Patient labeling method, device, equipment and storage medium based on hierarchical calculation
By adopting a hierarchical calculation method on the smart medical platform, combining high-risk diagnostic tags, drug tags and medical treatment times, multi-dimensional identification and labeling is solved, the platform's incomplete and accurate identification when distinguishing the risk level of hypertensive patients is solved. The problem of low rate achieves more accurate risk level identification.
Patent Information
- Application Number
- CN202111017493.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-31
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2041-08-31
AI Technical Summary
Smart medical platforms only rely on the blood pressure index when distinguishing the risk levels of hypertensive patients, resulting in insufficient comprehensive identification of risk levels and low marking accuracy.
A high-risk diagnostic tag and drug tag were obtained based on stratification calculations. Multi-dimensional identification and labeling were performed by calculating the average historical drug type values of multiple samples of patients, combining the number of medical treatments and the drug type thresholds associated with the attribute interval.
It improves the comprehensive identification of patient risk levels and marking accuracy, allowing smart medical platforms to more accurately distinguish high-risk and medium-risk patients.
Smart Images

Figure CN113643776B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of smart medical technology, and in particular to a patient labeling method, device, equipment and storage medium based on hierarchical computing. Background Art
[0002] With the continuous progress of society and the continuous development of smart medical technology, people are more and more concerned about their own health problems. Many hospitals and institutions will mark patients for risk, so as to provide patients with disease treatment, product recommendations and other services. Taking hypertension as an example, the purpose of marking hypertensive patients is to distinguish the risk levels of different hypertensive patients, supplement the hypertension risk labels, and enable the smart medical platform to analyze hypertensive patients with different risk levels, so as to provide disease treatment, product recommendations and other services for patients with different risk levels in the future.
[0003] In the related technology, many smart medical platforms need to obtain the index thresholds for high-risk hypertensive patients in the medical guidelines when marking hypertensive patients, and set the preset conditions for screening hypertensive patients according to the index thresholds. If the systolic blood pressure of a hypertensive patient is greater than 160 mmHg, or the diastolic blood pressure is greater than 100 mmHg, it will be determined as high risk and marked. If it does not belong to the above situation, it is a low-risk hypertensive patient and marked.
[0004] In the process of implementing the present invention, the inventors found that the related technology has at least the following technical problems:
[0005] When distinguishing the risk levels of hypertensive patients, the smart medical platform only uses the known blood pressure index for rough distinction, which means that some hypertensive patients may be in a high-risk state, but are classified as low-risk patients because they do not meet the high-risk conditions set for hypertension in medicine. This leads to incomplete risk level identification and low marking accuracy. Summary of the invention
[0006] In view of this, the present application provides a patient marking method, device, equipment and storage medium based on hierarchical calculation, the main purpose of which is to solve the current problems of incomplete risk level identification and low marking accuracy.
[0007] According to the first aspect of the present application, a patient marking method based on hierarchical calculation is provided, the method comprising:
[0008] Obtaining a high-risk diagnosis label, a high-risk drug label, and a drug type threshold, wherein the high-risk diagnosis label and the high-risk drug label are obtained in a medical guideline and are associated with the target disease, and the first drug type threshold is obtained by calculating the type average of historical drug types of multiple sample patients, and the multiple sample patients are marked as high risk;
[0009] Determine a target patient among the patients to be marked with a target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold, wherein the target patient is a patient among the patients to be marked who does not hit the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold of the target disease;
[0010] Obtain a threshold value for the number of medical visits, and count the number of historical medical visits of the target patient;
[0011] When the number of historical medical visits is less than the medical visit threshold, determining the attribute interval hit by the age information and gender information of the target patient, and querying the second drug category threshold associated with the attribute interval;
[0012] If the query determines that the attribute interval has the second drug type threshold associated therewith, counting the types of drugs used by the target patient;
[0013] When the type of used drugs is greater than the second drug type threshold, the target patient is marked as high risk.
[0014] Optionally, determining a target patient from among the patients to be labeled for the target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold comprises:
[0015] Acquire the patients to be marked, filter the patients to be marked whose disease information is associated with the high-risk diagnosis label among the patients to be marked, and mark the filtered patients to be marked as high-risk;
[0016] Filtering the patients to be marked whose drug information is associated with the high-risk drug label among the filtered patients to be marked, and marking the filtered patients to be marked as high risk;
[0017] Counting the types of drugs used by the patients to be marked after filtering, filtering the patients to be marked whose types of drugs used are greater than the first drug type number threshold, and marking the filtered patients to be marked as high risk;
[0018] The remaining patients to be marked after filtering are regarded as the target patients.
[0019] Optionally, the obtaining of the threshold of the number of medical visits includes:
[0020] Determine a plurality of sample patients, query a risk label of the target disease associated with each sample patient in the plurality of sample patients, wherein the risk label is high risk or medium-low risk;
[0021] Grouping the multiple sample patients according to the risk labels, and grouping the sample patients with the same risk labels into the same group to obtain two sample patient groups;
[0022] For each of the two sample patient groups, counting the number of historical medical visits of each sample patient included in the sample patient group as the number of sample medical visits;
[0023] Based on the sample medical visits included in each sample patient group, the average medical visits of each sample patient group is calculated to obtain two average medical visits;
[0024] The two average times of medical treatment are processed by quartile method to obtain the median of the two average times of medical treatment, and the median is used as the threshold of the times of medical treatment.
