Medical performance determination system

Abstract

The invention relates to a medical performance determination system. The system comprises a data storage module, a performance determination module, an auxiliary module and a display module, wherein the data storage module is used for storing medical data and standard data of each diagnosis group; the performance determination module is used for classifying the medical data according to diagnosis and treatment doctors to obtain diagnosis and treatment data of the doctors; performing performance determination on each doctor according to the diagnosis and treatment data of each doctor and the standard data of each diagnosis group; the auxiliary module is used for determining an auxiliary doctor and corresponding benchmark data according to the performance determination result, and providing the corresponding benchmark data for the auxiliary doctor; and the display module is used for displaying the medical data, the standard data, the performance determination data and the benchmark data. According to the system, the doctor performance can be automatically determined, and the problems that manual determination is prone to errors, is prone to being influenced by external factors and is low in performance determination accuracy are solved.

Description

Technical Field

[0001] The present invention relates to the field of medical technologies, and in particular to a medical performance determination system. Background Art

[0002] Currently, performance determination is carried out manually. For example, doctors summarize their work, and performance determination personnel determine the performance based on the work content summarized by doctors.

[0003] Manual determination is not only prone to errors but also easily affected by external factors, which makes the accuracy of the existing performance determination relatively low. Summary of the Invention

[0004] The present invention provides a medical performance determination system, which includes: a data storage module, a performance determination module, an auxiliary module, and a display module;

[0005] Among them, the data storage module is used to store medical data and standard data of each diagnosis group; the medical data is data involved in the hospital diagnosis and treatment process, and the standard data is regularly released by relevant personnel;

[0006] The performance determination module is used to classify the medical data according to the diagnosing doctors to obtain the diagnosis and treatment data of each doctor; and determine the performance of each doctor based on the diagnosis and treatment data of each doctor and the standard data of each diagnosis group;

[0007] The auxiliary module is used to determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result, and provide the corresponding benchmark data to the auxiliary doctor;

[0008] The display module is used to display medical data, standard data, performance determination data, and benchmark data.

[0009] Optionally, determining the performance of each doctor based on the diagnosis and treatment data of each doctor and the standard data of each diagnosis group includes:

[0010] For any doctor i, his performance is determined through the following steps:

[0011] Determine all the diagnosis and treatment data of doctor i as the target diagnosis and treatment data;

[0012] Determine the patients, diagnosis groups, and diagnosis and treatment links corresponding to each target diagnosis and treatment data; among them, the target diagnosis and treatment data is composed of the diagnosis and treatment data of each diagnosis and treatment node; for any target diagnosis and treatment data, the nodes in its diagnosis and treatment link correspond one by one to the diagnosis and treatment nodes in any target diagnosis and treatment data, the relationship between the nodes in its diagnosis and treatment link is the same as the diagnosis and treatment order of each diagnosis and treatment node, and the data attribute value of each node in the diagnosis and treatment link is the diagnosis and treatment data of its corresponding diagnosis and treatment node;

[0013] Cluster the treatment chains corresponding to the target treatment data based on patients;

[0014] For each category, determine the treatment performance value according to the treatment chains, diagnosis groups, and standard data of each diagnosis group in the category; among them, the treatment performance value Dvij(u) of any treatment chain u in any category j = (the similarity between any treatment chain u in category j and the standard data of the diagnosis group of treatment chain u) / the standard performance value of category j; the standard performance value of category j is determined according to the patients corresponding to category j, the department and professional title of doctor i;

[0015] Determine the performance of doctor i according to the mean and standard deviation of the treatment performance values of each category.

[0016] Optionally, the steps for determining the standard performance value of category j are as follows:

[0017] Determine the similarity between the treatment data of each doctor in the department where doctor i belongs and the standard data of the diagnosis group of the patients corresponding to category j;

[0018] Determine that the first value is the mean of the similarities of all doctors in the department where doctor i belongs;

[0019] Determine that the second value is the mean of the similarities of all doctors with the same professional title as doctor i in the department where doctor i belongs;

[0020] Determine that the third value is the standard deviation of the similarities of all doctors in the department where doctor i belongs;

[0021] Determine that the fourth value is the standard deviation of the similarities of all doctors with the same professional title as doctor i in the department where doctor i belongs;

[0022] If the first value is not greater than the second value, determine that the standard performance value of category j is the second value;

[0023] If the first value is greater than the second value, determine the standard performance value of category j according to the third value and the fourth value.

[0024] Optionally, determining the standard performance value of category j according to the third value and the fourth value includes:

[0025] Determine that the fifth value = α(j)×(the third value + the fourth value) / 2; where α(j) is an adjustment coefficient obtained based on the patient attributes corresponding to category j;

[0026] Determine that the sixth value = (the first value - the second value) / the second value;

[0027] Determine that the standard performance value of category j = min{the second value×(1 + the sixth value×the fifth value), the first value×(1 - the third value)}.

[0028] Optionally, determine the performance of doctor i based on the mean and standard deviation of the diagnosis and treatment performance values of each category, including:

[0029] Determine the similarity degree of the hospital with respect to each diagnosis group;

[0030] Determine the seventh value as the mean of the similarity degree of the hospital with respect to each diagnosis group;

[0031] Determine the eighth value as the mean of the standard performance values of each category;

[0032] Determine the performance determination result of doctor i as β×(standard deviation of the diagnosis and treatment performance values of each category / mean of the diagnosis and treatment performance values of each category) / performance threshold; where β is a determination coefficient determined based on the seventh value and the eighth value.

[0033] Optionally, if the seventh value is not greater than the eighth value, then β = 1; otherwise, determine β through the following steps:

[0034] Determine the similarity degree of the department to which doctor i belongs with respect to the diagnosis group;

[0035] Determine the proportion of each diagnosis group involved in the target diagnosis and treatment data; where the proportion of any diagnosis group involved in the target diagnosis and treatment data is the number of target diagnosis and treatment data involving any diagnosis group / the number of diagnosis and treatment data of the department to which doctor i belongs involving any diagnosis group;

[0036] Determine the ninth value as the number of diagnosis groups involved in the target diagnosis and treatment data with a proportion not less than the proportion threshold; where the proportion threshold is determined based on the diagnosis and treatment data of the department to which doctor i belongs;

[0037] β = max{softmax{(mean of the similarity degree of the department to which doctor i belongs with respect to the diagnosis group / the seventh value)×(the ninth value / the number of diagnosis groups involved in the target diagnosis and treatment data)}, coefficient minimum threshold}; where softmax{} is a normalization function.

