Auxiliary decision-making system and method based on clinical pathways

Abstract

The invention discloses an auxiliary decision-making system and method based on a clinical pathway, and relates to the technical field of clinical medicines.The system comprises a patient indication collection module, a clinical pathway simulation module, a pathway diagnosis and treatment analysis module and a pathway auxiliary decision-making module, and the patient indication collection module and the clinical pathway simulation module are arranged. Multi-dimensional medical indication analysis and prediction are carried out on all patients in the early stage of clinical path making, so that a clinical path simulation model conforming to the actual diagnosis and treatment conditions of the patients is constructed, a path diagnosis and treatment analysis module and a path auxiliary decision module are arranged, deep analysis is carried out on a plurality of clinical simulation paths generated by the clinical path simulation model, and a path diagnosis and treatment result is obtained. Each clinical simulation path is subjected to multi-stage disassembly analysis from the two aspects of diagnosis and treatment payment and diagnosis and treatment expression, so that an auxiliary decision-making clinical path conforming to medical resource configuration and clinical diagnosis and treatment effects is selected, and the accuracy and personalization of medical services are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of clinical medical technology, and more particularly, to a clinical pathway-based decision support system and method. Background Art

[0002] In current clinical practice, the development of clinical pathways often relies on the experience and expertise of healthcare professionals, lacking scientific, systematic data analysis and predictive tools. Traditional clinical pathway development methods typically involve gradual adjustments and refinements during the patient's treatment process. This "trial-and-error" approach to pathway development is not only inefficient but also struggles to ensure accuracy and personalization.

[0003] With the continuous advancement of medical technology and the increasing abundance of medical data, clinical pathway development methods based on big data and artificial intelligence have gradually become a research hotspot. However, existing clinical pathway development systems mostly focus solely on patients' physiological indicators and the diagnosis and treatment process, ignoring the cost of medical resources and the medical pressures on medical staff. As a result, the generated clinical pathways may not achieve the optimal balance between medical resource allocation and clinical diagnosis and treatment effectiveness.

[0004] In order to overcome the deficiencies of the prior art, the present invention proposes a clinical pathway-based decision support system and method. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a clinical pathway-based decision support system and method.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The auxiliary decision-making system based on clinical pathways includes a patient indication collection module, a clinical pathway simulation module, a pathway diagnosis and treatment analysis module, and a pathway auxiliary decision-making module;

[0008] The patient indication collection module is used to collect the initial data of the path of various types of medical indications of all patients;

[0009] The clinical pathway simulation module is used to determine the pathway termination data of various types of medical indications for all patients, and to construct a clinical pathway simulation model based on the pathway initial data and pathway termination data of various types of medical indications for all patients;

[0010] The pathway diagnosis and treatment parsing module controls the clinical pathway simulation model to generate multiple clinical simulation pathways and obtains the pathway diagnosis and treatment value of each clinical simulation pathway;

[0011] The pathway auxiliary decision module determines whether to mark the clinical simulation pathway as an auxiliary decision clinical pathway based on the comparison result of the pathway diagnosis and treatment value and the pathway diagnosis and treatment threshold.

[0012] Furthermore, a clinical pathway simulation model is constructed based on the initial pathway data and the final pathway data of various types of medical indications of all patients. Specifically, medical simulation software is selected, and an entity of each patient is created in the medical simulation software. Based on the initial pathway data of various types of medical indications of the patients, corresponding parameters are added to the patient entity, including vital signs, psychological status, and nutritional status. Based on the final pathway data of various types of medical indications of the patients, the diagnosis and treatment direction of each patient entity is determined, and a clinical pathway simulation model is constructed.

[0013] Furthermore, the path diagnosis and treatment value of the clinical simulation path is obtained as follows: during the simulation diagnosis and treatment process, the diagnosis and treatment disassembly time is set, and an indication performance time node is set after each diagnosis and treatment disassembly time, and the diagnosis and treatment path payment value of the diagnosis and treatment disassembly time and the node indication performance value of the indication performance time node are obtained. At the end of the simulation diagnosis and treatment, the path payment fluctuation value Rce and the number of path performance optimizations Bvx are obtained, and the diagnosis and treatment path payment values ​​of all diagnosis and treatment disassembly times are summed and averaged to obtain the diagnosis and treatment path payment mean Ve, and the node indication performance values ​​of all indication performance time nodes are summed and averaged to obtain the node indication performance mean Mt. Using the formula The path diagnosis and treatment value Ysaw of the clinical simulation pathway is obtained, where u1 is the path effort fluctuation coefficient, u2 is the path performance optimization coefficient, u3 is the path effort mean coefficient, and u4 is the indication performance mean coefficient.