[0025] Optionally, the method further comprises:
[0026] When the number of historical medical visits is greater than or equal to the medical visit number threshold, querying a third drug category threshold according to the basic information of the target patient;
[0027] When the query of the third drug type threshold is successful, comparing the drug type used by the target patient with the third drug type threshold, and marking the target patient according to the comparison result;
[0028] When the third drug category threshold query fails, the target patient is marked as medium-low risk.
[0029] Optionally, comparing the type of drug used by the target patient with the third drug type threshold, and marking the target patient according to the comparison result, includes:
[0030] When the comparison result indicates that the type of drugs used by the target patient is greater than the third drug type threshold, marking the target patient as high risk;
[0031] When the comparison result indicates that the type of drug used by the target patient is less than or equal to the third drug type threshold, the target patient is marked as medium-low risk.
[0032] Optionally, after determining the attribute interval hit by the age information and gender information of the target patient and querying the second drug category threshold associated with the attribute interval, the method further includes:
[0033] If the query determines that the attribute interval does not have an associated second drug category threshold, the target patient is marked as high risk.
[0034] Optionally, the method further comprises:
[0035] When the type of used drugs is less than or equal to the second drug type threshold, the target patient is marked as medium-low risk.
[0036] According to a second aspect of the present application, a patient marking device based on hierarchical calculation is provided, the device comprising:
[0037] A first acquisition module is used to acquire a high-risk diagnosis label, a high-risk drug label, and a drug type threshold, wherein the high-risk diagnosis label and the high-risk drug label are acquired in a medical guide and are associated with the target disease, and the first drug type threshold is obtained by calculating the type average of historical drug types of multiple sample patients, and the multiple sample patients are marked as high risk;
[0038] a determination module, configured to determine a target patient among the patients to be marked with a target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold, wherein the target patient is a patient among the patients to be marked who does not hit the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold of the target disease;
[0039] The second acquisition module is used to obtain a threshold value of the number of medical visits and count the number of historical medical visits of the target patient;
[0040] A query module, configured to determine, when the number of historical medical visits is less than the medical visit threshold, an attribute interval hit by the age information and gender information of the target patient, and query a second drug category threshold associated with the attribute interval;
[0041] a statistical module, configured to count the types of drugs used by the target patient if the query determines that the attribute interval has the second drug type threshold associated therewith;
[0042] A marking module is used to mark the target patient as high risk when the type of used drugs is greater than the second drug type threshold.
[0043] Optionally, the determination module is used to obtain the patients to be marked, filter out the patients to be marked whose disease information is associated with the high-risk diagnostic label among the patients to be marked, and mark the filtered patients to be marked as high risk; filter out the patients to be marked whose drug information is associated with the high-risk drug label among the filtered patients to be marked, and mark the filtered patients to be marked as high risk; count the types of drugs used by the patients to be marked among the filtered patients to be marked, filter out the patients to be marked whose types of drugs used are greater than the first drug type number threshold, and mark the filtered patients to be marked as high risk; and use the remaining patients to be marked after filtering as the target patients.
[0044] Optionally, the second acquisition module is used to determine multiple sample patients, query the risk label of the target disease associated with each sample patient in the multiple sample patients, and the risk label is high risk or medium-low risk; group the multiple sample patients according to the risk label, and divide the sample patients with the same risk label into the same group to obtain two sample patient groups; for each sample patient group in the two sample patient groups, count the historical number of medical visits of each sample patient included in the sample patient group as the sample number of medical visits; based on the sample number of medical visits included in each sample patient group, calculate the average number of medical visits for each sample patient group to obtain two average number of medical visits; use the quartile method to process the two average number of medical visits to obtain the median of the two average number of medical visits, and use the median as the medical visit number threshold.
[0045] Optionally, the device further comprises:
[0046] The query module is further configured to query a third drug category threshold according to the basic information of the target patient when the historical number of medical visits is greater than or equal to the medical visit threshold;
[0047] The statistical module is further configured to compare the type of drug used by the target patient with the third drug type threshold when the query of the third drug type threshold is successful, and mark the target patient according to the comparison result.
[0048] The statistical module is further configured to mark the target patient as medium-low risk when the third drug category threshold query fails.
[0049] Optionally, the statistical module is also used to mark the target patient as high risk when the comparison result indicates that the types of drugs used by the target patient are greater than the third drug type threshold; when the comparison result indicates that the types of drugs used by the target patient are less than or equal to the third drug type threshold, mark the target patient as medium-low risk.
[0050] Optionally, the marking module is further configured to mark the target patient as high risk if the query determines that the attribute interval does not have an associated second drug category threshold.
[0051] Optionally, the marking module is further used to mark the target patient as medium-low risk when the type of used drugs is less than or equal to the second drug type threshold.
[0052] According to a third aspect of the present application, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.
[0053] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.
[0054] By means of the above technical scheme, the present application provides a patient labeling method, device, equipment and storage medium based on hierarchical calculation. The present application determines the target patients who do not hit the high-risk diagnostic label, high-risk drug label and first drug type threshold of the target disease among the patients to be labeled of the target disease. Subsequently, the threshold of the number of medical visits is obtained, and the historical number of medical visits of the target patient is counted. When the historical number of medical visits is less than the threshold of the number of medical visits, the attribute interval in which the age information and gender information of the target patient hit is determined, and the second drug type threshold associated with the attribute interval is queried. If the query determines that there is an associated second drug type threshold in the attribute interval, the types of drugs used by the target patient are counted. When the types of drugs used are greater than the second drug type threshold, the target patient is marked as high risk. By supplementing the risk stratification labels, different risk labels are applied to the patients to be labeled, so that the smart medical platform can more comprehensively identify the risk level of patients and improve the labeling accuracy.
