Medical data acquisition and analysis system and method thereof

Abstract

The invention discloses a medical data acquisition and analysis system and method, and relates to the technical field of data acquisition and analys.The medical data acquisition and analysis system comprises a medical data acquisition module, a medical data evaluation module, a processing module, a Web set display end and a data bin, the accuracy of prediction of complications of patients in hospitals is guaranteed, the treatment effect of the patients is improved, and the medical data acquisition and analysis system is suitable for popularization and application. According to the method and the system, the treatment quality of a patient is evaluated, firm data support is provided for research and judgment of a clinical demand set of a hospital, sufficiency of medical resources of the hospital is ensured, and treatment of complications of the patient is ensured while the treatment process of a new patient is ensured. The incision defect parameters, the actual complication condition and the speed of each healing stage of the patient are comprehensively considered, the accuracy of treatment quality evaluation of the patient is improved, and therefore the accuracy of follow-up rating and dividing of doctors in a hospital is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and analysis, and particularly to a medical data acquisition and analysis system and method thereof. Background Art

[0002] In the modern medical system, the acquisition and analysis of medical data have become key factors in improving the quality of medical services, promoting medical research, and facilitating public health management. With the rapid development of information technology, big data technology has been increasingly widely applied in the medical field. From clinical decision support to disease prevention, from drug research and development to personalized treatment, the importance of medical data is self-evident. Therefore, it is extremely necessary to collect and analyze medical data.

[0003] An existing technology, such as a medical data acquisition and analysis system and method disclosed in the invention patent application with the publication number of CN116580849B, by using machine learning algorithms to mine the mapping association features between the context semantic association features of each data item in the relevant data of diabetic patients in a certain area and the semantic understanding features of the physical examination data of the patient to be diagnosed, so as to conduct risk level assessment and prediction of diabetic patients, to help medical institutions and doctors intervene and treat patients at different stages.

[0004] Through the evaluation of the above solution, it can be found that the acquisition and analysis of medical data in the existing technology can meet the current requirements to a certain extent, but there are still certain defects, which are specifically reflected in the following aspects: in the existing technology, there are few dynamic monitoring data of the conditions of each patient in the hospital to predict the risk indication factors corresponding to various complications of each patient in the hospital. Due to the lack of the actual physical conditions of the patients, the probabilities of patients having complications are different. The neglect of this aspect in the existing technology makes it difficult to ensure the accuracy of the prediction of complications of patients in the hospital, thus reducing the treatment effect of patients, and it is also difficult to provide solid data support for the research and judgment of the clinical needs set of the hospital, making it difficult to ensure the adequacy of the medical resources in the hospital, affecting the treatment process of new patients and also affecting the treatment of patients' complications. At the same time, when evaluating the treatment quality of patients, the attention to the incision defect parameters, actual complication conditions, and the speed of each healing stage of patients is not high, reducing the accuracy of the evaluation of patients' treatment quality, and thus making it difficult to ensure the accuracy of the subsequent rating and classification of doctors in the hospital. Summary of the Invention

[0005] The purpose of the present invention is to provide a medical data acquisition and analysis system and method thereof, which solves the problems existing in the background art.

[0006] To solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect of the present invention, a medical data acquisition and analysis system is provided, including: a medical data acquisition module for acquiring the dynamic monitoring data of the conditions of each patient in the hospital;

[0007] A medical data evaluation module for predicting the risk indication factors corresponding to various complications of each patient in the hospital based on the dynamic monitoring data of the conditions of each patient in the hospital;

[0008] A processing module for determining the clinical demand set of the hospital based on the risk indication factors corresponding to various complications of each patient in the hospital, and evaluating the treatment quality indication factors of each patient in the hospital to determine the doctor link level label in the hospital;

[0009] A Web integrated display terminal for displaying the clinical demand set of the hospital and the doctor link level label in the hospital.