[0038] Optionally, determine the auxiliary doctor and the corresponding benchmark data based on the performance determination result, and provide the corresponding benchmark data to the auxiliary doctor, including:

[0039] Determine the auxiliary value of each doctor; where the auxiliary value of any doctor i = (performance determination result of doctor i / mean of the performance determination results of the doctors related to the diagnosis group corresponding to doctor i)×(1 + title coefficient of doctor i×department coefficient of doctor i);

[0040] Determine the doctor with an auxiliary value less than the auxiliary threshold as the auxiliary doctor;

[0041] Determine the benchmark data based on the doctors related to the diagnosis group corresponding to the auxiliary doctor.

[0042] Optionally, benchmark data is determined according to the doctors related to the diagnosis group corresponding to the assisting doctor, including:

[0043] Determine the diagnosis and treatment data of the doctor with the best performance determination result among the doctors related to the diagnosis group corresponding to the assisting doctor as the benchmark data; or,

[0044] Among the doctors related to the diagnosis group corresponding to the assisting doctor, determine the diagnosis and treatment data of the doctor with the most similar patients to those in the diagnosis group corresponding to the assisting doctor and the best performance determination result as the benchmark data.

[0045] Optionally, the computer program involved in the medical performance determination system is stored in a memory;

[0046] The memory is located inside an electronic device, and the electronic device further includes: a processor;

[0047] The processor is configured to execute the computer program involved in the medical performance determination system to implement the medical performance determination system.

[0048] Optionally, the computer program involved in the medical performance determination system is stored in a computer-readable storage medium;

[0049] The computer program involved in the medical performance determination system is executed by a processor to implement the medical performance determination system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic structural diagram of a medical performance determination system provided by an embodiment of the present application;

[0051] Figure 2 It is a schematic diagram of an admission record provided by an embodiment of the present application;

[0052] Figure 3 It is a schematic diagram of a medical path provided by an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of a diagnosis and treatment link provided by an embodiment of the present application;

[0054] Figure 5 It is a schematic diagram of the distribution of patients provided by an embodiment of the present application;

[0055] Figure 6 It is a schematic diagram of the case situation in medical data provided by an embodiment of the present application;

[0056] Figure 7 It is a schematic diagram of the distribution of doctors provided by an embodiment of the present application;

[0057] Figure 8A schematic diagram showing the distribution of medical data for diagnosing the "ES2 pulmonary mycosis" diagnostic group in a department provided by an embodiment of the present application;

[0058] Figure 9 A schematic diagram showing the distribution of DRG departments provided by an embodiment of the present application. Detailed implementation manners

[0059] To better explain the present invention for easy understanding, the present invention will be described in detail below with reference to the accompanying drawings through specific implementation manners.

[0060] Currently, the performance determination is carried out manually. For example, doctors summarize their work, and performance determination personnel determine the performance based on the work content summarized by doctors. Manual determination is not only prone to errors but also easily affected by external factors, resulting in low accuracy of the existing performance determination.

[0061] Based on this, the present invention relates to a medical performance determination system, which includes: a data storage module, a performance determination module, an auxiliary module, and a display module. Among them, the data storage module is used to store medical data and standard data of each diagnostic group; the medical data is the data involved in the hospital diagnosis and treatment process, and the standard data is regularly released by relevant personnel; the performance determination module is used to classify the medical data according to the diagnosing doctors to obtain the diagnosing data of each doctor; and determine the performance of each doctor through the diagnosing data of each doctor and the standard data of each diagnostic group; the auxiliary module is used to determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result, and provide the corresponding benchmark data to the auxiliary doctor; the display module is used to display medical data, standard data, performance determination data, and benchmark data. The system of the present invention can determine the performance of each doctor through the diagnosing data of each doctor and the standard data of each diagnostic group, enabling automatic determination of doctor performance, avoiding the problems of easy errors, being easily affected by external factors, and low accuracy of performance determination in manual determination.

[0062] This embodiment provides a medical performance determination system, which can be deployed in electronic devices such as computers and servers. The electronic device deploying the medical performance determination system includes a memory, which stores the computer program related to the medical performance determination system. In addition, the electronic device deploying the medical performance determination system further includes a processor, which is used to execute the computer program stored in the memory related to the medical performance determination system to implement the medical performance determination system. And / or,

[0063] The medical performance determination system provided in this embodiment is deployed in a device connected to a computer-readable storage medium, and the computer-readable storage medium stores the computer program related to the medical performance determination system. The computer program related to the medical performance determination system is executed by the processor to implement the medical performance determination system.

[0064] As Figure 1 shown, the patient-centered medical path optimization system provided in this embodiment includes: a data storage module 101, a performance determination module 102, an auxiliary module 103, and a display module 104.

[0065] 1. Data storage module 101

[0066] The data storage module is used to store medical data and the standard data of each diagnosis group.

[0067] The medical data is the data involved in the hospital diagnosis and treatment process, and the standard data is regularly released by relevant personnel.

[0068] For example, the data involved in the hospital diagnosis and treatment process is the data generated during the hospital operation, such as hospital patient data (such as name, gender, age, home address, contact information, etc.), the relevant data of each outpatient diagnosis and treatment of patients recorded by the outpatient-related systems in the hospital (such as Figure 2 the admission records, test data, examination data, etc. shown), the relevant data of each inpatient diagnosis and treatment of patients recorded by the inpatient-related systems (such as inpatient cases, daily test data, daily examination data, daily medication data, etc.), and the respective relevant data recorded by each business system (such as the drug procurement-related data and drug distribution-related data recorded by the pharmacy-related business system).

[0069] The standard data can be generated by the hospital or non-hospital. The standard data is the relevant data used to provide guidance, standards, benchmarks, norms, policies, opinions, notices, etc., such as the DRG (Diagnosis Related Groups) / DIP (Disease Severity and Intervention Complexity Points) - related data released by the medical-related departments, the standard data of each diagnosis group (such as the cost standard of each diagnosis group, the diagnosis and treatment duration standard of each diagnosis group, the diagnosis and treatment path-related standard of each diagnosis group, etc.), the drug centralized procurement-related data, the implementation guidelines and standard norms announced by the hospital.

[0070] In specific implementation, the data storage module 101 can be the memory of the electronic device deploying the medical performance determination system provided in this embodiment, or a hard disk, etc., or a cloud memory connected to the electronic device deploying the medical performance determination system provided in this embodiment.

[0071] 2. Performance determination module 102

[0072] A performance determination module is used to classify medical data by treating doctors to obtain the medical data of each doctor. The performance of each doctor is determined based on the medical data of each doctor and the standard data of each diagnosis group.

