includes extracting relevant feature data from doctors' diagnoses. Disease verification includes checking whether the corresponding disease name is correct based on the feature data. Drug verification will check whether there is a correlation between the drug and the disease and the drug's safety.

[0016] The characteristic data includes the patient's pathological characteristics, the name of the diagnosed disease, the treatment method, the type of treatment drug, and the dosage of the treatment drug.

[0017] Specifically, by setting up a monitoring module to verify doctors' diagnoses, this includes extracting data from the diagnoses and verifying the accuracy of the disease names and the rationality of drug use based on the extracted data, thereby reducing medical errors and improving patients' treatment outcomes.

[0018] Furthermore, the disease verification includes retrieving corresponding disease pathological feature data from the disease database based on the name of the disease diagnosed by the doctor, comparing the patient's pathological features in the doctor's diagnosis and extracting duplicate items A, and calculating whether the disease diagnosis is correct based on the disease verification algorithm.

[0019] Furthermore, the duplicate term A is denoted as A(x, y), and the disease correction algorithm is specifically as follows:

[0020] I = Σ i＝1 n (x i *y i ),

[0021] Where n is the number of duplicate terms A, x is the eigenvalue of duplicate term A, and y is the significance value of duplicate term A.

[0022] If I > Z, the diagnosis is correct; if the placement is incorrect, manual intervention is required for re-diagnosis.

[0023] Furthermore, Z is the diagnostic threshold, which can be adjusted according to actual data needs. x represents the characteristic value, which is proportional to the importance of the disease characteristic. If the disease characteristic is a significant indicator corresponding to the basic level, its characteristic value is higher, and vice versa. y represents the significance value of the duplicate item, which is positively correlated with the proportion of times the duplicate item appears in the basic patients.

[0024] Specifically, the method compares a doctor's diagnosis with the disease database and uses a verification algorithm to evaluate the accuracy of the diagnosis. If the verification algorithm's result exceeds a set threshold, the diagnosis is considered correct. Otherwise, further human intervention and re-diagnosis are required. This method allows for personalized diagnostic verification based on the importance of different diseases and characteristics. This can improve the diagnostic accuracy for specific patients' conditions, and by setting appropriate verification algorithms and thresholds, the misdiagnosis rate can be effectively reduced, especially for diseases requiring highly accurate diagnosis.

[0025] Furthermore, the drug calibration includes method calibration, type calibration, and dosage verification. Method calibration involves querying the corresponding treatment method in the disease database by looking up the disease name in the doctor's diagnosis and comparing it with the doctor's diagnosis. If they are the same, the verification is successful; otherwise, the doctor needs to intervene to re-diagnose or supplement the diagnosis results.

[0026] The specific treatment methods are divided into medication and surgery. Among them, surgical procedures have corresponding surgical indicators in the existing disease database, which helps to distinguish the methods of verification.

[0027] Furthermore, the category verification includes extracting all drug types from the doctor's diagnosis, which is a sequence z, and recording the available drug types corresponding to the disease name in the doctor's diagnosis as a sequence k. If the sequence z is completely contained in the sequence k and does not overlap with the patient's drug allergy history, the category verification will pass; otherwise, the verification will fail.

[0028] Furthermore, the dosage verification includes extracting the dosage of each drug in the doctor's diagnosis and determining whether the dosage is within a reasonable range based on the drug's pharmacological instructions. If it is, the dosage verification is passed.

[0029] The effects of the aforementioned technical solution are as follows: the medical monitoring platform helps improve the consistency and quality of medical services, reduces errors and missed diagnoses caused by human factors, and provides better data support to help doctors make more accurate diagnostic and treatment decisions. Furthermore, it can improve the effective utilization of medical resources and ensure that patients can receive appropriate medical services in a timely manner. Attached Figure Description

[0030] Figure 1 This is a schematic diagram illustrating the principle of a medical monitoring platform as described in this invention. Detailed Implementation

[0031] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0032] One embodiment of the present invention is a medical supervision platform, which includes establishing a patient personal information database and a pathology database;

[0033] Physicians conduct patient interviews and prescribe corresponding diagnoses based on information from the patient database;

[0034] The monitoring module verifies doctors' diagnoses using big data comparison.

