A hospital information integration intelligent integrated management and control system

Abstract

The present invention discloses an intelligent integrated management and control system for hospital information integration, which belongs to the technical field of hospital information management, and comprises a rule base, an abnormality recognition module and a medical record supervision module; the rule base is used to store various medical rules; the abnormality recognition module is used to perform abnormality recognition on medication data based on the rule base; identify various medical rules in the rule base; establish an abnormality recognition model based on the medical rules; perform real-time recognition on medication data through the abnormality recognition model, and obtain abnormal judgment values ​​corresponding to various medication data; determine operation abnormality data according to the abnormal judgment values; perform corresponding processing according to the obtained abnormal operation data; the medical record supervision module is used to supervise the writing of cases, obtain various target cases, and identify the case type of the target cases; obtain various case requirements of the corresponding case types; obtain case verification values ​​corresponding to various case requirements; determine case supervision results according to the case verification values; and process various target cases according to the case supervision results.

Description

Technical Field

[0001] The present invention belongs to the technical field of hospital information management, and in particular is a hospital information integrated intelligent integrated management and control system. Background Art

[0002] With the rapid development of the medical industry, hospitals are facing increasingly complex operational management challenges, among which the accuracy and efficiency of information management are particularly important. In the current medical information management system, although basic business process automation and data recording functions have been realized, there are still many deficiencies in the implementation of the rule base, the supervision of medication data, the standardization of medical record writing, and the intelligence of information retrieval.

[0003] First, as a core component of hospital information management, the accuracy and timeliness of the rule base are directly related to the quality and safety of medical services. However, the existing rule base often lacks an effective update mechanism during implementation, resulting in a lag in data supervision and difficulty in timely detection and correction of violations. In addition, the supervision of violations often relies on manual review, which is not only inefficient but also prone to omissions.

[0004] Secondly, as an important record of the patient's diagnosis and treatment process, the standardization and reliability of medical record writing directly affects the medical quality assessment and the resolution of legal disputes. The traditional medical record supervision method mainly relies on manual review, which not only increases the workload of medical staff, but also makes it difficult to ensure the accuracy and consistency of medical record writing. Therefore, a more efficient and intelligent medical record supervision method is needed to improve the standardization and reliability of medical record writing.

[0005] Furthermore, as one of the important functions of hospital information management, the accuracy and efficiency of information retrieval directly affect the work efficiency of medical staff and the medical experience of patients. However, existing information retrieval systems often lack the ability to learn and correct themselves, and cannot dynamically adjust the retrieval content and rules according to the actual needs and feedback of users, resulting in inaccurate and incomplete retrieval results.

[0006] In order to solve the above problems or some of the problems, the present invention proposes a hospital information integration intelligent integrated management and control system. Summary of the invention

[0007] In order to solve the problems existing in the above solutions, the present invention provides a hospital information integration intelligent integrated management and control system.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] A hospital information integration intelligent integrated management and control system, including a rule base, an abnormality recognition module and a medical record supervision module;

[0010] The rule library is used to store various medical rules.

[0011] The anomaly recognition module is used to identify anomalies in medication data based on a rule base; identify each medical rule in the rule base; and establish an anomaly recognition model based on the medical rules;

[0012] The medication data is identified in real time through the abnormal identification model to obtain the abnormal judgment value corresponding to each medication data; the operation abnormal data is determined according to the abnormal judgment value; and corresponding processing is performed according to the obtained abnormal operation data.

[0013] Furthermore, the expression of the anomaly recognition model is:

[0014]

[0015] In the formula: s is the input data, the input data is the medication data; the output data is the abnormal judgment value YC(s).

[0016] Furthermore, the method for processing according to abnormal operation data includes:

[0017] Identify the violators corresponding to each abnormal operation data, summarize the violators, establish a list of violators, establish a violation database based on the list of violators, establish a storage node corresponding to each violator in the violation database, and store each abnormal operation data in the corresponding storage node according to the corresponding violator;

[0018] According to the formula Calculate the violation value of each violator;

[0019] Where: PX is the violation value; i is the medication data corresponding to the violator, i = 1, 2, ..., n, n is a positive integer; e is a natural constant; λti is the time reduction coefficient, and its value range is [0, 1];

[0020] Dynamically mark the violation value of each violator in the list of violators, and sort the violators in the list of violators in descending order of violation value;

[0021] The violators whose violation values ​​are greater than the threshold value X1 are marked accordingly in the list of violators;

[0022] According to the formula Calculate the corresponding rule comprehensive value;

[0023] Where: PW is the comprehensive value of the rule; j represents the violator, j = 1, 2, ..., m, m is a positive integer; A0 is the number of non-violators; QW (PXj) is the conversion function;

[0024] The rule comprehensive value is marked accordingly in the list of violators to indicate the implementation of the medical rule, so as to facilitate the management personnel to adjust the medical rule or strengthen the supervision of the implementation of the medical rule.