[0010] In the second aspect of the present invention, a method for implementing the medical data acquisition and analysis system of the present invention is provided, including: ST1. Acquiring the dynamic monitoring data of the conditions of each patient in the hospital;

[0011] ST2. Predicting the risk indication factors corresponding to various complications of each patient in the hospital based on the dynamic monitoring data of the conditions of each patient in the hospital;

[0012] ST3. Determining the clinical demand set of the hospital based on the risk indication factors corresponding to various complications of each patient in the hospital, and evaluating the treatment quality indication factors of each patient in the hospital to determine the doctor link level label in the hospital;

[0013] ST4. Displaying the clinical demand set of the hospital and the doctor link level label in the hospital.

[0014] The beneficial effects of the present invention are as follows: (1) Based on the dynamic monitoring data of the conditions of each patient in the hospital, the present invention predicts the risk indication factors corresponding to various complications of each patient in the hospital, making up for the deficiencies in the prior art, ensuring the accuracy of predicting complications of patients in the hospital, thereby improving the treatment effect of patients, and also providing solid data support for the study and judgment of the clinical demand set of the hospital, ensuring the adequacy of the hospital's medical resources, guaranteeing the treatment process of newly admitted patients and also ensuring the treatment of patients' complications.

[0015] (2) When evaluating the treatment quality of patients, the present invention comprehensively considers the incision defect parameters, actual complication conditions and the speed of each healing stage of patients, improving the accuracy of the evaluation of patients' treatment quality, thereby ensuring the accuracy of the subsequent rating and classification of doctors in the hospital. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of the system structure connection of the present invention.

[0018] Figure 2 It is a flowchart of the method of the present invention. Specific embodiments

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] Refer to Figure 1 As shown, the first aspect of the present invention provides a medical data collection and analysis system, including: a medical data collection module, a medical data evaluation module, a processing module, a Web centralized display terminal, and a data warehouse;

[0021] It should be understood that in the present invention, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0022] It should be noted that the medical data collection module is connected to the medical data evaluation module, the medical data evaluation module is connected to the processing module, the processing module is connected to the Web centralized display terminal, and the data warehouse is respectively connected to the medical data evaluation module and the processing module.

[0023] The medical data collection module is used to collect the dynamic monitoring data of the conditions of each patient in the hospital;

[0024] In the specific embodiment of the present invention, the dynamic monitoring data of the condition includes the characteristic values of each basic physical parameter, the characteristic values of each associated physical parameter, the characteristic values of each psychological parameter, and the characteristic values of each activity parameter.

[0025] It should be noted that the characteristic values of the basic physical parameters include, but are not limited to, BMI value, body fat percentage, body temperature, etc. The acquisition methods are relatively mature and will not be elaborated here. The characteristic values of the associated physical parameters are specifically located from the associated physical parameters corresponding to each disease type in the data warehouse based on the medical records of each patient in the hospital. The characteristic values of the psychological parameters include the mental health characteristic values of each dimension. The characteristic values of the activity parameters include, but are not limited to, activity duration, sleep duration, sedentary duration, etc. The acquisition methods are also relatively mature and will not be elaborated here.

[0026] It should be noted that the associated physical parameters corresponding to each disease type are specifically set by medical experts.

[0027] It should also be noted that the mental health characteristic values of each dimension include, but are not limited to, the mental health characteristic values evaluated from online psychological assessment questionnaires, the mental health characteristic values monitored by smart bracelets, and the mental health characteristic values obtained from the hospital internal monitoring platform.

[0028] Once again, it should be noted that the mental health characteristic values monitored by the smart bracelet contain values from 0 to 1, and the mental health characteristic values monitored by the smart bracelet are proportional to the heart rate variability characteristic values monitored by the smart bracelet.

[0029] The specific method for obtaining the mental health characteristic values obtained from the hospital internal monitoring platform is as follows: Obtain the conversation videos from the hospital internal monitoring platform, obtain the emotional types of each patient through facial emotion recognition, combine the negative emotional types stored in the data warehouse, count the number of negative emotional types of each patient, and perform normalization after taking the inverse to obtain the mental health characteristic values obtained from the hospital internal monitoring platform for each patient. The facial emotion recognition technology is relatively mature and will not be elaborated here.

[0030] The medical data evaluation module is used to predict the risk indication factors corresponding to various complications of each patient in the hospital based on the dynamic monitoring data of the conditions of each patient in the hospital.