[0055] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0057] Figure 1 A schematic diagram of a patient labeling method based on hierarchical calculation provided in an embodiment of the present application is shown;
[0058] Figure 2A A schematic diagram of a patient labeling method based on hierarchical calculation provided in an embodiment of the present application is shown;
[0059] Figure 2B A schematic diagram of a patient labeling method based on hierarchical calculation provided in an embodiment of the present application is shown;
[0060] Figure 3 A schematic diagram of the structure of a patient marking device based on hierarchical calculation provided in an embodiment of the present application is shown;
[0061] Figure 4 A schematic diagram of the device structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0062] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.
[0063] The present application embodiment provides a patient labeling method based on hierarchical calculation, such as Figure 1 As shown, the method includes:
[0064] 101. Obtain high-risk diagnostic labels, high-risk drug labels, and drug type thresholds. High-risk diagnostic labels and high-risk drug labels are obtained from medical guidelines and are associated with target diseases. Drug type thresholds are obtained by calculating the average value of historical drug types for multiple sample patients. Multiple sample patients are marked as high risk.
[0065] 102. Determine a target patient among patients with a target disease to be labeled based on a high-risk diagnostic label, a high-risk drug label, and a first drug category threshold. The target patient is a patient among the patients to be labeled who does not hit the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold of the target disease.
[0066] 103. Obtain the threshold of the number of medical visits and count the historical number of medical visits of the target patient.
[0067] 104. When the number of historical medical visits is less than the medical visit threshold, determine the attribute interval hit by the target patient's age information and gender information, and query the second drug type threshold associated with the attribute interval.
[0068] 105. If the query determines that the attribute interval has an associated second drug type threshold, then count the types of drugs used by the target patient.
[0069] 106. When the type of drug used is greater than a second drug type threshold, the target patient is marked as high risk.
[0070] The method provided in the embodiment of the present application determines the target patients who do not hit the high-risk diagnostic label, high-risk drug label and first drug category threshold of the target disease among the patients to be marked for the target disease, then obtains the threshold of the number of medical visits, counts the historical number of medical visits of the target patient, and when the historical number of medical visits is less than the threshold of the number of medical visits, determines the attribute interval where the age information and gender information of the target patient hit, queries the second drug category threshold associated with the attribute interval, and if the query determines that the attribute interval has an associated second drug category threshold, then counts the types of drugs used by the target patient, and when the types of drugs used are greater than the second drug category threshold, marks the target patient as high risk. By supplementing the risk stratification labels, different risk labels are applied to the patients to be marked, so that the smart medical platform can more comprehensively identify the risk level of patients and improve the marking accuracy.
[0071] The present application embodiment provides a patient labeling method based on hierarchical calculation, such as Figure 2A As shown, the method includes:
[0072] 201. Identify target patients among patients with the target disease to be labeled.
[0073] With the continuous progress of society and the continuous development of Internet technology, people are more and more concerned about their own health problems. Many hospitals and institutions will mark patients for risk, so as to provide patients with disease treatment, product recommendations and other services. Taking hypertension as an example, the purpose of marking hypertensive patients is to distinguish the risk levels of different hypertensive patients, supplement the hypertension risk labels, and enable the smart medical platform to analyze hypertensive patients with different risk levels, so as to provide disease treatment, product recommendations and other services for patients with different risk levels in the future. At present, when marking hypertensive patients, it is necessary to obtain the indicator thresholds for high-risk hypertensive patients in the medical guidelines, and set the preset conditions for screening hypertensive patients according to the indicator thresholds. If the systolic blood pressure of a hypertensive patient is greater than 160mmHg, or the diastolic blood pressure is greater than 100mmHg, it will be determined as high risk and marked. If it does not belong to the above situation, it is a low-risk hypertensive patient and marked. However, the applicant realized that the smart medical platform only used the known blood pressure index to make a rough distinction when distinguishing the risk levels of hypertensive patients, resulting in some hypertensive patients who may be in a high-risk state, but are classified as low-risk patients because they do not meet the high-risk conditions set for hypertension in medicine, resulting in incomplete risk level identification and low marking accuracy.
[0074] Therefore, the present application provides a patient marking method, which can be applied to a smart medical platform, so that the smart medical platform determines the target patients who do not hit the high-risk diagnostic label, high-risk drug label and first drug type threshold of the target disease among the patients to be marked for the target disease, and then obtains the threshold of the number of medical visits, and counts the historical number of medical visits of the target patient. When the number of historical medical visits is less than the threshold of the number of medical visits, the attribute interval hit by the age information and gender information of the target patient is determined, and the second drug type threshold associated with the attribute interval is queried. If the query determines that there is an associated second drug type threshold in the attribute interval, the target patient's drug type is counted, and when the drug type used is greater than the second drug type threshold, the target patient is marked as high risk. By supplementing the risk stratification label, different risk labels are performed on the marked patients, so that the smart medical platform can identify the risk level of the patient more comprehensively and improve the marking accuracy. Among them, the smart medical platform can be operated based on an independent server, or it can be operated based on a server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (Content Delivery Network, CDN), and basic cloud computing such as big data and artificial intelligence platforms. In this way, when the relevant information of the target patient is subsequently identified, the medical data of the target patient, such as personal health records, prescriptions, examination reports, etc., can be downloaded from the server.