[0073] Each time a patient visits a doctor, the doctor will record the patient information, disease-related information, and mark the treating doctor at the same time. All behaviors such as medication and examination will also mark the patient information, disease-related information, and treating doctor. Therefore, when the performance determination module classifies medical data by treating doctors to obtain the medical data of each doctor, it can extract the treating doctor in each medical data, and then classify the medical data according to the doctor identifier (such as ID number), so as to obtain the medical data of each treating doctor.

[0074] It should be noted that on the one hand, due to the large amount of medical data, and on the other hand, due to the timeliness of performance determination (such as only determining the performance for the current month or year, etc.), the medical data mentioned in this embodiment can be the medical data for a recent period of time, such as the medical data for the most recent month, year, etc., so as to ensure that the system provided in this embodiment can determine the performance that most conforms to the current situation of the doctor. Similarly, the standard data also has timeliness, and the standard data mentioned in this embodiment is the latest standard data.

[0075] When the performance determination module determines the performance of each doctor based on the medical data of each doctor and the standard data of each diagnosis group, for any doctor i, its performance can be determined through the following steps:

[0076] 201. Determine all the medical data of doctor i as the target medical data.

[0077] 202. Determine the patients, diagnosis groups, and treatment links corresponding to each target medical data.

[0078] Among them, the target medical data is composed of the medical data of each treatment node.

[0079] For any target medical data, the nodes in its treatment link correspond one-to-one with the treatment nodes in any target medical data, the relationship between the nodes in its treatment link is the same as the treatment order of each treatment node, and the data attribute values of the nodes in the treatment link are the medical data of their corresponding treatment nodes.

[0080] 1. Patient

[0081] For any target medical data, since it records patient information, the patient information in any target medical data can be directly extracted, and then the patient corresponding to any target medical data can be obtained.

[0082] 2. Diagnosis group

[0083] For any target diagnosis and treatment data, since it records patient information, condition-related information, etc., the condition-related information in any target diagnosis and treatment data can be extracted to determine the diagnosis group.

[0084] For example, any target diagnosis and treatment data is Figure 2 the shown admission record, then the performance determination module extracts Figure 2 the current medical history, past medical history, etc. in it, and obtains the diagnosis group of this medical data through the DRG grouping scheme.

[0085] 3. Diagnosis and treatment link

[0086] For any target diagnosis and treatment data, a diagnosis and treatment link can be obtained. For example, any target diagnosis and treatment data is the data of a certain hospitalization of patient 1, the attending doctor during the hospitalization is doctor 1, and the patient was hospitalized for 5 days. Then each day corresponds to a medical node, and the medical path consists of 5 nodes corresponding to 5 days, which is formed according to the diagnosis and treatment order (i.e., the admission date), as Figure 3 shown. Each medical node corresponds to the relevant medical data of that day.

[0087] Through Figure 3 the shown medical path, the Figure 4 shown diagnosis and treatment link can be obtained.

[0088] Figure 4 The nodes in the Figure 3 shown diagnosis and treatment link correspond one-to-one with the diagnosis and treatment nodes of the Figure 4 shown medical path (for example, the 1st day corresponds to node 1, the 2nd day corresponds to node 2, the 3rd day corresponds to node 3, the 4th day corresponds to node 4, and the 5th day corresponds to node 5). Figure 3 The relationship between the nodes in the Figure 4 shown diagnosis and treatment link is the same as the diagnosis and treatment order of the diagnosis and treatment nodes of the Figure 3 shown medical path. Moreover,

[0089] 203. Based on the patient, cluster the diagnosis and treatment links corresponding to the target diagnosis and treatment data.

[0090] The target diagnosis and treatment data is all the diagnosis and treatment data of doctor i, which is the data of the diagnosis and treatment processes of all the patients diagnosed by doctor i. In step 203, the performance determination module will cluster all the target diagnosis and treatment data of doctor i again according to the patients, so that the diagnosis and treatment data of each patient by doctor i is grouped into one category, and then the diagnosis and treatment links corresponding to the diagnosis and treatment data are also grouped into one category. Each category contains the diagnosis and treatment link of the diagnosis and treatment data of doctor i for a certain patient.

[0091] For example, for any patient j diagnosed by doctor i, first obtain the diagnostic data of patient j in the target diagnostic data, and then form a category with the diagnostic links corresponding to the obtained diagnostic data, denoted as category j.

[0092] 204. For each category, determine the diagnostic performance value according to the diagnostic links, diagnostic groups, and standard data of each diagnostic group in the category.

[0093] Among them, the diagnostic performance value Dvij(u) of any diagnostic link u in category j = (similarity between any diagnostic link u in category j and the standard data of the diagnostic group of diagnostic link u) / standard performance value of category j.

[0094] The standard performance value of category j is determined according to the patient corresponding to category j, the department and professional title of doctor i.

[0095] 1. Calculation process of the similarity between any diagnostic link u in category j and the standard data of the diagnostic group of diagnostic link u.

[0096] The similarity can be achieved through existing feature comparison schemes.

[0097] For example, pre-construct feature indicators of diagnostic links, such as the age, condition, test results, examination results, diagnosis, length of hospital stay, daily diagnostic situation, cost, medication, professional title of the attending doctor, etc. of the patient (the features here can adopt existing evaluation features).

[0098] The performance determination module first obtains the feature vector of diagnostic link u based on the pre-constructed feature indicators of diagnostic links. Then, based on the pre-constructed feature indicators of diagnostic links, obtain the standard feature indicators of the standard data of the diagnostic group of diagnostic link u (i.e., the diagnostic group corresponding to the target diagnostic data of diagnostic link u) (this feature indicator can first determine the standard data related to the diagnostic group of diagnostic link u, and then extract it from this standard data). Subsequently, calculate the distance (such as Euclidean distance) between the two feature vectors, and this distance value is the similarity between any diagnostic link u in category j and the standard data of the diagnostic group of diagnostic link u.

[0099] Among them, the standard feature indicator represents the standard path for doctors to diagnose diseases related to the diagnostic group of diagnostic link u (such as the standard length of hospital stay for doctors to diagnose diseases related to the diagnostic group of diagnostic link u, the daily examination content, medication situation, etc.). The standard feature indicator only reflects the recommended diagnostic link situation. The recommended diagnostic link is only guiding and not necessarily to be executed. Therefore, the recommended diagnostic link can be the optimal path or the common diagnostic link for general patients, etc.

[0100] Any diagnosis and treatment link u in class j is the real diagnosis and treatment data of doctor i treating patient j. The similarity between any diagnosis and treatment link u in class j and the standard data of the diagnosis group of diagnosis and treatment link u is the matching degree between this real diagnosis and treatment data and the standard.

[0101] 2. The calculation process of the standard performance value of class j.