[0035] After verification, the doctor's diagnosis is entered into the patient's information database and the corresponding medical resources are allocated.

[0036] The working principle of the above technical solution is as follows: By establishing a patient information database and a large pathology database, doctors can obtain useful reference information. Patients and doctors conduct consultations, and doctors can access the patient information database to understand the patient's medical history and personal information. Doctors prescribe corresponding diagnoses based on the patient's symptoms and medical history. The monitoring module uses big data to compare and verify the doctor's diagnosis. It can check whether the doctor's diagnosis matches the information in the large pathology database to reduce diagnostic errors. If the monitoring module finds a problem with the doctor's diagnosis, the doctor needs to verify and correct it. Once the diagnosis is confirmed, it can be entered into the patient information database for future reference. The platform can automatically allocate medical resources, such as surgery time, bed, and medication, based on the diagnosis results and the patient's needs to ensure that the patient receives timely treatment.

[0037] The effects of the aforementioned technical solution are as follows: the medical monitoring platform helps improve the consistency and quality of medical services, reduces errors and missed diagnoses caused by human factors, and provides better data support to help doctors make more accurate diagnostic and treatment decisions. Furthermore, it can improve the effective utilization of medical resources and ensure that patients can receive appropriate medical services in a timely manner.

[0038] In one embodiment of the present invention, the patient personal information database includes the patient's basic information, past medical history, drug allergy history, examination results and symptoms, and the pathology database includes disease name, disease indications, drug mechanism and treatment method.

[0039] The working principle of the above technical solution is as follows: the use of patient information databases and pathology databases can reduce medical errors caused by incomplete or incorrect information. When patients consult doctors at the hospital, they can manually enter relevant basic information on mobile devices or at the hospital to establish a personal information database and generate personal electronic files. Corresponding hospital test results are automatically synchronized to the personal information database. Doctors can more easily obtain and verify patient information based on the patient's personal information database, reducing the risk of missed diagnoses and misdiagnoses, and improving medical efficiency. The database can accelerate medical processes, enabling doctors to make decisions and diagnoses more quickly. It can also automate some processes, such as the allocation of medical resources, thereby improving the effective use of medical resources. Patients can access their own information, understand their health status, and participate more actively in medical decision-making and self-management.

[0040] The effects of the aforementioned technical solutions are as follows: patient information databases and large-scale pathology databases help improve the quality of medical care and increase medical efficiency, while also supporting medical research and health policy development. The establishment and management of these databases are crucial for modern healthcare systems, enabling them to provide better services and support to patients and medical professionals.

[0041] In one embodiment of the present invention, the doctor's diagnosis includes extracting pathological features directly related to the disease diagnosis based on the test results and symptoms in the patient's personal information database, making a corresponding disease diagnosis based on the pathological features, and making a corresponding treatment diagnosis based on the results of the disease diagnosis.

[0042] Furthermore, treatment diagnosis includes the treatment method, type of drug, and dosage.

[0043] The working principle of the above technical solution is as follows: Doctors extract corresponding pathological features based on the patient's symptoms in the patient's information database, combined with the patient's test results and past medical history, and make a corresponding disease diagnosis based on the pathological features. The disease diagnosis is specifically the corresponding name of the disease. At the same time, corresponding treatment diagnoses are made based on the disease diagnosis, and different treatment methods are made according to different diseases.

[0044] The benefits of the aforementioned technical solution are as follows: This process helps doctors combine a patient's personal information with pathological characteristics to develop an accurate diagnosis and corresponding treatment plan. By comprehensively considering the patient's medical history, symptoms, test results, and pathological characteristics, doctors can better meet the patient's medical needs. Furthermore, this method helps reduce medical misdiagnosis and missed diagnosis, improving the quality of medical services.

[0045] In one embodiment of the present invention, the monitoring module includes feature data collection, disease verification, and drug verification. Feature data collection includes extracting relevant feature data from doctors' diagnoses. Disease verification includes checking whether the corresponding disease name is correct based on the feature data. Drug verification will check whether there is a correlation between the drug and the disease and the drug's safety.