[0025] Furthermore, the expression of the conversion function is:

[0026]

[0027] Furthermore, it also includes a rule optimization module, which is used to optimize and analyze each medical rule, obtain supervision results in real time, and the supervision results include supervision errors and supervision correctness; determine each rule unit data and analysis rules according to the supervision results;

[0028] Establish a material analysis library, identify each analysis rule, and set a storage node corresponding to each analysis rule in the material analysis library; input each rule unit data into the storage node corresponding to the corresponding analysis rule;

[0029] Real-time identification of rule unit data in each storage node in the material analysis library, result analysis, identification and adjustment of each rule unit data according to the analysis rules, and determination of each candidate adjustment method; test and simulate each candidate adjustment method, determine the target adjustment method, and adjust the supervision method based on the target adjustment method.

[0030] Furthermore, the method of testing and simulating each candidate adjustment method includes:

[0031] Set a test set, simulate each candidate adjustment method according to the test set, and obtain the corresponding simulation pass rate;

[0032] According to the formula Calculate the evaluation value of each candidate adjustment method;

[0033] Where: LK is the evaluation value; HM(h) is the piecewise function, the expression is h is the simulated qualified rate, β is the preset qualified rate, such as 0.95; GL is the change proportion, and the value range is (0, 1];

[0034] Eliminate the candidate adjustment methods with an evaluation value of 0, and select the candidate adjustment method with the largest remaining evaluation value as the target adjustment method.

[0035] The medical record supervision module is used to supervise the writing of cases, obtain each target case, identify the case type of the target case, and obtain each case requirement of the corresponding case type;

[0036] According to the requirements of each case, a corresponding case verification model is established. The expression of the case verification model is: In the formula: q is the input data, which is the data corresponding to the case requirements in the case; the output data is the case verification value BL(q);

[0037] Analyze the target cases through the case verification model to obtain the case verification values ​​corresponding to each case requirement; determine the case supervision results based on the obtained case verification values; and process each target case based on the case supervision results.

[0038] Furthermore, it also includes a case analysis module, which is used to analyze the supervision results of each case, set a list of evaluators, and count the case failure rates of evaluators on each case requirement according to the identified case supervision results; mark the case requirements with case failure rates not equal to 0 as the supervision requirements of the corresponding evaluators, and mark the corresponding case failure rates as the supervision single item value;

[0039] Determine the types of unqualified cases corresponding to the evaluators and the proportion of each type of unqualified cases based on the regulatory requirements;

[0040] Obtain case data in real time, analyze the case data, and obtain the type value corresponding to each unqualified type; the value range of the type value is [0, 100];

[0041] Mark the unqualified type corresponding to the evaluator as z, z = 1, 2, ..., v, v is a positive integer;

[0042] According to the formula Calculate the required value for each case required by the assessor;

[0043] Where: UY is the required value; η is the regulatory single item value required by the corresponding case; Bz is the proportion of the corresponding unqualified type; LAz is the type value of the corresponding unqualified type;

[0044] Mark each regulatory item value in the assessor list.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] Through the mutual cooperation among the rule base, anomaly recognition module, rule optimization module, medical record supervision module and case analysis module, comprehensive supervision of medical data, medication data and medical record writing is achieved; with the help of advanced technologies such as data mining and machine learning, intelligent analysis and decision support of complex data are achieved; by integrating various information and resources within the hospital, real-time updating, sharing and automatic control of information are achieved, thereby improving the overall operational efficiency and service quality of the hospital. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, a hospital information integration intelligent integrated management and control system includes a rule base, an abnormality recognition module, a rule optimization module, a medical record supervision module and a case analysis module;

[0051] The rule base is established by the hospital according to its needs and is used to collect, organize and store information such as various internal rules and regulations, operating specifications, diagnosis and treatment standards, and medication rules of the hospital. It is an existing module.