[0102] 301. Determine the similarity between the diagnosis and treatment data of each doctor in the department where doctor i belongs and the standard data of the diagnosis group of the corresponding patients in class j.

[0103] The similarity calculation process is similar to the calculation process of "the similarity between any diagnosis and treatment link u in class j and the standard data of the diagnosis group of diagnosis and treatment link u", and will not be elaborated here.

[0104] For example, if the department where doctor i belongs is the emergency department, and there are two doctors in the emergency department, namely doctor 1 and doctor 2, and the diagnosis group of the corresponding patients in class j is "ES2 pulmonary mycosis", then the similarity between each diagnosis and treatment data of doctor 1 and the standard data of "ES2 pulmonary mycosis" will be determined, and the average value of the similarities between all diagnosis and treatment data and the standard data of "ES2 pulmonary mycosis" will be determined as the similarity between the diagnosis and treatment data of doctor 1 and the standard data of "ES2 pulmonary mycosis". Determine the similarity between each diagnosis and treatment data of doctor 2 and the standard data of "ES2 pulmonary mycosis", and the average value of the similarities between all diagnosis and treatment data and the standard data of "ES2 pulmonary mycosis" will be determined as the similarity between the diagnosis and treatment data of doctor 2 and the standard data of "ES2 pulmonary mycosis".

[0105] It should be noted that if there are multiple diagnosis groups for the corresponding patients in class j (that is, the corresponding patients in class j have multiple diseases), then the similarity between the diagnosis and treatment data of each doctor in the department where doctor i belongs and the standard data of each diagnosis group of the corresponding patients in class j will be determined, and then the average value of the similarities between the diagnosis and treatment data of a certain doctor in the department where doctor i belongs and the standard data of each diagnosis group of the corresponding patients in class j will be determined as the similarity between the diagnosis and treatment data of this doctor and the standard data of the diagnosis group of the corresponding patients in class j.

[0106] 302. Determine the first value as the average value of the similarities of all doctors in the department where doctor i belongs.

[0107] For example, determine the first value = (the similarity between the diagnosis and treatment data of doctor 1 and the standard data of "ES2 pulmonary mycosis" + the similarity between the diagnosis and treatment data of doctor 2 and the standard data of "ES2 pulmonary mycosis") / 2.

[0108] The first value represents the degree of match between the average diagnosis and treatment process in the department to which doctor i belongs and the standard process. The higher the first value, the higher the overall performance of the doctors in the department to which doctor i belongs (this performance is reflected by the degree of similarity with the standard. The higher the similarity, the more the doctor's medical behavior conforms to the standard, and the higher the performance).

[0109] 303, determining the second value as the average of the similarities of all doctors in the department to which doctor i belongs and whose professional title is the same as doctor i.

[0110] A doctor's professional title can be determined according to the existing professional title evaluation standards.

[0111] For example, professional titles include: resident physician, attending physician, associate chief physician, chief physician, etc. The evaluation criteria are:

[0112] Resident physician: Complete standardized residency training and initially acquire the ability to independently diagnose and treat common diseases.

[0113] Attending physician: can handle more complex illnesses and provide guidance to junior physicians.

[0114] Associate Chief Physician: Has profound attainments in this professional field and can solve difficult diseases.

[0115] Chief Physician: He is the leader of this profession and has high authority in both academic and clinical aspects.

[0116] The professional title is obtained based on the comprehensive ability of the doctor and is a recognition of the doctor's professional ability. The second value represents the average similarity of doctors with the same professional title as doctor i. The lower the second value, the lower the overall performance of doctors with the corresponding professional title of doctor i.

[0117] 304. Determine the third value as the standard deviation of the similarities of all doctors in the department to which doctor i belongs.

[0118] The standard deviation is calculated using the existing standard deviation formula.

[0119] The third value represents the performance gap between doctors in the department to which doctor i belongs. The larger the third value, the greater the performance gap between doctors in the department to which doctor i belongs. Some doctors have higher performance, while others have lower performance, that is, the performance of doctors fluctuates greatly. The smaller the third value, the smaller the performance gap between doctors in the department to which doctor i belongs, and the performance difference between doctors is not large.

[0120] 305, determining the fourth value as the standard deviation of the similarity of all doctors in the department to which doctor i belongs who have the same professional title as doctor i.

[0121] The fourth value characterizes the performance gap among doctors with the same professional title of doctor i. The larger the fourth value, the greater the performance gap among doctors with the same professional title, indicating that some doctors have relatively high performance and some have relatively low performance, that is, the doctor performance fluctuates greatly. The smaller the fourth value, the smaller the performance gap among doctors with the same professional title, and the performance of doctors is not very different from each other.

[0122] 306. If the first value is not greater than the second value, then the standard performance value of class j is determined as the second value. If the first value is greater than the second value, then the standard performance value of class j is determined according to the third value and the fourth value.

[0123] Doctors in the same department are composed of doctors with different professional titles, such as including one chief physician, two deputy chief physicians, 5 attending physicians, etc. The higher the professional title, the stronger the ability, and then their performance should not be low, which is manifested in the higher similarity between their diagnosis and treatment data and the standard data.

[0124] If the first value is not greater than the second value, it means that the overall performance of the department to which doctor i belongs is not higher than the overall performance of doctors with the same professional title in the department to which doctor i belongs. That is, in the department to which doctor i belongs, the performance of doctors with the same professional title as doctor i is better. This may be due to their better comprehensive ability (i.e., higher professional title), such as doctor i is a chief physician, or the academic leader of the department. At this time, the overall performance of doctors with the same professional title in the department to which doctor i belongs is a benchmark value for determining the current performance of doctor i. That is to say, the performance of doctor i is not compared with the situation of all doctors in the department to which he belongs, but with the situation of doctors with the same professional title as him to determine the level of doctor i's current performance. Therefore, the average similarity corresponding to this professional title is used as the standard performance value of class j (that is, the standard performance value of class j is determined as the second value).

[0125] If the first value is greater than the second value, it means that the overall performance of the department to which doctor i belongs is higher than the overall performance of doctors with the same professional title in the department to which doctor i belongs. That is, in the department to which doctor i belongs, the performance of doctors with the same professional title as doctor i is worse. This may be due to their lack of ability (such as lower professional title). At this time, the environment to which doctor i belongs (such as the performance situation among doctors in the department to which doctor i belongs and the performance situation among doctors with the same professional title in the department to which doctor i belongs) has a greater impact on his performance. Therefore, the standard performance value of class j will be determined according to the third value and the fourth value.

[0126] Specifically, the process of determining the standard performance value of class j according to the third value and the fourth value is as follows:

[0127] (1) Determine the fifth value = α(j) × (the third value + the fourth value) / 2.