[0031] In a specific embodiment of the present invention, the specific method for predicting the risk indication factors corresponding to various complications of each patient in the hospital is as follows: Extract the characteristic values of the basic physical parameters, the characteristic values of the associated physical parameters, the characteristic values of the psychological parameters, and the characteristic values of the activity parameters from the dynamic monitoring data of the conditions of each patient in the hospital, and determine the physical quality characteristic parameter β of each patient in the hospital. i , where i is the number of each patient, i = 1, 2,..., n;

[0032] Import the physical quality characteristic parameters of each patient in the hospital into the risk indication factor evaluation model of various complications. Output the risk indication factor α corresponding to various complications of each patient in the hospital im , where α′ _1m represents the reference risk indication factor corresponding to the reference physical literacy characteristic parameter β′ of the mth type of complication in the data warehouse, and α′ _ ′ m 、α′ _ ″ m The risk reduction indication factor corresponding to the excess of the unit physical literacy characteristic of the mth type of complication in the data warehouse and the risk increase indication factor corresponding to the reduction of the unit physical literacy characteristic, where m is the number of various complications, and m = 1, 2,..., l.

[0033] In a specific embodiment of the present invention, the method for determining the physical literacy characteristic parameter of each patient in the hospital is as follows: Compare the characteristic values of each basic physical parameter of each patient in the hospital with the appropriate characteristic value intervals of each basic physical parameter stored in the data warehouse to determine the offset λ _ih of each basic physical parameter of each patient in the hospital, and obtain the first physical literacy characteristic parameter of each patient in the hospital through numerical processing where e is the natural constant, B is the reference first physical literacy characteristic parameter stored in the data warehouse, and λ _ ′ h represents the allowable offset of the hth basic physical parameter stored in the data warehouse, and h is the number of each basic physical parameter, h = 1, 2,..., g;

[0034] It should be noted that the appropriate characteristic value intervals of each basic physical parameter of each patient stored in the data warehouse are specifically determined based on the age of the patient.

[0035] It should also be noted that the method for determining the offset of each basic physical parameter of each patient in the hospital is as follows: Compare the characteristic values of each basic physical parameter of each patient in the hospital with the appropriate characteristic value intervals. If the characteristic value of a certain basic physical parameter is within the appropriate characteristic value interval, record the offset of this basic physical parameter as 0. Otherwise, compare the characteristic value of this basic physical parameter with the maximum or minimum value of the appropriate characteristic value interval to obtain the offset of this basic physical parameter. The sign of the offset is positive or negative. When the sign of the offset is positive, it means that the characteristic value of the basic physical parameter is greater than the maximum value of the appropriate characteristic value interval. When the sign of the offset is negative, it means that the characteristic value of the basic physical parameter is less than the minimum value of the appropriate characteristic interval.

[0036] Compare the eigenvalue of each associated physical parameter of each patient in the hospital with the appropriate eigenvalue interval of each special physical parameter stored in the data warehouse to determine the offset of each associated physical parameter of each patient in the hospital. After similar processing, obtain the second physical literacy characteristic parameter β(2) of each patient in the hospital _i ;

[0037] It should be noted that the specific special physical parameters are the sum of all associated physical parameters

[0038] It should also be noted that the method for determining the offset of each associated physical parameter of each patient in the hospital is the same as that for determining the offset of each basic physical parameter, and the analysis method for the second physical literacy characteristic parameter of each patient in the hospital is the same as that for the first physical literacy characteristic parameter

[0039] Perform mean processing on the eigenvalues of each psychological parameter of each patient in the hospital to obtain the third physical literacy characteristic parameter β(3) of each patient in the hospital _i ;

[0040] Similarly, compare the eigenvalue of each activity parameter of each patient in the hospital with the appropriate eigenvalue interval of each activity parameter stored in the data warehouse to determine the offset of each activity parameter of each patient in the hospital. After similar processing, obtain the fourth physical literacy characteristic parameter β(4) of each patient in the hospital _i ;

[0041] Import the first physical literacy characteristic parameter, the second physical literacy characteristic parameter, the third physical literacy characteristic parameter, and the fourth physical literacy characteristic parameter of each patient in the hospital into the physical literacy characteristic parameter evaluation model, and output the physical literacy characteristic parameter of each patient in the hospital