[0046] The characteristic data includes the patient's pathological characteristics, the name of the diagnosed disease, the treatment method, the type of treatment drug, and the dosage of the treatment drug.

[0047] The working principle of the above technical solution is as follows: by setting up a monitoring module to verify the doctor's diagnosis, including extracting data from the diagnosis content, and verifying the correctness of the disease name diagnosis and the rationality of the drug use based on the extracted content, thereby reducing medical errors and improving the patient's treatment effect.

[0048] The effects of the aforementioned technical solution are as follows: the monitoring module helps improve the accuracy and consistency of medical diagnoses, reduces medical errors, and ensures that patients receive safe and effective treatment. Especially in large-scale healthcare services, such a module can help ensure consistency in medical standards and improve the quality of patient care.

[0049] In one embodiment of the present invention, the disease verification includes retrieving corresponding disease pathological feature data from the disease database based on the name of the disease diagnosed by the doctor, comparing the patient pathological features in the doctor's diagnosis and extracting duplicate items A, and calculating whether the disease diagnosis is correct based on the disease verification algorithm.

[0050] In one embodiment of the present invention, the duplicate item A is denoted as A(x, y), and the disease correction algorithm is specifically as follows:

[0051] I = Σ i＝1 n (x i *y i ),

[0052] Where n is the number of duplicate terms A, x is the eigenvalue of duplicate term A, and y is the significance value of duplicate term A.

[0053] If I > Z, the diagnosis is correct; if the placement is incorrect, manual intervention is required for re-diagnosis.

[0054] Furthermore, Z is the diagnostic threshold, which can be adjusted according to actual data needs. x represents the characteristic value, which is proportional to the importance of the disease characteristic. If the disease characteristic is a significant indicator corresponding to the basic level, its characteristic value is higher, and vice versa. y represents the significance value of the duplicate item, which is positively correlated with the proportion of times the duplicate item appears in the basic patients.

[0055] The working principle of the above technical solution is as follows: It compares the doctor's diagnosis with the content of a disease database and uses a verification algorithm to evaluate the accuracy of the diagnosis. If the result of the verification algorithm exceeds a set threshold, the diagnosis is considered correct. Otherwise, further human intervention and re-diagnosis are required. This method allows for personalized diagnostic verification based on the importance of different diseases and characteristics. This can improve the diagnostic accuracy for specific patients' conditions. By setting appropriate verification algorithms and thresholds, the misdiagnosis rate can be effectively reduced, especially for diseases requiring highly accurate diagnosis.

[0056] In one embodiment of the present invention, suppose patient 1 comes for consultation. During the consultation, the doctor makes a preliminary diagnosis of a certain disease R based on the patient's symptoms and examination results. The patient's pathological characteristics are compared with those in the doctor's diagnosis and duplicate items A are extracted, namely fever, headache, and rash.

[0057] The characteristic values ​​of the repeated term A are: fever (x1 = 1), headache (x2 = 0.8), and rash (x3 = 0.5). These characteristic values ​​represent the degree of presence of pathological features. For example, fever is a typical symptom, so the value is relatively high; headache is relatively common but not specific, so the value is slightly lower; and rash is a less common symptom, so the value is even lower.

[0058] The significance values ​​of the duplicate term A were: fever (y1 = 0.9), headache (y2 = 0.2), and rash (y3 = 0.7).

[0059] These eigenvalues ​​represent the significance of pathological features in disease R. For example, fever is a typical symptom, so the value is high; headache is relatively common but not specific, so the value is slightly low; and rash is a less common symptom, so the value is even lower.

[0060] The patient's calibration value was calculated as follows: I = I = Σ(xi*yi) = (1*0.9) + (0.8*0.2) + (0.5*0.7) = 0.9 + 0.16 + 0.35 = 1.41;

[0061] Next, we need to determine a threshold Z, which is derived from historical data and statistical analysis, to determine the degree of matching between pathological features and disease diagnosis.

[0062] If I is greater than Z, the diagnosis is considered correct; if I is less than or equal to Z, the diagnosis is considered incorrect and requires manual intervention for re-diagnosis.