[0128] Among them, α(j) is an adjustment coefficient obtained based on the patient attributes corresponding to class j. This adjustment coefficient is related to patient characteristics and is obtained through big data learning of sample data or work experience. For example, different ages, different symptoms, and different underlying diseases have a greater impact on the treatment of the current diagnosis group disease of patients. For patients in the same diagnosis group, those with a relatively younger age will recover from depression faster than those with a relatively older age, and the medications in their treatment links may be different, and thus the treatment links will also vary. α(j) is a coefficient that comprehensively considers the individual differences of patients.

[0129] Since the performance of doctor i is jointly affected by the overall business level of the department and the business level that doctor i should achieve (represented by doctors with the same professional title in the department to which doctor i belongs), the fifth value is thus obtained by comprehensively considering the performance fluctuations of doctors in the department to which doctor i belongs (the performance fluctuations of doctors in the department to which doctor i belongs reflect the overall business level of the department) and according to the performance fluctuations of doctors with the same professional title in the department to which doctor i belongs (the performance fluctuations of doctors with the same professional title in the department to which doctor i belongs reflect the business level that doctor i should achieve). It reflects the influence of external factors (department and professional title) on the performance of doctor i.

[0130] (2) Determine the sixth value = (the first value - the second value) / the second value.

[0131] The first value - the second value represents the gap between the overall level of the department to which doctor i belongs and the level corresponding to doctor i's professional title. The sixth value represents the ratio of this gap to the level corresponding to doctor i's professional title. This ratio actually represents the position of the level corresponding to doctor i's professional title in the department to which doctor i belongs.

[0132] The larger the sixth value, the larger the first value - the second value (that is, the gap between the average performance of doctors in the department to which doctor i belongs and the average performance of doctors corresponding to doctor i's professional title is relatively large), and the level corresponding to doctor i's professional title is at a relatively low performance position in the department to which doctor i belongs, then doctor i's professional title is very low; or the second value is relatively small, that is, the average performance of doctors corresponding to doctor i's professional title is relatively poor, and doctor i's professional title is very low. Therefore, the larger the sixth value, the lower doctor i's professional title, the insufficient basic ability, and doctor i is still in the process of learning and improving the ability.

[0133] The smaller the sixth value, the smaller the first value - the second value (that is, the gap between the average performance of doctors in the department to which doctor i belongs and the average performance of doctors corresponding to doctor i's professional title is relatively small), and the level corresponding to doctor i's professional title is at a relatively high performance position in the department to which doctor i belongs, then doctor i's professional title is relatively high; or the second value is relatively large, that is, the average performance of doctors corresponding to doctor i's professional title is relatively high, and doctor i's professional title is relatively high. Therefore, the smaller the sixth value, the higher doctor i's professional title, the relatively high ability of doctor i, and the stability.

[0134] The sixth value reflects the doctor i's ability and stability during the diagnosis and treatment process from the perspective of the doctor i's professional title. The sixth value reflects the influence of internal factors (such as the abilities that the doctor himself should possess and the stability of the doctor's diagnosis and treatment level during the medical diagnosis process) on the performance of doctor i.

[0135] (3) Determine the standard performance value of class j = min{the second value × (1 + the sixth value × the fifth value), the first value × (1 - the third value)}.

[0136] The second value reflects the performance of doctor i from the overall situation of doctors with the same professional title in the department to which doctor i belongs. This value is a standard value and does not involve the characteristics of doctor i. This characteristic can be reflected by the sixth value × the fifth value, and the sixth value × the fifth value reflects the influence on doctor i from both external and internal factors.

[0137] The first value × (1 - the third value) is the average performance of all doctors in the department to which doctor i belongs considering the performance fluctuations of all doctors in the department to which doctor i belongs.

[0138] The standard performance that doctor i should have is reflected by the minimum value between the second value × (1 + the sixth value × the fifth value) and the first value × (1 - the third value). Therefore, determine the standard performance value of class j = min{the second value × (1 + the sixth value × the fifth value), the first value × (1 - the third value)}.

[0139] The diagnosis and treatment performance value Dvij(u) of any diagnosis and treatment link u in any class j = (the similarity between any diagnosis and treatment link u in class j and the standard data of the diagnosis group of diagnosis and treatment link u) / the standard performance value of class j. It reflects the relationship between the matching degree of the diagnosis and treatment path u of doctor i treating patient j and the standard and the standard matching degree of doctor i treating patient j. The larger this value is, the more in line with the standard the diagnosis and treatment path u of doctor i treating patient j is.

[0140] 205. Determine the performance of doctor i according to the mean and standard deviation of the diagnosis and treatment performance values of each class.

[0141] The performance determination module can determine the performance of doctor i according to the mean and standard deviation of the diagnosis and treatment performance values of each class through the following steps.

[0142] 401. Determine the similarity degree of the hospital relative to each diagnosis group.

[0143] The similarity degree can be determined based on the similarity. The similarity calculation process can be similar to "the calculation process of the similarity between any diagnosis and treatment link u in class j and the standard data of the diagnosis group of diagnosis and treatment link u", which will not be elaborated here.

[0144] For example, determine the similarity between the diagnosis and treatment links corresponding to each diagnosis and treatment data in the hospital and the standard data of the diagnosis group of that link, and then use the average value of all similarities of each diagnosis group as the degree of similarity of the hospital relative to each diagnosis group.

[0145] For example, the diagnosis and treatment links corresponding to each diagnosis and treatment data in the hospital include Link A, Link B, and Link C. The diagnosis group of Link A is Diagnosis Group 1, the diagnosis group of Link B is Diagnosis Group 2, and the diagnosis group of Link C is Diagnosis Group 1. Then determine the similarity between Link A and the standard data of Diagnosis Group 1, the similarity between Link B and the standard data of Diagnosis Group 2, and the similarity between Link C and the standard data of Diagnosis Group 1, and then use the average value of the three similarities as the degree of similarity of the hospital relative to each diagnosis group.

[0146] 402. Determine the seventh value as the average value of the degree of similarity of the hospital for each diagnosis group.

[0147] The seventh value characterizes the matching degree between the average diagnosis and treatment process of the hospital and the standard process. The lower the seventh value, the lower the overall diagnosis and treatment performance of the hospital (this performance is reflected by the degree of similarity with the standard, and the higher the similarity, the higher the performance).

[0148] 403. Determine the eighth value as the average value of the standard performance values of each category.

[0149] The eighth value characterizes the average standard performance that Doctor i should have. The lower the eighth value, the lower the standard performance of Doctor i.

[0150] 404. Determine the performance determination result of Doctor i as β×(standard deviation of the diagnosis and treatment performance values of each category / average value of the diagnosis and treatment performance values of each category) / performance threshold.