[0075] Among them, the target patients are those who do not hit the high-risk diagnostic label, high-risk drug label and first drug category threshold of the target disease among the patients to be marked. That is to say, many high-risk patients can be identified through some existing identification rules. These identified patients who are obviously high-risk can be directly marked as high-risk, and patients who do not obviously hit the high-risk situation are used as target patients for subsequent multi-dimensional identification. In order to identify such patients who are obviously high-risk, the smart medical platform will obtain high-risk diagnostic labels and high-risk drug labels that are associated with the target disease in the medical guidelines in advance, and determine multiple sample patients marked as high-risk, calculate the average value of the historical drug categories of multiple sample patients to obtain the drug category threshold, and then use the high-risk diagnostic label, high-risk drug label and drug category threshold to determine the target patient for subsequent multi-dimensional identification. The specific process of determining the target patient among the patients to be marked with the target disease is as follows:
[0076] Specifically, the patient to be marked is obtained, and according to the high-risk diagnosis label, the high-risk drug label and the drug type threshold, the patient to be marked whose disease information is associated with the high-risk diagnosis label is filtered out among the patients to be marked, and the filtered patient to be marked is marked as high risk. Specifically, when identifying disease information, two methods can be used. One method is to obtain the patient data information of the patient to be marked, identify the patient data information by text recognition, extract the disease type in the patient data information as the target disease type, and take the patient to be marked who is associated with the high-risk diagnosis label of the target disease in the target disease type as the target patient. It should be noted that since the patient to be marked may also go to the hospital for other diseases, such as colds, appendicitis, etc., this will cause the patient data information to have disease types that are not related to the target disease. Therefore, the disease types known to be related to the target disease in the medical guide can be used to filter all the disease types of the patient to be marked, and the disease types related to the target disease in the patient data information are taken as the target disease types. Another method is to identify whether the patient to be marked meets the high-risk diagnostic label of the target disease in the ICD (International Classification of Diseases) disease code of the patient to be marked, and filter the patient to be marked when it is determined to meet the high-risk diagnostic label. For example, the high-risk diagnostic label may include hypertension level 2 or above, hypertension above moderate risk, diabetes, cerebrovascular disease, heart disease, kidney disease, peripheral vascular disease, retinopathy, hypertensive heart disease, hypertensive kidney disease, hypertensive heart and kidney disease, and secondary hypertension.
[0077] Next, filter out the patients whose drug information is associated with high-risk drug labels from the filtered patients to be marked, and mark the filtered patients to be marked as high-risk, where the high-risk drug labels can be the types of drugs that high-risk hypertensive patients may use as recorded in the medical guidelines, or they can be searched in the historical claims data of the smart medical platform for hypertensive customers who have received hospitalization or surgery claims, identify the names of drugs used by customers who have received claims, and combine the names of drugs used by customers who have received claims with the types of drugs that high-risk hypertensive patients may use as recorded in the medical guidelines. For example, high-risk drug labels can include diabetes drugs, cerebrovascular disease drugs, heart disease drugs, kidney disease drugs, peripheral vascular disease drugs, retinopathy drugs, and hypertensive emergency drugs.
[0078] Subsequently, the types of drugs used by the patients to be marked after filtering are counted, and the number of drug types used is compared with the first drug type threshold. The first drug type threshold can be set by default to the high-risk drug type threshold recorded in the medical guide, or it can be set according to the historical claims information of the smart medical platform. Specifically, the number of drug types used by customers who have incurred claims is counted, the mean number of drug types used is calculated, and the mean number of drug types used is used as the first drug type threshold. Relevant staff can set it in the system according to the actual application scenario. This application does not specifically limit the setting size and setting method of the first drug type threshold. Filter the patients to be marked whose used drug types are greater than the first drug type threshold, and mark the filtered patients to be marked as high risk.
[0079] Finally, the remaining patients to be marked after filtering are used as the target patients.
[0080] Through the existing risk level labels, namely high-risk diagnosis labels, high-risk drug labels, and the first drug type number threshold, the patients to be marked are preliminarily screened. For patients to be marked who have hit the existing risk level labels, they can be directly filtered, that is, they can be directly marked as high risk, and no subsequent graded marking is required.
[0081] 202. Obtain a threshold for the number of medical visits, and count the target patient's historical number of medical visits. When the historical number of medical visits is less than the threshold for the number of medical visits, execute the following step 203; when the historical number of medical visits is greater than or equal to the threshold for the number of medical visits, execute the following step 204.
[0082] In an embodiment of the present application, a threshold value of the number of medical visits of the target patient is obtained, the historical number of medical visits of the target patient is compared with the threshold value of the number of medical visits, different risk indicators are obtained based on the comparison results, and then the target patient is accurately risk-marked according to the corresponding risk indicators.
[0083] First, obtain the threshold of the number of medical visits. The threshold of the number of medical visits can be set by relevant staff according to the customer information of the smart medical platform according to the specific implementation scenario. Specifically, multiple sample patients are determined, where, taking patients with hypertension as an example, the sample patients can be customers with hypertension extracted from the customer information of the smart medical platform. Query the risk label of the target disease associated with each sample patient in the multiple sample patients, and the risk label is high risk or medium and low risk. Group multiple sample patients according to the risk label, and divide the sample patients with the same risk label into the same group to obtain two sample patient groups. In the actual application process, the sample patients can be divided into a high-risk group and a medium-low risk group according to the risk record of the type of hypertension disease in the medical guide. For each sample patient group in the two sample patient groups, the historical number of medical visits of each sample patient included in the sample patient group is counted as the sample number of medical visits, and based on the sample number of medical visits included in each sample patient group, the average number of medical visits of each sample patient group is calculated to obtain two average number of medical visits. Finally, the two average number of medical visits are processed by the quartile method to obtain the median of the two average number of medical visits, and the median is used as the threshold of the number of medical visits. The above process is to group the sample patients into high-risk, medium-risk and low-risk groups, and then count the average number of medical visits for both the high-risk group and the medium-risk group. After obtaining two average number of medical visits, use quartiles to determine the median of the two average number of medical visits, and use the median as the threshold for the number of medical visits.