[0014] Furthermore, the path payment fluctuation value Rce is obtained as follows: all the diagnosis and treatment path payment values ​​are sorted in order of the diagnosis and treatment decomposition time, and the difference between the two adjacent diagnosis and treatment path payment values ​​after sorting is calculated and the absolute value is taken to obtain the path payment fluctuation value Rce.

[0015] Furthermore, the path performance optimization times Bvx are obtained as follows: all node indication performance values ​​are sorted in sequence according to the order of indication performance time nodes, and the indication performance value of the adjacent previous node after sorting is compared with the indication performance value of the next node. When the indication performance value of the previous node is greater than or equal to the indication performance value of the next node, no further processing is performed. When the indication performance value of the previous node is less than the indication performance value of the next node, the path performance optimization times are increased by one, and the path performance optimization times are marked as Bvx.

[0016] Furthermore, the node indication performance value of the indication performance time node is obtained as follows: obtain the comprehensive indication performance value of each patient entity, match all patient entities in pairs, calculate the difference between the comprehensive indication performance values ​​of the two matched patient entities and take the absolute value to obtain the indicator performance gap value, sum up all the indicator performance gap values ​​to obtain the total indicator performance gap value Jcvt, sum up the comprehensive indication performance values ​​of all patient entities to obtain the total comprehensive indication performance value Trgb, and use the formula The node indicator performance value Shyb of the indicator performance time node is obtained, where v1 is the indicator performance gap coefficient and v2 is the comprehensive indicator performance coefficient.

[0017] Furthermore, the comprehensive indication performance value of the patient entity is obtained as follows: the indication data of each type of medical indication is collected when the patient entity is at the indication performance time node, the indication data of each type of medical indication is extracted and integrated into a comprehensive medical indication feature, a comprehensive indication performance model is obtained, the comprehensive medical indication feature is input into the comprehensive indication performance model, and the comprehensive indication performance model outputs the comprehensive indication performance value of the patient entity.

[0018] Furthermore, the method for obtaining the treatment path payment value of the treatment disassembly time is as follows: collect all activity logs within the treatment disassembly time, the activity logs include activity type, patient entity name, activity start time, activity end time, obtain the patient entity name in the activity log, mark the activity logs of the same patient entity as the same patient activity log, and then obtain the treatment payment value Zsw of each patient entity, s=1, 2, …, S, s is the patient entity number, S is the total number of patient entities, set the treatment payment coefficient to pw, w=1, 2, 3, …, w-1, w, p1<p2<p3<…<pw-1<pw, use the formula Get the treatment path payment value Diam of the treatment breakdown time.

[0019] Furthermore, the method for obtaining the diagnosis and treatment payment value of the patient entity is as follows: sort all the patient activity logs of a patient entity in the order of the activities, compare the activity types of the two adjacent patient activity logs after sorting, when the activity types of the two adjacent patient activity logs are the same, increase the number of activity repetitions by one, when the activity types of the two adjacent patient activity logs are different, no further processing is performed, mark the number of activity repetitions as Ysg, calculate the time difference between the end time and the start time of the activity in the patient activity log, obtain the activity payment duration, sum up all the activity payment durations and take the average to obtain the average activity payment duration Tmg, mark the total number of patient activity logs as Nge, and use the formula The diagnosis and treatment payment value Zsw of the patient entity is obtained, where ha is the activity repetition coefficient, hb is the activity payment duration coefficient, and hc is the activity log quantity coefficient.