[0052] The abnormality recognition module is used to identify abnormalities in medication data based on the rule base; identify the medical rules in the rule base, which are various set operation specifications, diagnosis and treatment standards, medication rules, etc.; establish an abnormality recognition model based on the medical rules, that is, identify the medication data within the corresponding range based on the corresponding medical rules to determine whether it complies with the medical rules; the expression of the abnormality recognition model is In the formula: s is the input data, the input data is the medication data; the output data is the abnormal judgment value YC(s);

[0053] The medication data is identified in real time through the abnormal recognition model to obtain the abnormal judgment value corresponding to each medication data; the medical information with the abnormal judgment value of 1 is marked as abnormal operation data, that is, the abnormality caused by the corresponding doctors and other staff not following the corresponding medical rules; corresponding processing is performed according to the obtained abnormal operation data.

[0054] According to the abnormal operation data obtained, corresponding processing is performed. In one embodiment, feedback can be directly given to the violators corresponding to the abnormal operation data, and the violation is handled according to the preset error penalty system. In another embodiment, because the abnormal operation data cannot be fully utilized if the processing is performed according to the above embodiment, the corresponding processing is graded processing, and the process is as follows:

[0055] Identify the violators corresponding to each abnormal operation data, summarize the violators, establish a list of violators, establish a violation database based on the list of violators, establish a storage node corresponding to each violator in the violation database, and store each abnormal operation data in the corresponding storage node according to the corresponding violator;

[0056] According to the formula Calculate the violation value of each violator; where: PX is the violation value; i is the medication data corresponding to the violator, that is, the medication data uploaded by the violator, i = 1, 2, ..., n, n is a positive integer; e is a natural constant; λti is the time reduction coefficient, which is set according to the storage time of the abnormal operation data corresponding to the medication data, and is used to reduce the impact of historical violations on the current violator. It is only affected by the storage time and is manually set according to the hospital's management requirements. Generally, the farther the time is from the current time, the smaller the time reduction coefficient. If it is not set, the default time reduction coefficient is 1, and its value range is [0, 1];

[0057] Dynamically mark the violation value of each violator in the list of violators, and sort the violators in the list of violators in descending order of violation value;

[0058] The violators whose violation values ​​are greater than the threshold value X1 are marked accordingly in the list of violators, indicating that the violation rate of the above-mentioned personnel exceeds the preset requirement;

[0059] According to the formula Calculate the corresponding rule comprehensive value;

[0060] Where: PW is the comprehensive value of the rule; j represents the violator, j = 1, 2, ..., m, m is a positive integer; A0 is the number of non-violators; QW (PXj) is the conversion function,

[0061] The rule comprehensive value is marked accordingly in the list of violators to indicate the implementation of the medical rule, so as to facilitate the management personnel to adjust the medical rule or strengthen the supervision of the implementation of the medical rule.

[0062] The rule optimization module is used to optimize and analyze each medical rule and obtain supervision results in real time. The supervision result refers to whether the supervision is wrong based on each medical rule. Supervision error refers to judging that medical data that does not comply with the medical rule is in compliance with the medical rule; that is, the supervision result includes supervision error and supervision correctness; the data and medical rules corresponding to the supervision result of supervision error are marked as rule unit data and analysis rules;

[0063] Establish a material analysis library, which is a database for data storage, identify each analysis rule, set a storage node corresponding to each analysis rule in the material analysis library; input each rule unit data into the storage node corresponding to the corresponding analysis rule;

[0064] Real-time identification of rule unit data in each storage node in the material analysis library, result analysis, identification and adjustment of each rule unit data according to the analysis rules, and determination of various candidate adjustment methods. A brief summary is how to adjust the existing supervision method based on the analysis rules to determine whether the rule unit data does not conform to the analysis rules; specifically, an adjustment analysis model is established based on existing neural networks such as CNN networks or DNN networks, and a corresponding training set is established manually for training. The training set includes input data and output data. The input data is the analysis rules and each rule unit data; the output data is the candidate adjustment method, and the adjustment analysis model after successful training is used to analyze and determine the various candidate adjustment methods.