[0042] In a specific embodiment of the present invention, the physical literacy characteristic parameter evaluation model is specifically: β i =β(1) _i *γ1 + β(2) _i *γ2 + β(3) _i *γ3 + β(4) _i *γ4, where γ1, γ2, γ3, and γ4 respectively represent the weight influence coefficients corresponding to the preset first physical literacy characteristic parameter, the second physical literacy characteristic parameter, the third physical literacy characteristic parameter, and the fourth physical literacy characteristic parameter

[0043] It should be noted that the weight influence coefficients corresponding to the first physical literacy characteristic parameter, the second physical literacy characteristic parameter, the third physical literacy characteristic parameter, and the fourth physical literacy characteristic parameter are specifically set by medical experts

[0044] Based on the dynamic monitoring data of the conditions of each patient in the hospital, the present invention predicts the risk indication factors corresponding to various complications of each patient in the hospital, makes up for the deficiencies in the prior art, ensures the accuracy of predicting complications of patients in the hospital, thereby improving the treatment effect of patients, and also provides solid data support for the judgment of the clinical demand set of the hospital, ensures the adequacy of the hospital's medical resources, guarantees the treatment process of newly admitted patients, and also ensures the treatment of patients' complications.

[0045] The processing module is used to determine the clinical demand set of the hospital based on the risk indication factors corresponding to various complications of each patient in the hospital, evaluate the treatment quality indication factors of each patient in the hospital, and determine the doctor link level label in the hospital.

[0046] In a specific embodiment of the present invention, the method for specifically determining the clinical demand set of the hospital is as follows: comparing the risk indication factors corresponding to various complications of each patient in the hospital with the set of clinical demand consumable quantities corresponding to each complication in each risk indication factor interval stored in the data warehouse, screening to obtain the set of clinical demand consumable quantities corresponding to various complications of each patient in the hospital, and classifying and summarizing to obtain the set of clinical demand consumable quantities of the hospital.

[0047] Comparing the risk indication factors of various complications of each patient in the hospital with the preset risk indication factor thresholds of various complications. If the risk indication factor of a certain complication is greater than or equal to the risk indication factor threshold of this complication, then this complication is recorded as a risk complication, summarizing to obtain various risk complications of each patient in the hospital, and constructing a set of risk complication keywords of each patient in the hospital.

[0048] Extracting the compensation duration corresponding to each reference complication keyword set from the data warehouse, and determining the similarity between the set of risk complication keywords of each patient in the hospital and each reference complication keyword set. If the similarity between the set of risk complication keywords of a certain patient and a certain reference complication keyword set is the largest, then the compensation duration corresponding to this reference complication keyword set is used as the compensation duration of this patient, screening to obtain the compensation duration of each patient in the hospital, obtaining the estimated treatment duration of each patient in the hospital from the hospital operation platform, and adding it to the compensation duration to obtain the usage duration of the auxiliary terminal of each patient in the hospital, and summarizing to obtain the set of usage durations of the auxiliary terminal of the hospital.

[0049] It should be noted that determining the similarity between the set of risk complication keywords of each patient in the hospital and each reference complication keyword set is prior art and will not be elaborated here.

[0050] Taking the set of clinical demand consumable quantities of the hospital and the set of usage durations of the auxiliary terminal as subsets of the clinical demand set of the hospital.

[0051] In a specific embodiment of the present invention, the method for evaluating the treatment quality indication factors of each patient in the hospital is as follows: Obtain the treatment videos of each patient in the hospital from the hospital operation platform, identify each treatment action of each patient in the hospital through action recognition technology, and obtain the blood loss set and the time points of each blood transfusion of each patient in the hospital, and evaluate the operation quality indication factors of each patient in the hospital;

[0052] It should be noted that the sorting method of the above treatment actions is sorted in chronological order.

[0053] Obtain the incision picture set of each patient in the hospital from the hospital operation platform, and obtain the number of complications of each patient in the hospital from the hospital operation platform, and evaluate the recovery quality indication factors of each patient in the hospital;

[0054] Perform mean processing on the operation quality indication factors and recovery quality indication factors of each patient in the hospital to obtain the treatment quality indication factors of each patient in the hospital.