[0020] Furthermore, the decision-making support method based on the clinical pathway includes the following steps:

[0021] Step 1: Collect initial pathway data for all types of medical indications for all patients;

[0022] Step 2: Determine the pathway end data for each type of medical indication for all patients;

[0023] Step 3: Construct a clinical pathway simulation model based on the initial and final pathway data of all patients with various medical indications;

[0024] Step 4: The clinical pathway simulation model generates multiple clinical simulation pathways and obtains the pathway diagnosis and treatment value of each clinical simulation pathway;

[0025] Step 5: Based on the comparison results of the pathway diagnosis and treatment value and the pathway diagnosis and treatment threshold, determine whether to mark the clinical simulation pathway as an auxiliary decision-making clinical pathway.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The method of the present invention conducts a multi-stage disassembly and analysis of each clinical simulation pathway from the perspectives of treatment effort and treatment performance, thereby selecting a decision-making auxiliary clinical pathway that is consistent with medical resource allocation and clinical treatment effectiveness, ensuring the accuracy and personalization of medical services;

[0028] 2. Set up a patient indication collection module and a clinical pathway simulation module, conduct multi-dimensional medical indication analysis and prediction on all patients in the early stage of clinical pathway formulation, so as to build a clinical pathway simulation model that fits the patient's actual diagnosis and treatment situation, set up a pathway diagnosis and treatment analysis module and a pathway decision-making assistance module, and conduct in-depth analysis of multiple clinical simulation pathways generated by the clinical pathway simulation model to provide medical staff with fast and accurate decision-making support, which helps to shorten the time of medical decision-making and improve the efficiency of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flowchart of the method for the clinical pathway-based decision support method;

[0030] Figure 2 This is the system module diagram of the clinical pathway-based decision support system;

[0031] Figure 3 Flowchart for the construction of clinical pathway simulation model. DETAILED DESCRIPTION

[0032] Example 1: Reference Figure 1 , the decision-making support method based on clinical pathway includes the following steps:

[0033] Step 1: Collect initial pathway data for all types of medical indications for all patients;

[0034] Step 2: Determine the pathway end data for each type of medical indication for all patients;

[0035] Step 3: Construct a clinical pathway simulation model based on the initial and final pathway data of all patients with various medical indications;

[0036] Step 4: The clinical pathway simulation model generates multiple clinical simulation pathways and obtains the pathway diagnosis and treatment value of each clinical simulation pathway;

[0037] Step 5: Based on the comparison results of the pathway diagnosis and treatment value and the pathway diagnosis and treatment threshold, determine whether to mark the clinical simulation pathway as an auxiliary decision-making clinical pathway.

[0038] Example 2: Reference Figures 2 to 3 , the auxiliary decision-making system based on clinical pathways includes patient indication collection module, clinical pathway simulation module, pathway diagnosis and treatment analysis module, and pathway auxiliary decision-making module.

[0039] A clinical pathway is a standardized diagnosis and treatment plan developed for a specific disease or surgery. It is aimed at multiple patients suffering from the disease or needing to undergo the surgery. If a total of i patients have the same disease, a clinical pathway needs to be set for i patients. The clinical pathway includes the sequence and timing of each patient's treatment, care, examination and other activities.

[0040] Patient indication collection module: collects initial pathway data of various types of medical indications for all patients (types of treatment indications include but are not limited to vital signs indications, psychological status indications, nutritional status indications, etc. The initial pathway data is the data generated when the patient undergoes the corresponding medical indication examination before the clinical pathway is customized. For example, before the clinical pathway is customized, the vital signs indication examination of patient A is performed, and the initial pathway data of patient A's vital signs indications are obtained).

[0041] Clinical pathway simulation module: Determine the pathway termination data of various types of medical indications for all patients (pathway termination data is the data expected to be generated when the patient undergoes the corresponding medical indication examination after full recovery. For example, when patient B undergoes a psychological condition indication examination after full recovery, the pathway termination data of patient B’s psychological condition indication will be obtained). Construct a clinical pathway simulation model based on the pathway initial data and pathway termination data of various types of medical indications for all patients.

[0042] A clinical pathway simulation model is constructed based on the initial pathway data and the final pathway data of various types of medical indications of all patients. The clinical pathway simulation model generates multiple clinical simulation pathways. Specifically, medical simulation software such as ANYLOGIC and Flexsim is selected to create an entity of each patient in the simulation software. Based on the initial pathway data of various types of medical indications of the patient, corresponding parameters are added to the patient entity, including vital signs, psychological status, nutritional status, etc. Based on the final pathway data of various types of medical indications of the patient, the diagnosis and treatment direction of each patient entity is determined, and a clinical pathway simulation model is constructed. The clinical pathway simulation model can simulate diagnosis and treatment according to the diagnosis and treatment direction of each patient entity, and a clinical simulation pathway is generated for each simulated diagnosis and treatment.

[0043] A patient indication collection module and a clinical pathway simulation module are set up to conduct multi-dimensional medical indication analysis and prediction on all patients in the early stage of clinical pathway formulation, so as to build a clinical pathway simulation model that fits the patient's actual diagnosis and treatment situation.