[0065] Conduct test simulations on various candidate adjustment methods, determine the target adjustment method, and adjust the supervision method based on the target adjustment method.

[0066] The method of testing and simulating each candidate adjustment method includes:

[0067] Combine the rule unit data and analysis rules in the corresponding storage node to determine the test set, that is, determine the historical supervision results as correct supervision data according to the analysis rules, and combine them with the rule unit data to form a test set; simulate each candidate adjustment method according to the test set, that is, simulate the supervision of the test set after adjusting according to the corresponding candidate adjustment method, and obtain the corresponding simulation pass rate;

[0068] According to the formula Calculate the evaluation value of each candidate adjustment method;

[0069] Where: LK is the evaluation value; HM(h) is the piecewise function, the expression is h is the simulated qualified rate, β is the preset qualified rate, such as 0.95; GL is the change proportion, that is, the degree of change to the existing method, and the value range is (0, 1];

[0070] Eliminate the candidate adjustment methods with an evaluation value of 0, and select the candidate adjustment method with the largest remaining evaluation value as the target adjustment method.

[0071] The medical record supervision module is used to supervise the writing of cases, obtain cases that need to be supervised, mark them as target cases, identify the case type of the target case, that is, what type of case is prescribed by the department; and obtain the case requirements of the corresponding case type;

[0072] According to the requirements of each case, a corresponding case verification model is established. The case verification model is used to verify the corresponding part of the case according to the corresponding case requirements to determine whether it meets the case requirements. The expression of the case verification model is: In the formula: q is the input data, which is the data corresponding to the case requirements in the case; the output data is the case verification value BL(q);

[0073] Analyze the target cases through the case verification model to obtain the case verification values ​​corresponding to each case requirement; determine the case supervision results based on the obtained case verification values; and process each target case based on the case supervision results.

[0074] The case analysis module is used to analyze the supervision results of each case, set a list of evaluators, and the evaluators are the medical staff who write the cases; identify the case supervision results corresponding to each evaluator in real time, and count the case failure rate of the evaluator on each case requirement according to the identified case supervision results; mark the case requirements with a case failure rate not equal to 0 as the supervision requirements of the evaluator, and mark the corresponding case failure rate as the supervision single item value;

[0075] According to the unqualified cases corresponding to the regulatory requirements, determine the unqualified types of the assessors in accordance with the regulatory requirements and the proportion of each unqualified type. The unqualified type indicates what type of unqualified case part is, which is set according to the specific needs of the hospital;

[0076] Acquire case data in real time, case data refers to cases that have occurred and caused medical problems due to case problems; analyze case data to obtain type values ​​corresponding to each unqualified type; type value is set according to the severity of the medical problem of the case data of this type, and the value range is [0, 100], with the lightest being 0 and the most serious being 100. Other type values ​​are set according to the severity difference and are set according to the needs of the hospital; specifically, a corresponding case analysis model can be established based on a neural network such as a CNN network or a DNN network, and a corresponding training set can be established manually for training, the training set includes input data and output data, the input data is case data; the output data is the type value corresponding to each unqualified type; as the case data changes, the type value is in dynamic change; analyze the case data through the case analysis model after successful training to obtain the type value corresponding to each unqualified type;

[0077] The unqualified type corresponding to the evaluator is marked as z, where z = 1, 2, ..., v, and v is a positive integer. The unqualified type of each evaluator may be different and is determined according to their specific errors;

[0078] According to the formula Calculate the required value for each case required by the assessor;

[0079] Where: UY is the required value; η is the regulatory single item value required by the corresponding case; Bz is the proportion of the corresponding unqualified type; LAz is the type value of the corresponding unqualified type;

[0080] Mark each regulatory item value in the assessor list to facilitate management personnel to supervise and correct the corresponding assessors.