[0055] In a specific embodiment of the present invention, the method for evaluating the operation quality indication factors of each patient in the hospital is as follows: Compare each treatment action of each patient in the hospital with each standard treatment action of each patient in the hospital stored in the data warehouse one by one. If each treatment action of each patient in the hospital matches the corresponding standard treatment action successfully, record the treatment action influence parameter of each patient in the hospital as A. Otherwise, screen each conventional treatment action of each patient in the hospital, count the number of conventional treatment actions and the number of treatment actions of each patient in the hospital, and divide the number of conventional treatment actions of each patient in the hospital by the number of treatment actions to obtain the treatment action influence parameter A' of each patient in the hospital;

[0056] It should be noted that the method for screening each conventional treatment action of each patient in the hospital is as follows: If a certain treatment action of a certain patient matches the corresponding standard treatment action successfully, record this treatment action as a conventional treatment action, and screen each conventional treatment action of each patient in the hospital.

[0057] Based on the blood loss set of each patient in the hospital, judge the time points of each blood transfusion required for each patient in the hospital, obtain the time points of each blood transfusion of each patient in the hospital from the hospital operation platform, screen the associated time points corresponding to the time points of each blood transfusion required for each patient in the hospital, and obtain the deployment duration of each blood transfusion required for each patient in the hospital;

[0058] It should be noted that the specific method for determining the time points of each patient's need for blood transfusion in the hospital is as follows: compare the blood loss of each patient at each time point in the hospital with the blood loss corresponding to the need for blood transfusion in the data warehouse. If the blood loss at a certain time point is greater than or equal to the blood loss corresponding to the need for blood transfusion, then record this time point as the time point of the need for blood transfusion, and obtain the time points of each patient's need for blood transfusion in the hospital.

[0059] It should also be noted that the specific screening method for screening the associated time points corresponding to the time points of each patient's need for blood transfusion in the hospital is as follows: if the time point of a certain blood transfusion is after the time point of a certain need for blood transfusion and before the time point of the next need for blood transfusion of this need for blood transfusion or there is no time point of the next need for blood transfusion, then record this blood transfusion as the associated time point corresponding to the time point of this need for blood transfusion, and screen to obtain the associated time points corresponding to the time points of each patient's need for blood transfusion in the hospital.

[0060] The treatment action influence parameters of each patient in the hospital and the deployment duration T of each need for blood transfusion _ij are imported into the operation quality indication factor evaluation model to output the operation quality indication factors of each patient in the hospital. In the formula, R _i is the treatment action influence parameter of each patient in the hospital, where the value of R _i is A or A', T' is the blood transfusion allowable deployment duration in the data warehouse, and j is the number of each need for blood transfusion, j = 1, 2,..., k.

[0061] In a specific embodiment of the present invention, the specific evaluation method for the recovery quality indication factor of each patient in the hospital is as follows: based on the set of incision pictures of each patient in the hospital, identify the incision defect parameters of each patient in the hospital through image recognition technology, where the incision defect parameters include various incision defect types and their corresponding characteristic parameters, and determine the elapsed time of each healing stage of each patient in the hospital;

[0062] It should be noted that the characteristic parameter specifically refers to the area.

[0063] It should also be noted that the specific determination method for determining the incision healing speed of each patient in the hospital is as follows: compare a number of pictures in the set of incision pictures of each patient in the hospital with the set of pictures of each healing stage of each patient in the hospital located from the data warehouse through image processing software to obtain the similarity between each picture of each patient and each picture of each healing stage. If the similarity between a certain picture of a certain patient and a certain picture of a certain healing stage is the largest, then classify this picture into this healing stage, so as to obtain each picture of each healing stage of each patient in the hospital, and obtain the time points of each picture of each healing stage of each patient in the hospital, so as to obtain the elapsed time of each healing stage of each patient in the hospital.