[0084] Subsequently, the target medical insurance data of the target patient is obtained, and the medical treatment information in the target medical insurance data is identified, and the historical number of medical treatments of the target patient is counted, and the historical number of medical treatments is compared with the medical treatment number threshold. When the historical number of medical treatments is less than the medical treatment number threshold, the second drug type threshold is queried based on the basic information of the target patient, that is, the following step 203 is executed. When the historical number of medical treatments is greater than or equal to the medical treatment number threshold, the third drug type threshold is queried based on the basic information of the target patient, that is, the following step 204 is executed.
[0085] Since the patient's regular medical visits are closely related to their corresponding risk level, if the patient visits the doctor regularly, the condition can be well controlled. If the patient does not visit the doctor regularly, the condition may worsen. Therefore, the target patient's historical medical visits in the historical time period are counted. When the historical medical visits are greater than or equal to the medical visits threshold, it means that the target patient actually visits the doctor regularly. The target patient cannot be directly marked as high risk. Further evaluation is required based on different risk indicators to improve the accuracy of risk marking.
[0086] 203. When the number of historical medical visits is less than the medical visit threshold, determine the attribute interval hit by the target patient's age information and gender information, and query the second drug type threshold associated with the attribute interval.
[0087] In the embodiment of the present application, due to the different physical conditions of patients of different genders and ages, in actual application scenarios, males are often at higher risk than females, and older patients are at higher risk than younger patients. Therefore, after determining whether the target patient regularly seeks medical treatment, it is also necessary to query the corresponding risk indicators based on the basic information of the target patient, compare the medical information of the target patient with the corresponding risk indicators, and mark the target patient for risk based on the comparison results.
[0088] Among them, the basic information of the target patient is information that can reflect the physical state of the target patient, such as the patient's gender and age. Therefore, it is necessary to determine the attribute interval hit by the target patient's age information and gender information, and query the second drug type threshold associated with the attribute interval. For example, assuming that the target patient's age information is 65 years old and the gender information is female, the attribute interval hit is a female over 50 years old, and it is sufficient to check whether there is an associated second drug type threshold in the attribute interval. It should be noted that the second drug type number threshold is used to indicate the risk indicator corresponding to the current age information and gender information, for example, the number of types of antihypertensive drugs used. In the actual application process, sample patients can be set, wherein the sample patients are patients whose historical medical visits are less than the medical visit threshold. According to the risk records of hypertension disease types in the medical guidelines, the sample patients are divided into high-risk groups and medium- and low-risk groups, and the types of drugs used by each sample patient in the sample patient group are counted, and the average number of drug types used in each sample patient group is calculated to obtain the average number of drug types used in the preset number, and the average number of drug types used in the preset number is processed by the quartile method to obtain the median of the average number of drug types used in the preset number, and the median is used as the second drug type threshold. It should be noted that if the target patient's historical number of medical visits is less than the medical visit threshold and the basic information shows that he or she belongs to the high-risk group, there is no need to calculate the second drug type threshold. In other words, when the system subsequently queries the second drug type threshold based on the target patient's basic information, it will display that there is no second drug type threshold associated with the attribute interval that hits the target patient's age information and gender information.
[0089] Next, if the query determines that there is a second drug type threshold associated with the attribute interval, the types of drugs used by the target patient are counted, the types of drugs used are compared with the second drug threshold, and the target patient is marked based on the comparison result. When the types of drugs used are greater than the second drug type threshold, the target patient is marked as high risk, and when the types of drugs used are less than or equal to the second drug type threshold, the target patient is marked as medium-low risk. If the query for the second drug type threshold fails, the target patient is marked as high risk.
[0090] 204. When the number of historical medical visits is greater than or equal to the medical visit threshold, query the third drug type threshold according to the basic information of the target patient, and mark the target patient based on the third drug type threshold.
[0091] In an embodiment of the present application, when the number of historical medical visits is greater than or equal to the medical visit number threshold, it means that the current target patient visits the doctor regularly every year. At this time, based on the basic information of the current target patient, when regular medical visits are queried, the third drug type threshold corresponding to the basic information of the current target patient is used, and the target patient is marked based on the third drug type threshold.
[0092] In actual application, sample patients can be set, wherein the sample patients are patients whose historical number of medical visits is greater than or equal to the threshold number of medical visits. Based on the risk records of types of hypertension diseases in the medical guidelines, the sample patients are divided into high-risk groups and medium- and low-risk groups, and the types of drugs used by each sample patient in the sample patient group are counted, and the average number of drug types used in each sample patient group is calculated to obtain the average number of drug types used for the preset number, and the average number of drug types used for the preset number is processed using the quartile method to obtain the median of the average number of drug types used for the preset number, and the median is used as the third drug type threshold. It should be noted that if the target patient's historical number of medical visits is greater than or equal to the threshold number of medical visits and the basic information shows that it belongs to the low-risk population, there is no need to calculate the third drug type threshold, that is, when the system subsequently queries the third drug type threshold based on the basic information of the target patient, it will display a query failure.