[0151] The standard deviation of the diagnosis and treatment performance values of each category / average value of the diagnosis and treatment performance values of each category characterizes the difference in the matching degree between each diagnosis and treatment process of Doctor i and the standard process. The larger this value, the greater the difference in the matching degree between each diagnosis and treatment process and the standard process. For example, if the matching degree of a certain diagnosis and treatment process with the standard process is very high and the matching degree of a certain diagnosis and treatment process with the standard process is very low, it reflects the lack of stability in Doctor i's diagnosis and treatment. The smaller this value, the smaller the difference in the matching degree between each diagnosis and treatment process and the standard process, that is, the matching degree between each diagnosis and treatment process and the standard process is relatively consistent, which reflects the higher stability in Doctor i's diagnosis and treatment.

[0152] The performance threshold is a pre-set value, which reflects the basic requirement for doctor stability in performance appraisal. The performance threshold is determined according to the accuracy of performance determination. The larger this value, the stricter the performance determination and the higher the accuracy, and thus the higher the requirements for doctors.

[0153] (Standard deviation of various types of diagnosis and treatment performance values / Mean value of various types of diagnosis and treatment performance values) / Performance threshold characterizes the stability ratio of doctor i to the stability requirement of performance assessment. The larger this value, the higher the doctor's performance. The smaller this value, the lower the doctor's performance. This low performance is due on the one hand to the mismatch between the diagnosis and treatment process and the standard, and on the other hand to the insufficient stability of each diagnosis and treatment process.

[0154] Then, using β representing the basic performance of doctor i itself as a weight to adjust (Standard deviation of various types of diagnosis and treatment performance values / Mean value of various types of diagnosis and treatment performance values) / Performance threshold, the performance determination result that conforms to doctor i's own performance is obtained.

[0155] Among them, β is a determination coefficient determined according to the seventh value and the eighth value. This determination coefficient determines the standard performance ratio of doctor i from the perspective of the hospital and doctor i, and this ratio is an embodiment of doctor i's own basic performance.

[0156] In specific implementation, if the seventh value is not greater than the eighth value, it indicates that the overall performance of the hospital doctors is lower than the standard performance of doctor i. That is to say, doctor i is a doctor with higher ability in the hospital. At this time, (Standard deviation of various types of diagnosis and treatment performance values / Mean value of various types of diagnosis and treatment performance values) / Performance threshold will not be adjusted, that is, β = 1.

[0157] If the seventh value is greater than the eighth value, it indicates that the overall performance of the hospital doctors is not lower than the standard performance of doctor i. That is to say, doctor i is a doctor with lower ability in the hospital. At this time, β is determined through the following steps:

[0158] 501. Determine the similarity degree of the department to which doctor i belongs relative to the diagnosis group.

[0159] The similarity degree here can also be determined based on the similarity. The similarity calculation process can be similar to "determining the similarity degree of the hospital relative to each diagnosis group", which will not be elaborated here.

[0160] For example, determine the similarity between the diagnosis and treatment links corresponding to each diagnosis and treatment data in the department to which doctor i belongs and the standard data of the diagnosis group of this link, and then take the mean value of all similarities of each diagnosis group as the similarity degree of the department to which doctor i belongs relative to the diagnosis group.

[0161] For example, the diagnosis and treatment links corresponding to each diagnosis and treatment data in the department to which doctor i belongs include link A and link B. The diagnosis group of link A is diagnosis group 1, and the diagnosis group of link B is diagnosis group 2. Then determine the similarity between link A and the standard data of diagnosis group 1, and the similarity between link B and the standard data of diagnosis group 2, and then take the mean value of the two similarities as the similarity degree of the department to which doctor i belongs relative to the diagnosis group.

[0162] 502. Determine the proportion of each diagnosis group involved in the target diagnosis and treatment data.

[0163] Among them, the proportion of any diagnosis group involved in the target diagnosis and treatment data is the number of target diagnosis and treatment data involved in any diagnosis group / the number of diagnosis and treatment data of any diagnosis group involved in the department to which doctor i belongs.

[0164] The target diagnosis and treatment data are all the diagnosis and treatment data of doctor i. The proportion of any diagnosis group involved in the target diagnosis and treatment data represents the diagnosis and treatment proportion of doctor i in diagnosing diseases related to any diagnosis group in his / her department. The larger this value is, the more doctor i focuses on diagnosing diseases related to any diagnosis group in this department.

[0165] 503. Determine the ninth value as the number of diagnosis groups involved in the target diagnosis and treatment data with a proportion not less than the proportion threshold.

[0166] Among them, the proportion threshold is determined according to the diagnosis and treatment data involved in the department to which doctor i belongs. This value is comprehensively determined by relevant personnel according to the situation of the department (such as whether it is a characteristic consulting room of the hospital, etc.) and the situation of the diagnosis and treatment data (such as the number of patients, whether most patients are critically ill patients, etc.). This proportion threshold represents the business performance of doctor i relative to each diagnosis group. If the diagnosis and treatment proportion of doctor i in diagnosing diseases related to any diagnosis group in his / her department is larger than the proportion threshold, it means that doctor i is the main doctor diagnosing diseases related to any diagnosis group, and the higher his / her business performance is, the more it means that doctor i mainly diagnoses diseases related to any diagnosis group.

[0167] The ninth value is the number of diagnosis groups mainly diagnosed by doctor i.

[0168] 504. β = max{softmax{(the average similarity degree of the department to which doctor i belongs relative to the diagnosis group / the seventh value) × (the ninth value / the number of diagnosis groups involved in the target diagnosis and treatment data)}, the minimum coefficient threshold}.

[0169] Among them, softmax{} is a normalization function.

[0170] The average similarity degree of the department to which doctor i belongs relative to the diagnosis group / the seventh value represents the performance of doctor i relative to the hospital. The larger this value is, the higher the performance of doctor i.

[0171] The ninth value / the number of diagnosis groups involved in the target diagnosis and treatment data represents the proportion of the diagnosis groups mainly diagnosed by doctor i. The larger this value is, the more diseases doctor i is good at diagnosing, and the more comprehensive doctor i's medical ability is.

[0172] (Mean of the similarity degree of the department where doctor i belongs relative to the diagnosis group / Seventh value) × (Ninth value / Number of diagnosis groups involved in the target diagnosis and treatment data) reflects the basic performance of doctor i from two aspects: doctor i compared to the hospital and his medical capabilities. softmax{(Mean of the similarity degree of the department where doctor i belongs relative to the diagnosis group / Seventh value) × (Ninth value / Number of diagnosis groups involved in the target diagnosis and treatment data)} is the normalized value of (Mean of the similarity degree of the department where doctor i belongs relative to the diagnosis group / Seventh value) × (Ninth value / Number of diagnosis groups involved in the target diagnosis and treatment data).