[0044] Pathway diagnosis and treatment analysis module: The clinical pathway simulation model generates multiple clinical simulation pathways (multiple simulations can generate multiple different clinical simulation pathways) and obtains the pathway diagnosis and treatment value of each clinical simulation pathway.

[0045] The path diagnosis and treatment value of the clinical simulation path is obtained as follows: during the simulation diagnosis and treatment process, the diagnosis and treatment disassembly time is set (the diagnosis and treatment disassembly time is a preset time period, and the length of the time period is modified according to the needs. During the simulation diagnosis and treatment process, the diagnosis and treatment disassembly time is infinitely looped), and an indication performance time node is set after each diagnosis and treatment disassembly time. The diagnosis and treatment path payment value of the diagnosis and treatment disassembly time and the node indication performance value of the indication performance time node are obtained. At the end of the simulation diagnosis and treatment, all the diagnosis and treatment path payment values ​​are sorted in order according to the diagnosis and treatment disassembly time, and the difference between the two adjacent diagnosis and treatment path payment values ​​after sorting is calculated and the absolute value is taken to obtain the path payment fluctuation value Rce, and all the node indication performance values ​​are sorted according to the diagnosis and treatment disassembly time. Sort the indication performance time nodes in order, compare the indication performance value of the previous node with the indication performance value of the next node after sorting, and do not do further processing when the indication performance value of the current node is greater than or equal to the indication performance value of the next node. When the indication performance value of the current node is less than the indication performance value of the next node, increase the number of path performance optimizations by one, and mark the number of path performance optimizations as Bvx. Sum up and average the treatment path expenditure values ​​of all treatment decomposition times to obtain the mean treatment path expenditure Ve. Sum up and average the node indication performance values ​​of all indication performance time nodes to obtain the node indication performance mean Mt. Use the formula The pathway diagnosis and treatment value Ysaw of the clinical simulation pathway is obtained, where u1 is the pathway effort fluctuation coefficient, u2 is the pathway performance optimization coefficient, u3 is the pathway effort mean coefficient, and u4 is the indication performance mean coefficient. The value of u1 is 0.51, the value of u2 is 0.83, the value of u3 is 0.44, and the value of u4 is 0.62.

[0046] The node indication performance value of the indication performance time node is obtained as follows: obtain the comprehensive indication performance value of each patient entity, match all patient entities in pairs, calculate the difference between the comprehensive indication performance values ​​of the two matched patient entities and take the absolute value to obtain the indicator performance gap value, sum up all the indicator performance gap values ​​to obtain the total indicator performance gap value Jcvt, sum up the comprehensive indication performance values ​​of all patient entities to obtain the total comprehensive indication performance value Trgb, and use the formula The node indicator performance value Shyb of the indicator performance time node is obtained, where v1 is the indicator performance gap coefficient, v2 is the comprehensive indicator performance coefficient, the value of v1 is 1.48, and the value of v2 is 0.81.

[0047] The method for obtaining the comprehensive indication performance value of the patient entity is as follows: collecting the indication data of various types of medical indications when the patient entity is at the indication performance time node, extracting features of the indication data of various types of medical indications and fusing them into comprehensive medical indication features, obtaining a comprehensive indication performance model, inputting the comprehensive medical indication features into the comprehensive indication performance model, and the comprehensive indication performance model outputs the comprehensive indication performance value of the patient entity.

[0048] The comprehensive indication performance model is constructed as follows: obtain multiple comprehensive medical indication features, each comprehensive medical indication feature can be data collected from real patients or virtually set data, build a deep learning model, use the comprehensive medical indication features as training data for the deep learning model, and assign a comprehensive indication performance value to each training data, the comprehensive indication performance value is (1.0~8.0), the larger the comprehensive indication performance value, the better the medical indication performance of the patient entity, and the smaller the comprehensive indication performance value, the worse the medical indication performance of the patient entity. Divide all training data into 70% training set and 30% validation set, train the training set and validation set, and after the training is completed, construct a comprehensive indication performance model.