[0093] Specifically, when the third drug type threshold query is successful, the target patient's drug type is compared with the third drug type threshold, and the target patient is marked according to the comparison result. When the comparison result indicates that the target patient's drug type is greater than the third drug type threshold, the target patient is marked as high risk, and when the comparison result indicates that the target patient's drug type is less than or equal to the third drug type threshold, the target patient is marked as medium-low risk. When the third drug type threshold query fails, the target patient is marked as medium-low risk. For example, the target patient A's medical insurance data information is obtained, and it is concluded that the target patient A is a female, 68 years old, and uses 4 types of drugs. Based on the basic information of the target patient A, the third drug type threshold is queried as 3. By comparing the drug type with the third drug type threshold, it can be concluded that the drug type is greater than the third drug type threshold. Therefore, the system marks A as high risk. The target patient B's medical insurance data information is obtained, and it is concluded that the target patient B is a female, 45 years old, and uses 4 types of drugs. Based on the basic information of the target patient B, the third drug type threshold cannot be queried, so the system marks B as medium-low risk.
[0094] In summary, taking a patient with hypertension as an example, the patient marking process in this application is summarized as follows:
[0095] See also Figure 2B First, obtain the patients to be marked, filter the patients to be marked whose disease information is associated with a high-risk diagnosis label among the patients to be marked, and mark the filtered patients to be marked as high-risk, filter the patients to be marked whose drug information is associated with a high-risk drug label among the filtered patients to be marked, and mark the filtered patients to be marked as high-risk, count the types of drugs used by the patients to be marked among the filtered patients to be marked, filter the patients to be marked whose drug types are greater than the first drug type number threshold, and mark the filtered patients to be marked as high-risk, and take the remaining patients to be marked after filtering as target patients. Then, obtain the threshold of the number of medical visits, count the historical number of medical visits of the target patient, when the historical number of medical visits is less than the threshold of the number of medical visits, query the second drug type threshold according to the basic information of the target patient, if the query of the second drug type threshold is successful, count the types of drugs used by the target patient, and compare the types of drugs used with the second drug type threshold. When the types of drugs used are greater than the second drug type threshold, the target patient is marked as high-risk, and when the types of drugs used are less than or equal to the second drug type threshold, the target patient is marked as medium-low risk. If the query for the second drug type threshold fails, the target patient is marked as high risk. When the number of historical medical visits is greater than or equal to the medical visit threshold, the third drug type threshold is queried based on the target patient's basic information. When the query for the third drug type threshold is successful, the target patient's used drug types are compared with the third drug type threshold. If the comparison result indicates that the target patient's used drug types are greater than the third drug type threshold, the target patient is marked as high risk. If the comparison result indicates that the target patient's used drug types are less than or equal to the third drug type threshold, the target patient is marked as medium-low risk. When the query for the third drug type threshold fails, the target patient is marked as medium-low risk.
[0096] The method provided in the embodiment of the present application determines the target patients who do not hit the high-risk diagnostic label, high-risk drug label and first drug category threshold of the target disease among the patients to be marked for the target disease, then obtains the threshold of the number of medical visits, counts the historical number of medical visits of the target patient, and when the historical number of medical visits is less than the threshold of the number of medical visits, determines the attribute interval where the age information and gender information of the target patient hit, queries the second drug category threshold associated with the attribute interval, and if the query determines that the attribute interval has an associated second drug category threshold, then counts the types of drugs used by the target patient, and when the types of drugs used are greater than the second drug category threshold, marks the target patient as high risk. By supplementing the risk stratification labels, different risk labels are applied to the patients to be marked, so that the smart medical platform can more comprehensively identify the risk level of patients and improve the marking accuracy.
[0097] Further, as Figure 1 In a specific implementation of the method, the present application provides a patient marking device based on hierarchical calculation, such as Figure 3 As shown, the device includes: a first acquisition module 301, a determination module 302, a second acquisition module 303, a query module 304, a statistics module 305, and a marking module 306.
[0098] The first acquisition module 301 is used to acquire a high-risk diagnosis label, a high-risk drug label and a drug type threshold, wherein the high-risk diagnosis label and the high-risk drug label are acquired in a medical guide and are associated with the target disease, and the first drug type threshold is obtained by calculating the type average of historical drug types of multiple sample patients, and the multiple sample patients are marked as high risk;
[0099] The determination module 302 is used to determine a target patient from among the patients to be marked for the target disease, wherein the target patient is a patient who does not hit a high-risk diagnosis label, a high-risk drug label, and a first drug category threshold for the target disease among the patients to be marked;
[0100] The second acquisition module 303 is used to obtain a threshold of the number of medical visits and to count the number of historical medical visits of the target patient;
[0101] The query module 304 is used to determine the attribute interval hit by the age information and gender information of the target patient when the historical number of medical visits is less than the medical visit number threshold, and query the second drug type threshold associated with the attribute interval;
[0102] The statistical module 305 is used to count the types of drugs used by the target patient if the query determines that the attribute interval has the second drug type threshold associated therewith;
[0103] The marking module 306 is used to mark the target patient as high risk when the type of used drugs is greater than the second drug type threshold.