[0063] In this example, let's assume the threshold Z is set to 1.2. Since our calculated I value is 1.41, which exceeds the threshold Z, the original diagnosis (disease R) is considered correct according to this algorithm.

[0064] In one embodiment of the present invention, the drug calibration includes method calibration, type calibration and dosage verification. The method calibration involves querying the corresponding treatment method in the disease database by the disease name in the doctor's diagnosis and comparing it with the doctor's diagnosis. If they are the same, the verification is successful; otherwise, the doctor needs to intervene to re-diagnose or supplement the diagnosis results.

[0065] The specific treatment methods are divided into medication and surgery. Among them, surgical procedures have corresponding surgical indicators in the existing disease database, which helps to distinguish the methods of verification.

[0066] In one embodiment of the present invention, the category verification includes extracting all drug types from the doctor's diagnosis, which is a sequence z, and recording the available drug types corresponding to the disease name in the doctor's diagnosis as a sequence k. If the sequence z is entirely contained in the sequence k and does not overlap with the patient's drug allergy history, the category verification is passed; otherwise, the verification fails.

[0067] The specific steps are as follows: Extracting drug type information: First, it is necessary to extract all drug types from the doctor's diagnosis. These drug types form a sequence z. This includes the generic name or brand name of each drug.

[0068] To obtain disease-related drug types: In order to perform type verification, it is necessary to determine the name of the disease diagnosed by the doctor and query the available drug types related to that disease. These available drug types form a sequence k.

[0069] Medication type verification: This involves comparing the sequence z (all medications diagnosed by the doctor) and the sequence k (available medications related to the disease). If all medications in sequence z are included in sequence k and do not overlap with the patient's drug allergy history, then the type verification passes. This means the medications prescribed by the doctor are relevant to the patient's disease, will not trigger an allergic reaction, and are appropriate.

[0070] Handling discrepancies: If mismatches or duplicate medications are found during the verification process, action needs to be taken. This may include consulting with the doctor, reassessing the patient's condition or drug allergy history to determine the correct medication.

[0071] Special considerations: In some cases, patients may have a specific history of allergies or contraindications to certain medications. These factors need to be carefully considered to ensure patient safety.

[0072] In one embodiment of the present invention, the dosage verification includes extracting the dosage of each drug in the doctor's diagnosis and determining whether the dosage is within a reasonable range based on the drug's pharmacological instructions. If it is, the dosage verification is passed.

[0073] The specific steps are as follows: Extracting dosage information: First, it is necessary to extract the dosage information for each medication in the doctor's diagnosis. This includes the dosage unit (e.g., milligrams, milliliters, units, etc.) and the specific dosage value for each drug.

[0074] Refer to the drug's pharmacological instructions: These instructions provide guidelines for the drug's use and dosage, and are typically included in the drug's package insert or information sheet. Healthcare professionals should carefully study these instructions to understand the recommended dosage range, usage, and frequency of the drug.

[0075] Determining the appropriate dosage: Based on the drug's pharmacological instructions, healthcare professionals can determine the appropriate dosage range for a drug. This range is typically based on factors such as the patient's age, weight, gender, and condition. The appropriate dosage should ensure that the patient receives sufficient medication to treat their condition without causing adverse reactions or toxicity.

[0076] Dosage Comparison: The dosage extracted from the doctor's diagnosis is compared with the reasonable value. If the dosage in the doctor's diagnosis is within the reasonable range, the dosage verification is successful.

[0077] Special considerations: Some special cases may require extra caution, such as children, the elderly, pregnant women, or patients with specific medical conditions. For these patients, dosage selection may need to be more careful.

[0078] Double checking: In a healthcare setting, double checking is a common practice, especially when it comes to the dosage of high-risk medications. Two healthcare professionals independently check the medication dosage to ensure accuracy.