[0064] Import the incision defect parameters and the number of complications M of each patient in the hospital _i and the elapsed time TI of each healing stage _if into the recovery quality indication factor evaluation model to output the recovery quality indication factors of each patient in the hospital. In the formula, M′ is the allowable number of complications in the data warehouse, and θ _ip , τ _ip , TI′ _f respectively represent the risk indication factor corresponding to the p-th incision defect type of the i-th patient in the hospital, the risk indication factor corresponding to the unit characteristic parameter, and the appropriate elapsed time of the f-th healing stage. p is the number of each incision defect type, p = 1, 2,..., q, and f is the number of each healing stage, f = 1, 2,..., t.

[0065] It should be noted that the risk indication factors corresponding to each incision defect type of each patient in the hospital and the risk indication factors corresponding to the unit characteristic parameters are specifically matched from the risk indication factors corresponding to each incision defect type and the risk indication factors corresponding to the unit characteristic parameters preset in the data warehouse for each patient in the hospital. The appropriate elapsed time of each healing stage in the hospital is specifically set by medical experts. The incision defect types include redness, exudation, cracking, etc.

[0066] It should be noted that the method for specifically determining the doctor link level label in the hospital is as follows: Based on the treatment quality indication factors of each patient in the hospital, obtain the responsible doctors of each patient in the hospital from the hospital operation platform, map to obtain each patient corresponding to each responsible doctor, and obtain the treatment quality indication factors of each patient corresponding to each responsible doctor. Perform mean processing on them as the treatment quality indication factors corresponding to each responsible doctor, and compare them with the treatment quality indication factor intervals corresponding to each level label of the doctor link stored in the data warehouse. Screen to obtain the level labels corresponding to each responsible doctor, map to obtain each responsible doctor corresponding to each level label, and summarize to generate the doctor link level label.

[0067] When evaluating the treatment quality of patients, the present invention comprehensively considers the incision defect parameters, actual complication conditions, and the speed of each healing stage of patients, improving the accuracy of the treatment quality evaluation of patients, thereby ensuring the accuracy of the subsequent rating and classification of doctors in the hospital.

[0068] The Web integrated display terminal is used to display the clinical requirement set of the hospital and the doctor link level label in the hospital.

[0069] Refer to Figure 2As shown in the figure, the second aspect of the present invention provides a method for implementing the medical data acquisition and analysis system of the present invention, including: ST1, collecting the dynamic monitoring data of the conditions of each patient in the hospital;

[0070] ST2, based on the dynamic monitoring data of the conditions of each patient in the hospital, predicting the risk indication factors corresponding to various complications of each patient in the hospital;

[0071] ST3, based on the risk indication factors corresponding to various complications of each patient in the hospital, determining the clinical requirement set of the hospital, and evaluating the treatment quality indication factors of each patient in the hospital to determine the doctor link level label in the hospital;

[0072] ST4, displaying the clinical requirement set of the hospital and the doctor link level label in the hospital.

[0073] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A medical data collection and analysis system, characterized in that: include: Medical data collection module, used to collect dynamic monitoring data of the condition of each patient in the hospital; The medical data evaluation module is used to predict the risk indicator factors corresponding to various complications of each patient in the hospital based on the dynamic monitoring data of the condition of each patient in the hospital; The processing module is used to determine the hospital's clinical demand set based on the risk indicator factors corresponding to various complications of each patient in the hospital, evaluate the treatment quality indicator factors of each patient in the hospital, and determine the link level label of the doctors in the hospital; The web display terminal is used to display the hospital's clinical demand set and the link level labels of doctors within the hospital.

2. A medical data collection and analysis system according to claim 1, characterized in that: The dynamic disease condition monitoring data includes characteristic values ​​of each basic physical parameter, characteristic values ​​of each associated physical parameter, characteristic values ​​of each psychological parameter and characteristic values ​​of each activity parameter.

3. A medical data collection and analysis system according to claim 2, characterized in that: The specific method for predicting the risk indicator factors corresponding to various complications of each patient in the hospital is as follows: Extract the characteristic values ​​of each basic physical parameter, each associated physical parameter, each psychological parameter, and each activity parameter from the dynamic monitoring data of each patient in the hospital, and determine the physical literacy characteristic parameter β of each patient in the hospital. i , i is the number of each patient, i = 1, 2, ..., n; Import the physical fitness characteristic parameters of each patient in the hospital into the risk indicator factor assessment model for various complications Output the risk indicator factor α corresponding to each type of complication of each patient in the hospital im , where α′ _1m It is represented as the reference risk indicator factor corresponding to the reference physical literacy characteristic parameter β′ of the mth type of complication in the data warehouse, α″ _m , α″′ _m The reduction risk indicator factor corresponding to the excess of the unit physical fitness characteristics of the mth type of complication in the data warehouse, and the increase risk indicator factor corresponding to the reduction of the unit physical fitness characteristics, m is the number of each type of complication, m = 1, 2, ..., l.