[0104] In a specific application scenario, the determination module 302 is used to obtain the patients to be marked, filter out the patients to be marked whose disease information is associated with the high-risk diagnostic label among the patients to be marked, and mark the filtered patients to be marked as high risk; filter out the patients to be marked whose drug information is associated with the high-risk drug label among the filtered patients to be marked, and mark the filtered patients to be marked as high risk; count the types of drugs used by the patients to be marked among the filtered patients to be marked, filter out the patients to be marked whose types of drugs used are greater than the first drug type number threshold, and mark the filtered patients to be marked as high risk; and use the remaining patients to be marked after filtering as the target patients.
[0105] In a specific application scenario, the second acquisition module 303 is used to determine multiple sample patients, query the risk label of the target disease associated with each sample patient in the multiple sample patients, and the risk label is high risk or medium-low risk; group the multiple sample patients according to the risk label, and divide the sample patients with the same risk label into the same group to obtain two sample patient groups; for each sample patient group in the two sample patient groups, count the historical number of medical visits of each sample patient included in the sample patient group as the sample number of medical visits; based on the sample number of medical visits included in each sample patient group, calculate the average number of medical visits for each sample patient group to obtain two average number of medical visits; use the quartile method to process the two average number of medical visits to obtain the median of the two average number of medical visits, and use the median as the medical visit number threshold.
[0106] In a specific application scenario, the device further includes:
[0107] The query module 304 is further configured to query a third drug category threshold according to the basic information of the target patient when the historical number of medical visits is greater than or equal to the medical visit threshold;
[0108] The statistical module 305 is further configured to compare the type of drug used by the target patient with the third drug type threshold when the query of the third drug type threshold is successful, and mark the target patient according to the comparison result.
[0109] The statistical module 305 is further configured to mark the target patient as medium-low risk when the third drug category threshold query fails.
[0110] In a specific application scenario, the statistical module 305 is also used to mark the target patient as high risk when the comparison result indicates that the types of drugs used by the target patient are greater than the third drug type threshold; when the comparison result indicates that the types of drugs used by the target patient are less than or equal to the third drug type threshold, mark the target patient as medium-low risk.
[0111] In a specific application scenario, the marking module 306 is further configured to mark the target patient as high risk if the query determines that the attribute interval does not have the associated second drug category threshold.
[0112] In a specific application scenario, the marking module 306 is further used to mark the target patient as medium-low risk when the type of used drugs is less than or equal to the second drug type threshold.
[0113] The device provided in the embodiment of the present application determines the target patients who do not hit the high-risk diagnosis label, high-risk drug label and first drug category threshold of the target disease among the patients to be marked for the target disease, and then obtains the threshold of the number of medical visits, counts the historical number of medical visits of the target patient, and when the historical number of medical visits is less than the threshold of the number of medical visits, determines the attribute interval where the age information and gender information of the target patient hit, queries the second drug category threshold associated with the attribute interval, and if the query determines that the attribute interval has an associated second drug category threshold, then counts the types of drugs used by the target patient, and when the types of drugs used are greater than the second drug category threshold, marks the target patient as high risk. By supplementing the risk stratification labels, different risk labels are applied to the patients to be marked, so that the smart medical platform can more comprehensively identify the risk level of patients and improve the marking accuracy.
[0114] It should be noted that for other corresponding descriptions of the functional units involved in the patient marking device based on hierarchical calculation provided in the embodiment of the present application, reference can be made to Figure 1 and FIG. 2A to FIG. 2B The corresponding description in will not be repeated here.
[0115] In an exemplary embodiment, see Figure 4 , and also provides a device, which includes a bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device, wherein each functional unit can communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the patient marking method based on hierarchical calculation in the above embodiment.
[0116] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the patient marking method based on hierarchical calculation.
[0117] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.
[0118] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present application.
[0119] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.
[0120] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.
[0121] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.
Claims
1. A patient labeling method based on hierarchical calculation, characterized in that: include: Obtaining a high-risk diagnosis label, a high-risk drug label, and a first drug category threshold, wherein the high-risk diagnosis label and the high-risk drug label are obtained in a medical guideline and are associated with a target disease, and the first drug category threshold is obtained by calculating a category average of historical drug categories of a plurality of sample patients, and the plurality of sample patients are marked as high risk; Determine a target patient among the patients to be marked with a target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold, wherein the target patient is a patient among the patients to be marked who does not hit the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold of the target disease; Obtaining a threshold for the number of medical visits, counting the historical number of medical visits of the target patient, wherein the multiple sample patients are grouped according to high risk, medium and low risk to obtain two sample patient groups, and the average number of medical visits for the two sample patient groups is counted to obtain two average number of medical visits, and the median of the two average number of medical visits is determined by using the quartile method, and the median is used as the threshold for the number of medical visits; When the number of historical medical visits is less than the medical visit number threshold, determine the attribute interval hit by the age information and gender information of the target patient, query the second drug type threshold associated with the attribute interval, and the second drug type threshold is used to indicate the risk indicator corresponding to the current age information and gender information, wherein the multiple sample patients are divided into a high-risk group and a medium-low risk group, and the types of drugs used by each sample patient in the high-risk group and the medium-low risk group are counted, and the average number of drug types used in the high-risk group and the medium-low risk group are calculated respectively to obtain two average numbers of drug types used, and the two average numbers of drug types used are processed by the quartile method to obtain the median of the two average numbers of drug types used, and the median is used as the second drug type threshold; If the query determines that the attribute interval has the second drug type threshold associated therewith, counting the types of drugs used by the target patient; When the type of drug used is greater than the second drug type threshold, marking the target patient as high risk; Among them, when the number of historical medical visits is greater than or equal to the medical visit number threshold, the third drug type threshold is queried according to the basic information of the target patient, and when the third drug type threshold is queried successfully, the types of drugs used by the target patient are compared with the third drug type threshold, and when the comparison result indicates that the types of drugs used by the target patient are greater than the third drug type threshold, the target patient is marked as high risk, and when the comparison result indicates that the types of drugs used by the target patient are less than or equal to the third drug type threshold, the target patient is marked as medium-low risk; accordingly, when the third drug type threshold query fails, the target patient is marked as medium-low risk.