[0079] The above scheme works as follows: It queries a disease database using the disease name in the doctor's diagnosis to find the corresponding treatment. Then, it compares the found treatment with the doctor's diagnosis. If the found treatment matches the doctor's diagnosis, the method verification passes. Otherwise, the doctor needs to intervene to re-diagnose or provide supplementary diagnostic results. This verification step helps ensure that the doctor's chosen treatment meets the standards and matches the disease name. It involves extracting all drug types from the doctor's diagnosis, forming a sequence z, and then forming a sequence k of available drug types corresponding to the disease name in the doctor's diagnosis. In the type verification, if all drug types in sequence z are included in sequence k and do not overlap with the patient's drug allergy history, then the type verification passes. If there is a mismatch or overlap, the verification fails. This step helps ensure that the types of medications prescribed by the doctor are appropriate and will not trigger allergic reactions. Dosage verification involves extracting the dosage of each drug in the doctor's diagnosis and determining whether the dosage is within a reasonable range based on the drug's pharmacological instructions. If the dosage is within the reasonable range and the dosage verification is passed, this helps to ensure that the medication dosage received by the patient is safe and effective.

[0080] The effects of the above technical solutions are: increasing the accuracy and rationality of medical diagnoses; and ensuring that treatment methods, drug types, and dosages conform to medical standards and patient needs by verifying doctors' drug treatment plans. These verification steps help reduce the risks of drug treatment and improve patient treatment outcomes.

[0081] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A medical supervision platform, characterized in that, This includes establishing a patient personal information database and a large pathology database; Physicians conduct patient interviews and prescribe corresponding diagnoses based on information from the patient database; The monitoring module verifies doctors' diagnoses using big data comparison. After verification, the doctor's diagnosis is entered into the patient's information database and the corresponding medical resources are allocated.

2. A medical supervision platform according to claim 1, characterized in that, The patient information database includes basic patient information, past medical history, drug allergy history, examination results, and symptoms. The pathology database includes disease names, disease indications, drug mechanisms, and treatment methods.

3. The medical supervision platform according to claim 1, characterized in that, The doctor's diagnosis includes extracting pathological features directly related to the disease diagnosis based on the test results and symptoms in the patient's personal information database, making a corresponding disease diagnosis based on the pathological features, and making a corresponding treatment diagnosis based on the results of the disease diagnosis.

4. A medical supervision platform according to claim 1, characterized in that, The monitoring module includes feature data collection, disease verification, and drug verification. Feature data collection includes extracting relevant feature data from doctors' diagnoses. Disease verification includes checking whether the corresponding disease name is correct based on the feature data. Drug verification will check whether there is a correlation between the drug and the disease and the drug's safety. The feature data includes the patient's pathological characteristics, the name of the diagnosed disease, the treatment method, the type of treatment drug, and the dosage of the treatment drug.

5. A medical supervision platform according to claim 4, characterized in that, The disease verification process includes retrieving corresponding disease pathological feature data from the disease database based on the doctor's diagnosed disease name as an index, comparing the patient's pathological features with those in the doctor's diagnosis and extracting duplicate items A, and calculating whether the disease diagnosis is correct based on the disease verification algorithm.

6. A medical supervision platform according to claim 5, characterized in that, The duplicate term A is denoted as A(x, y), and the disease correction algorithm is specifically as follows: I=S i＝1 n (x i *y i ), Where n is the number of duplicate terms A, x is the eigenvalue of duplicate term A, and y is the significance value of duplicate term A. If I > Z, the diagnosis is correct; if the placement is incorrect, manual intervention is required for re-diagnosis.

7. A medical supervision platform according to claim 6, characterized in that, The drug calibration includes method calibration, type calibration and dosage verification. Method calibration involves querying the corresponding treatment method in the disease database by looking up the disease name in the doctor's diagnosis and comparing it with the doctor's diagnosis. If they are the same, the verification is successful; otherwise, the doctor needs to intervene to re-diagnose or supplement the diagnosis results.

8. A medical supervision platform according to claim 6, characterized in that, The category verification includes extracting all drug types from the doctor's diagnosis, which is a sequence z, and recording the available drug types corresponding to the disease name in the doctor's diagnosis as a sequence k. If the sequence z is completely contained in the sequence k and does not overlap with the patient's drug allergy history, the category verification will pass; otherwise, the verification will fail.

9. A medical supervision platform according to claim 8, characterized in that, The dosage verification includes extracting the dosage of each drug in the doctor's diagnosis and determining whether the dosage is within the reasonable range based on the drug's pharmacological instructions. If it is, the dosage verification is passed.

Images