4. A medical data collection and analysis system according to claim 3, characterized in that: The specific determination method of the physical fitness characteristic parameters of each patient in the hospital is as follows: The characteristic values ​​of each basic physical parameter of each patient in the hospital are compared with the appropriate characteristic value intervals of each basic physical parameter of each patient stored in the data warehouse to determine the offset λ of each basic physical parameter of each patient in the hospital _ih , after numerical processing, the first physical literacy characteristic parameters of each patient in the hospital are obtained Where e is a natural constant, B is the reference first physical literacy characteristic parameter stored in the data warehouse, λ _ ' h It is represented as the allowable offset of the hth basic body parameter stored in the data bin, where h is the number of each basic body parameter, h = 1, 2, ..., g; The characteristic values ​​of the associated physical parameters of each patient in the hospital are compared with the appropriate characteristic value intervals of each special physical parameter stored in the data warehouse to determine the offset of each associated physical parameter of each patient in the hospital. After similar processing, the second physical literacy characteristic parameter β(2) of each patient in the hospital is obtained. _i ; The characteristic values ​​of each psychological parameter of each patient in the hospital are averaged to obtain the third physical literacy characteristic parameter β(3) of each patient in the hospital _i ; Similarly, the characteristic values ​​of each activity parameter of each patient in the hospital are compared with the appropriate characteristic value intervals of each activity parameter stored in the data warehouse to determine the offset of each activity parameter of each patient in the hospital. After similar processing, the fourth physical literacy characteristic parameter β(4) of each patient in the hospital is obtained. _i ; The first physical literacy characteristic parameter, the second physical literacy characteristic parameter, the third physical literacy characteristic parameter and the fourth physical literacy characteristic parameter of each patient in the hospital are imported into the physical literacy characteristic parameter evaluation model, and the physical literacy characteristic parameters of each patient in the hospital are output.

5. A medical data collection and analysis system according to claim 4, characterized in that: The physical literacy characteristic parameter evaluation model is specifically: β i =β(1) _i *γ1+β(2) _i *γ2+β(3) _i *γ3+β(4) _i *γ4, where γ1, γ2, γ3, and γ4 represent the weight influence coefficients corresponding to the preset first physical fitness characteristic parameter, the second physical fitness characteristic parameter, the third physical fitness characteristic parameter, and the fourth physical fitness characteristic parameter, respectively.

6. A medical data collection and analysis system according to claim 1, characterized in that: The specific method for determining the clinical demand set of the hospital is as follows: Compare the risk indicator factors corresponding to various complications of each patient in the hospital with the clinical demand consumable quantity sets corresponding to each complication in each risk indicator factor interval stored in the data warehouse, screen out the clinical demand consumable quantity sets corresponding to various complications of each patient in the hospital, and classify and summarize them to obtain the clinical demand consumable quantity sets of the hospital; Compare the risk indicator factors of various complications of each patient in the hospital with the preset risk indicator factor thresholds of various complications. If the risk indicator factor of a certain type of complication is greater than or equal to the risk indicator factor threshold of the complication, then record the complication as a risk complication. Summarize the various risk complications of each patient in the hospital and construct a risk complication keyword set for each patient in the hospital. Extract the compensation time corresponding to each reference complication keyword set from the data warehouse, and determine the similarity between the risk complication keyword set of each patient in the hospital and each reference complication keyword set, so as to screen the compensation time of each patient in the hospital, obtain the estimated treatment time of each patient in the hospital from the hospital operation platform, and add it to the compensation time to obtain the use time of the auxiliary terminal of each patient in the hospital, and summarize to obtain the auxiliary terminal use time set of the hospital; The hospital's clinical demand consumables quantity set and auxiliary terminal usage time set are taken as subsets of the hospital's clinical demand set.