[0173] The minimum coefficient threshold is a benchmark value set in advance. To prevent the situation where the basic performance of doctor i is relatively low (such as an intern doctor), resulting in β being too small and then excessive adjustment.

[0174] The performance determination module determines the performance of doctor i based on the matching situation between the diagnosis and treatment data of doctor i and the standard, and the standard performance situation of doctor i (this standard performance is the objective impact on doctor i caused by external factors and internal factors). Since the determination not only considers the medical situation of doctor i himself, but also considers the objective factors of doctor i, an accurate determination result can be obtained.

[0175] 3. Auxiliary module 103

[0176] The auxiliary module is used to determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result, and provide the corresponding benchmark data to the auxiliary doctor.

[0177] The auxiliary module can determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result through the following steps, and provide the corresponding benchmark data to the auxiliary doctor:

[0178] 601. Determine the auxiliary value of each doctor.

[0179] Among them, the auxiliary value of any doctor i = (Performance determination result of doctor i / Mean of the performance determination results of the doctors related to the diagnosis group corresponding to doctor i) × (1 + Professional title coefficient of doctor i × Department coefficient of doctor i).

[0180] Performance determination result of doctor i / Mean of the performance determination results of the doctors related to the diagnosis group corresponding to doctor i characterizes the performance situation of doctor i. The larger this value is, the better the performance of doctor i.

[0181] The professional title coefficient of doctor i is a value between 0 and 1, which is set in advance by relevant personnel. This value characterizes the self-adjustment ability of the doctor corresponding to the professional title. The higher the professional title, the stronger the ability of the doctor with this professional title. If there is a poor performance (such as a large gap from the standard), he can quickly and actively find the problem and make self-adjustment, thereby improving the performance. Therefore, the higher the professional title, the larger the professional title coefficient.

[0182] The department coefficient of doctor i is a value between 0 and 1, which is pre-set for relevant personnel. This value characterizes the self-adjustment ability of the doctor corresponding to the department. The more excellent the department (such as a key department in a hospital), the better the ability, quality, and teamwork of the doctors in this department. If there is a poor performance (such as a large gap between a doctor's medical behavior and the standard), their colleagues and / or themselves can quickly and actively find the problem and make adjustments, thereby improving performance. Therefore, the more important the department that doctor i belongs to, the greater the department coefficient of doctor i.

[0183] The mean value of the performance determination result of doctor i / the performance determination results of the relevant doctors in the diagnosis group corresponding to doctor i is increased by multiplying the professional title coefficient of doctor i by the department coefficient of doctor i to obtain the auxiliary value of any doctor i, that is, the auxiliary value of any doctor i = (the performance determination result of doctor i / the mean value of the performance determination results of the relevant doctors in the diagnosis group corresponding to doctor i) × (1 + the professional title coefficient of doctor i × the department coefficient of doctor i).

[0184] The auxiliary value of any doctor i characterizes whether doctor i needs to rely on external forces (such as providing benchmark data) to help improve performance. The larger the auxiliary value, the less external assistance is needed.

[0185] 602. Determine the assisted doctors as those with an auxiliary value less than the auxiliary threshold.

[0186] The auxiliary threshold is an empirical value set in advance, which can be determined according to the assistance intensity. The greater the assistance intensity, the greater the auxiliary threshold. In this way, more assisted doctors will provide corresponding benchmark data for more doctors.

[0187] 603. Determine the benchmark data according to the relevant doctors in the diagnosis group corresponding to the assisted doctors.

[0188] For example, determine the diagnosis and treatment data of the doctor with the best performance determination result among the relevant doctors in the diagnosis group corresponding to the assisted doctor as the benchmark data. Or, among the relevant doctors in the diagnosis group corresponding to the assisted doctor, determine the diagnosis and treatment data of the doctor with the most similar patients to those in the diagnosis group corresponding to the assisted doctor and the best performance determination result as the benchmark data.

[0189] In addition, other methods can also be used to determine the benchmark data, such as determining the diagnosis and treatment data of the department director as the benchmark data, etc.

[0190] 4. Display module 104

[0191] The display module is used to display medical data, standard data, performance determination data, and benchmark data.

[0192] For example, medical data includes all medical-related data such as doctor information, patient information, case information, department distribution, drug information, and the distribution of medical data in departments.

[0193] Such as the display module displays Figure 5 The patient distribution shown, Figure 6 The case situation in the medical data shown, Figure 7 The doctor distribution shown, Figure 8 The distribution of medical data of the diagnosis group "ES2 pulmonary mycosis" in departments shown, Figure 9 The DRG department distribution shown, etc.

[0194] The standard data can be announcements, data, etc. released by relevant units. The medical paths for each diagnosis group are such as the medical paths for each doctor for each patient and the optimized medical paths.

[0195] The performance determination data can be the performance determination results of the performance determination module for each doctor and the relevant data generated during the performance determination process.

[0196] The benchmark data can be the benchmark data determined by the auxiliary module and the relevant data generated during the benchmark data determination process.

[0197] The display module can display all data. In specific implementation, different data can be displayed according to conditions such as the level and authorization of the display object. For example, only display the relevant data of a certain doctor's department for a certain doctor, etc., to achieve flexible and secure display of data.

[0198] This embodiment relates to a medical performance determination system, which includes: a data storage module, a performance determination module, an auxiliary module, and a display module; wherein, the data storage module is used to store medical data and the standard data of each diagnosis group; the medical data is the data involved in the hospital diagnosis and treatment process, and the standard data is regularly released by relevant personnel; the performance determination module is used to classify the medical data according to the treating doctors to obtain the treating data of each doctor; and perform performance determination on each doctor through the treating data of each doctor and the standard data of each diagnosis group; the auxiliary module is used to determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result and provide the corresponding benchmark data to the auxiliary doctor; the display module is used to display medical data, standard data, performance determination data, and benchmark data. The system of this embodiment can perform performance determination on each doctor through the treating data of each doctor and the standard data of each diagnosis group, enabling automatic determination of doctor performance, avoiding problems such as easy errors, being easily affected by external factors, and low accuracy in performance determination in manual determination.

[0199] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods or systems are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the system process of the present invention is not limited to the specific modules and steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present invention.