2. The method according to claim 1, characterized in that The step of determining a target patient from among patients to be labeled with a target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold comprises: Acquire the patients to be marked, filter the patients to be marked whose disease information is associated with the high-risk diagnosis label among the patients to be marked, and mark the filtered patients to be marked as high-risk; Filtering the patients to be marked whose drug information is associated with the high-risk drug label among the filtered patients to be marked, and marking the filtered patients to be marked as high risk; Counting the types of drugs used by the patients to be marked after filtering, filtering the patients to be marked whose types of drugs used are greater than the first drug type threshold, and marking the filtered patients to be marked as high risk; The remaining patients to be marked after filtering are regarded as the target patients.
3. The method according to claim 1, characterized in that: The threshold for obtaining the number of medical visits includes: Determine a plurality of sample patients, query a risk label of the target disease associated with each sample patient in the plurality of sample patients, wherein the risk label is high risk or medium-low risk; Grouping the multiple sample patients according to the risk labels, and grouping the sample patients with the same risk labels into the same group to obtain two sample patient groups; For each of the two sample patient groups, counting the number of historical medical visits of each sample patient included in the sample patient group as the number of sample medical visits; Based on the sample medical visits included in each sample patient group, the average medical visits of each sample patient group is calculated to obtain two average medical visits; The two average times of medical treatment are processed by quartile method to obtain the median of the two average times of medical treatment, and the median is used as the threshold of the times of medical treatment.
4. The method according to claim 1, characterized in that: After determining the attribute interval hit by the age information and gender information of the target patient and querying the second drug category threshold associated with the attribute interval, the method further includes: If the query determines that the attribute interval does not have an associated second drug category threshold, the target patient is marked as high risk.
5. The method according to claim 1, characterized in that After counting the types of drugs used by the target patient, the method further includes: When the type of used drugs is less than or equal to the second drug type threshold, the target patient is marked as medium-low risk.
6. A patient marking device based on hierarchical calculation, characterized in that: include: A first acquisition module is used to acquire a high-risk diagnosis label, a high-risk drug label, and a first drug category threshold, wherein the high-risk diagnosis label and the high-risk drug label are acquired in a medical guideline and are associated with a target disease, and the first drug category threshold is obtained by calculating a category average of historical drug categories of a plurality of sample patients, and the plurality of sample patients are marked as high risk; a determination module, configured to determine a target patient among the patients to be marked with a target disease according to the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold, wherein the target patient is a patient among the patients to be marked who does not hit the high-risk diagnostic label, the high-risk drug label, and the first drug category threshold of the target disease; The second acquisition module is used to obtain a threshold value of the number of medical visits, and to count the historical number of medical visits of the target patient, wherein the multiple sample patients are grouped according to high risk, medium and low risk to obtain two sample patient groups, and the average number of medical visits of the two sample patient groups is counted to obtain two average number of medical visits, and the median of the two average number of medical visits is determined by using the quartile method, and the median is used as the threshold value of the number of medical visits; A query module, used for, when the number of historical medical visits is less than the medical visit number threshold, determining the attribute interval hit by the age information and gender information of the target patient, querying a second drug type threshold associated with the attribute interval, the second drug type threshold being used to indicate the risk index corresponding to the current age information and gender information, wherein the multiple sample patients are divided into a high-risk group and a medium-low risk group, counting the types of drugs used by each sample patient in the high-risk group and the medium-low risk group, calculating the average number of drug types used by the high-risk group and the medium-low risk group respectively, obtaining two average numbers of drug types used, processing the two average numbers of drug types used by the quartile method, obtaining the median of the two average numbers of drug types used, and using the median as the second drug type threshold; a statistical module, configured to count the types of drugs used by the target patient if the query determines that the attribute interval has the second drug type threshold associated therewith; a marking module, configured to mark the target patient as high risk when the type of drug used is greater than the second drug type threshold; Among them, the query module is also used to query the third drug type threshold according to the basic information of the target patient when the historical number of medical visits is greater than or equal to the medical visit number threshold; the statistical module is also used to compare the types of drugs used by the target patient with the third drug type threshold when the third drug type threshold query is successful, and when the comparison result indicates that the types of drugs used by the target patient are greater than the third drug type threshold, mark the target patient as high risk; and when the comparison result indicates that the types of drugs used by the target patient are less than or equal to the third drug type threshold, mark the target patient as medium-low risk; accordingly, the statistical module is also used to mark the target patient as medium-low risk when the third drug type threshold query fails.
7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
Citation Information
Patent Citations
Tumor malignant risk stratification auxiliary diagnosis system of artificial intelligence medical image
CN109166105A
Apparatus for patient record identification
CN110033835A
Chronic disease comprehensive service platform
CN111554365A
Postoperative self-service evaluation system suitable for differentiated thyroid cancer patient
CN111739638A
Chronic disease processing method and device, computer equipment and storage medium
CN111933237A