7. A medical data collection and analysis system according to claim 1, characterized in that: The specific evaluation method for evaluating the treatment quality indicator factors of each patient in the hospital is as follows: Obtain treatment videos of each patient in the hospital from the hospital operation platform, identify each treatment action of each patient in the hospital through action recognition technology, obtain the bleeding volume set and the time point of each blood transfusion of each patient in the hospital, and evaluate the operation quality indicator factors of each patient in the hospital; Obtain a collection of incision images of each patient in the hospital from the hospital operation platform, obtain the number of complications of each patient in the hospital from the hospital operation platform, and evaluate the recovery quality indicator factors of each patient in the hospital; The operation quality indicator factor and recovery quality indicator factor of each patient in the hospital are averaged to obtain the treatment quality indicator factor of each patient in the hospital.

8. A medical data collection and analysis system according to claim 7, characterized in that: The specific evaluation method of the operation quality indicator factors of each patient in the hospital is as follows: Compare each treatment action of each patient in the hospital with each standard treatment action of each patient in the hospital stored in the data warehouse one by one. If each treatment action of each patient in the hospital matches the corresponding standard treatment action successfully, the treatment action influencing parameter of each patient in the hospital is recorded as A. Otherwise, select each conventional treatment action of each patient in the hospital, and obtain the number of conventional treatment actions and the number of treatment actions of each patient in the hospital by counting. Divide the number of conventional treatment actions of each patient in the hospital by the number of treatment actions to obtain the treatment action influencing parameter A' of each patient in the hospital. Based on the set of bleeding volume of each patient in the hospital, the time point of each blood transfusion requirement of each patient in the hospital is determined, the time point of each blood transfusion requirement of each patient in the hospital is obtained from the hospital operation platform, the associated time point corresponding to each blood transfusion requirement time point of each patient in the hospital is screened, and the deployment time of each blood transfusion requirement of each patient in the hospital is obtained; The influencing parameters of the treatment actions of each patient in the hospital and the deployment time of each blood transfusion are calculated. _ij Import into the operation quality indicator factor evaluation model , output the operation quality indicator factors of each patient in the hospital, where R _i is the influencing parameter of the treatment actions of each patient in the hospital, where R _i The value of is A or A', T' is the allowed allocation time of blood transfusion in the data warehouse, j is the number of each blood transfusion requirement, j = 1, 2, ..., k.

9. A medical data collection and analysis system according to claim 7, characterized in that: The specific evaluation method of the recovery quality indicator factor of each patient in the hospital is as follows: Based on the incision picture collection of each patient in the hospital, the incision defect parameters of each patient in the hospital are identified by image recognition technology, wherein the incision defect parameters include each incision defect type and its corresponding characteristic parameter, and the duration of each healing stage of each patient in the hospital is determined; The incision defect parameters and the number of complications M of each patient in the hospital _i and the duration of each healing stage TI _if Import into the restoration quality indicator factor evaluation model , output the recovery quality indicator factor of each patient in the hospital, where M′ is the number of allowed complications in the data warehouse, θ _ip , τ _ip TI′ _f They are respectively represented by the risk indicator factor corresponding to the p-th incision defect type of the ith patient in the hospital, the risk indicator factor corresponding to the unit characteristic parameter, and the appropriate duration of the f-th healing stage. p is the number of each incision defect type, p=1,2,...,q, and f is the number of each healing stage, f=1,2,...,t.

10. A method for executing the medical data collection and analysis system according to any one of claims 1 to 9, characterized in that: include: ST1. Collect dynamic monitoring data of the condition of each patient in the hospital; ST2. Based on the dynamic monitoring data of the condition of each patient in the hospital, predict the risk indicator factors corresponding to various complications of each patient in the hospital; ST3. Based on the risk indicator factors corresponding to various complications of each patient in the hospital, determine the hospital's clinical demand set, evaluate the treatment quality indicator factors of each patient in the hospital, and determine the link level label of the doctors in the hospital; ST4. Display the hospital's clinical demand set and the link level labels of doctors within the hospital.

Images