[0200] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0201] Finally, it should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A medical performance determination system, characterized in that, The system includes: a data storage module, a performance determination module, an auxiliary module, and a display module; Among them, the data storage module is used to store medical data and standard data of each diagnosis group; the medical data is the data involved in the hospital diagnosis and treatment process, and the standard data is regularly released by relevant personnel; The performance determination module is used to classify the medical data by treating doctors to obtain the diagnosis and treatment data of each doctor; determine the performance of each doctor through the diagnosis and treatment data of each doctor and the standard data of each diagnosis group; The auxiliary module is used to determine the auxiliary doctor and the corresponding benchmark data according to the performance determination result, and provide the corresponding benchmark data to the auxiliary doctor; The display module is used to display medical data, standard data, performance determination data, and benchmark data.

2. The system according to claim 1, characterized in that, The performance determination of each doctor through the diagnosis and treatment data of each doctor and the standard data of each diagnosis group includes: For any doctor i, perform performance determination on him through the following steps: Determine all the diagnosis and treatment data of doctor i as the target diagnosis and treatment data; Determine the patients, diagnosis groups, and diagnosis and treatment links corresponding to each target diagnosis and treatment data; among them, the target diagnosis and treatment data is composed of the diagnosis and treatment data of each diagnosis and treatment node; for any target diagnosis and treatment data, the nodes in its diagnosis and treatment link correspond one by one to the diagnosis and treatment nodes in any target diagnosis and treatment data, the relationship between the nodes in its diagnosis and treatment link is the same as the diagnosis and treatment order of each diagnosis and treatment node, and the data attribute value of each node in the diagnosis and treatment link is the diagnosis and treatment data of its corresponding diagnosis and treatment node; Cluster the diagnosis and treatment links corresponding to the target diagnosis and treatment data based on the patients; For each category, determine the diagnosis and treatment performance value according to the diagnosis and treatment links, diagnosis groups, and standard data of each diagnosis group in this category; among them, the diagnosis and treatment performance value Dvij(u) of any diagnosis and treatment link u in any category j = (the similarity between any diagnosis and treatment link u in category j and the standard data of the diagnosis group of diagnosis and treatment link u) / the standard performance value of category j; the standard performance value of category j is determined according to the patients corresponding to category j, the department and professional title of doctor i; Perform performance determination on doctor i according to the mean and standard deviation of the diagnosis and treatment performance values of each category.

3. The system according to claim 2, wherein The steps for determining the standard performance value of category j are as follows: Determine the similarity between the diagnosis and treatment data of each doctor in the department where doctor i belongs and the standard data of the diagnosis group of the patients corresponding to category j; Determine the first value as the mean of the similarities of all doctors in the department where doctor i belongs; Determine the second value as the mean of the similarities of all doctors with the same professional title as doctor i in the department where doctor i belongs; Determine the third value as the standard deviation of the similarities of all doctors in the department where doctor i belongs; Determine the fourth value as the standard deviation of the similarities of all doctors with the same professional title as doctor i in the department where doctor i belongs; If the first value is not greater than the second value, determine the standard performance value of category j as the second value; If the first value is greater than the second value, determine the standard performance value of category j according to the third value and the fourth value.

4. The system according to claim 3, wherein The determination of the standard performance value of category j according to the third value and the fourth value includes: Determine the fifth value = α(j) × (the third value + the fourth value) / 2; where α(j) is an adjustment coefficient obtained based on the patient attributes corresponding to category j; Determine the sixth value = (the first value - the second value) / the second value; Determine the standard performance value of class j = min{the second value × (1 + the sixth value × the fifth value), the first value × (1 - the third value)}.

5. The system according to claim 2, wherein The performance determination of doctor i according to the mean and standard deviation of the diagnosis and treatment performance values of each class includes: Determine the similarity degree of the hospital with respect to each diagnostic group; Determine the seventh value as the mean of the similarity degrees of the hospital with respect to each diagnostic group; Determine the eighth value as the mean of the standard performance values of each class; Determine the performance determination result of doctor i as β × (the standard deviation of the diagnosis and treatment performance values of each class / the mean of the diagnosis and treatment performance values of each class) / the performance threshold; where β is a determination coefficient determined according to the seventh value and the eighth value.

6. The system according to claim 5, wherein If the seventh value is not greater than the eighth value, then β = 1; otherwise, determine β through the following steps: Determine the similarity degree of the department to which doctor i belongs with respect to the diagnostic group; Determine the proportion of each diagnostic group involved in the target diagnostic and treatment data; where the proportion of any diagnostic group involved in the target diagnostic and treatment data is the number of target diagnostic and treatment data involving the any diagnostic group / the number of diagnostic and treatment data of the department to which doctor i belongs involving the any diagnostic group; Determine the ninth value as the number of diagnostic groups involved in the target diagnostic and treatment data with a proportion not less than the proportion threshold; where the proportion threshold is determined according to the diagnostic and treatment data of the department to which doctor i belongs; β = max{softmax{(the mean of the similarity degrees of the department to which doctor i belongs with respect to the diagnostic group / the seventh value) × (the ninth value / the number of diagnostic groups involved in the target diagnostic and treatment data)}, the minimum coefficient threshold}; where softmax{} is a normalization function.

7. The system according to claim 1, wherein The determination of the auxiliary doctor and the corresponding benchmark data according to the performance determination result, and providing the corresponding benchmark data to the auxiliary doctor includes: Determine the auxiliary value of each doctor; where the auxiliary value of any doctor i = (the performance determination result of doctor i / the mean of the performance determination results of the doctors related to the diagnostic group corresponding to doctor i) × (1 + the professional title coefficient of doctor i × the department coefficient of doctor i); Determine the doctor with an auxiliary value less than the auxiliary threshold as the auxiliary doctor; Determine the benchmark data according to the doctors related to the diagnostic group corresponding to the auxiliary doctor.

8. The system according to claim 7, wherein The determination of the benchmark data according to the doctors related to the diagnostic group corresponding to the auxiliary doctor includes: Determine the diagnostic and treatment data of the doctor with the optimal performance determination result among the doctors related to the diagnostic group corresponding to the auxiliary doctor as the benchmark data; or, Among the doctors related to the diagnostic group corresponding to the auxiliary doctor, determine the diagnostic and treatment data of the doctor with the most similar patients to the patients of the diagnostic group corresponding to the auxiliary doctor and the optimal performance determination result as the benchmark data.

9. The system according to claim 1, wherein The computer program involved in the medical performance determination system is stored in the memory; The memory is located inside the electronic device, and the electronic device further includes: a processor; The processor is used to execute the computer program involved in the medical performance determination system to implement the medical performance determination system.

10. The system according to claim 1, characterized in that, The computer program involved in the medical performance determination system is stored in a computer-readable storage medium; The computer program involved in the medical performance determination system is executed by the processor to implement the medical performance determination system.

Images