[0081] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0082] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A hospital information integration intelligent integrated management and control system, characterized in that: Includes rule base, anomaly identification module and medical record supervision module; The rule library is used to store various medical rules; The anomaly recognition module is used to identify anomalies in medication data based on a rule base; identify each medical rule in the rule base; and establish an anomaly recognition model based on the medical rules; The medication data is identified in real time through an abnormal identification model to obtain abnormal judgment values ​​corresponding to each medication data; abnormal operation data is determined according to the abnormal judgment values; and corresponding processing is performed according to the obtained abnormal operation data; The medical record supervision module is used to supervise the writing of cases, obtain each target case, identify the case type of the target case, and obtain each case requirement of the corresponding case type; According to the requirements of each case, a corresponding case verification model is established. The expression of the case verification model is: ; In the formula: q is the input data, which is the data corresponding to the case requirements in the case; the output data is the case verification value BL(q); Analyze the target cases through the case verification model to obtain the case verification values ​​corresponding to the requirements of each case; determine the case supervision results according to the obtained case verification values; and process each target case according to the case supervision results; The expression of the anomaly recognition model is: ; In the formula: s is the input data, and the input data is the medication data; The output data is the abnormal judgment value YC(s); Methods for processing based on abnormal operation data include: Identify the violators corresponding to each abnormal operation data, summarize the violators, establish a list of violators, establish a violation database based on the list of violators, establish a storage node corresponding to each violator in the violation database, and store each abnormal operation data in the corresponding storage node according to the corresponding violator; According to the formula Calculate the violation value of each violator; Where: PX is the violation value; i is the medication data corresponding to the violator, i=1, 2, ..., n, n is a positive integer; e is a natural constant; λti is the time reduction coefficient, and its value range is [0, 1]; Dynamically mark the violation value of each violator in the list of violators, and sort the violators in the list of violators in descending order of violation value; The violators whose violation values ​​are greater than the threshold value X1 are marked accordingly in the list of violators; According to the formula Calculate the corresponding rule comprehensive value; Where: PW is the comprehensive value of the rule; j represents the violator, j=1, 2, ..., m, m is a positive integer; A0 is the number of non-violators; QW(PXj) is the conversion function, ; The rule comprehensive value is marked accordingly in the list of violators to indicate the implementation of the medical rule, so as to facilitate the management personnel to adjust the medical rule or strengthen the supervision of the implementation of the medical rule.

2. A hospital information integrated intelligent integrated management and control system according to claim 1, characterized in that: It also includes a rule optimization module, which is used to optimize and analyze each medical rule, obtain supervision results in real time, and the supervision results include supervision errors and supervision correctness; determine each rule unit data and analysis rules according to the supervision results; Establish a material analysis library, identify each analysis rule, and set a storage node corresponding to each analysis rule in the material analysis library; input each rule unit data into the storage node corresponding to the corresponding analysis rule; Real-time identification of rule unit data in each storage node in the material analysis library, result analysis, identification and adjustment of each rule unit data according to the analysis rules, and determination of each candidate adjustment method; test and simulate each candidate adjustment method, determine the target adjustment method, and adjust the supervision method based on the target adjustment method.

3. A hospital information integrated intelligent integrated management and control system according to claim 2, characterized in that: The method of testing and simulating each candidate adjustment method includes: Set a test set, simulate each candidate adjustment method according to the test set, and obtain the corresponding simulation pass rate; According to the formula Calculate the evaluation value of each candidate adjustment method; Where: LK is the evaluation value; HM(h) is the piecewise function, the expression is , h is the simulated qualified rate, β is the preset qualified rate, such as 0.95; GL is the change proportion, and its value range is (0, 1]; Eliminate the candidate adjustment methods with an evaluation value of 0, and select the candidate adjustment method with the largest remaining evaluation value as the target adjustment method.

4. The hospital information integrated intelligent integrated management and control system according to claim 1 is characterized in that: It also includes a case analysis module, which is used to analyze the supervision results of each case, set a list of evaluators, and count the case failure rates of evaluators on each case requirement according to the identified case supervision results; mark the case requirements with case failure rates not equal to 0 as the supervision requirements of the corresponding evaluators, and mark the corresponding case failure rates as the supervision single item value; Determine the types of unqualified cases corresponding to the evaluators and the proportion of each type of unqualified cases based on the regulatory requirements; Obtain case data in real time, analyze the case data, and obtain the type value corresponding to each unqualified type; the value range of the type value is [0, 100]; Mark the unqualified type corresponding to the evaluator as z, z=1, 2, ..., v, v is a positive integer; According to the formula Calculate the required value for each case required by the assessor; Where: UY is the required value; η is the regulatory single item value required by the corresponding case; Bz is the proportion of the corresponding unqualified type; LAz is the type value of the corresponding unqualified type; Mark each regulatory item value in the assessor list.

Images