[0049] The method for obtaining the treatment path payment value of the treatment breakdown time is as follows: collect all activity logs within the treatment breakdown time (in the simulated treatment process, each time an activity is taken on a patient entity, an activity log is generated. The activity log includes the activity type (activity types include treatment, nursing, examination, etc.), the patient entity name, the activity start time, and the activity end time), obtain the patient entity name in the activity log, mark the activity log of the same patient entity as the same patient activity log, and then obtain the treatment payment value Zs of each patient entity. w, s = 1, 2, ..., S, s is the number of patient entities, S is the total number of patient entities, set the treatment payment coefficient to pw, w = 1, 2, 3, ..., w-1, w, p1 < p2 < p3 < ... < pw-1 < pw, each treatment payment coefficient pw corresponds to a treatment payment value within a range, the range of treatment payment value includes (0, Zs1], (Zs1, Zs2], ..., (Zsw-1, Zsw], when Zsw∈(0, Zs1], the treatment payment coefficient is p1, using the formula Get the treatment path payment value Diam of the treatment breakdown time.

[0050] The method for obtaining the diagnosis and treatment payment value of a patient entity is as follows: sort all the patient activity logs of a patient entity in the order of the activities, compare the activity types of two adjacent patient activity logs after sorting, when the activity types of two adjacent patient activity logs are the same, increase the number of activity repetitions by one, when the activity types of two adjacent patient activity logs are different, no further processing is done, mark the number of activity repetitions as Ysg, calculate the time difference between the end time and the start time of the activity in the patient activity log, obtain the activity payment duration, sum up all the activity payment durations and take the average to obtain the average activity payment duration Tmg, mark the total number of patient activity logs as Nge, and use the formula The medical treatment expenditure value Zsw of the patient entity is obtained, where ha is the activity repetition coefficient, hb is the activity expenditure duration coefficient, and hc is the activity log quantity coefficient. The value of ha is 0.98, the value of hb is 1.14, and the value of hc is 0.95.

[0051] Pathway decision-making assistance module: Set the path diagnosis and treatment threshold (the path diagnosis and treatment threshold is the system preset threshold). When the path diagnosis and treatment value of the clinical simulation pathway is greater than or equal to the path diagnosis and treatment threshold, the clinical simulation pathway is marked as an assisted decision-making clinical pathway (medical staff can select an assisted decision-making clinical pathway from all assisted decision-making clinical pathways based on the actual medical situation, and arrange treatment, care, examination and other activities for all patients based on the assisted decision-making clinical pathway). When the path diagnosis and treatment value of the clinical simulation pathway is less than the path diagnosis and treatment threshold, no further processing is performed.

[0052] A pathway diagnosis and treatment analysis module and a pathway decision-making support module are set up to conduct in-depth analysis of multiple clinical simulation pathways generated by the clinical pathway simulation model, and conduct multi-stage disassembly and analysis of each clinical simulation pathway from the two levels of diagnosis and treatment effort and diagnosis and treatment performance, so as to select decision-making support clinical pathways that are in line with medical resource allocation and clinical diagnosis and treatment effects, ensure the accuracy and personalization of medical services, provide medical staff with fast and accurate decision-making support, help shorten the time of medical decision-making, and improve the efficiency of medical services.

[0053] The above formulas are all dimensionless and numerically calculated, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0054] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0055] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0057] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0058] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0059] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0060] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. The auxiliary decision-making system based on clinical pathway is characterized by: It includes patient indication collection module, clinical pathway simulation module, pathway diagnosis and treatment analysis module, and pathway decision-making assistance module; The patient indication collection module is used to collect the initial data of the path of various types of medical indications of all patients; The clinical pathway simulation module is used to determine the pathway termination data of various types of medical indications for all patients, and to construct a clinical pathway simulation model based on the pathway initial data and pathway termination data of various types of medical indications for all patients; The pathway diagnosis and treatment parsing module controls the clinical pathway simulation model to generate multiple clinical simulation pathways and obtains the pathway diagnosis and treatment value of each clinical simulation pathway; The pathway auxiliary decision module determines whether to mark the clinical simulation pathway as an auxiliary decision clinical pathway based on the comparison result of the pathway diagnosis and treatment value and the pathway diagnosis and treatment threshold.

2. The clinical pathway-based decision support system according to claim 1, characterized in that: A clinical pathway simulation model is constructed based on the initial pathway data and the final pathway data of various types of medical indications of all patients. Specifically, medical simulation software is selected, and an entity of each patient is created in the medical simulation software. Based on the initial pathway data of various types of medical indications of the patients, corresponding parameters are added to the patient entity, including vital signs, psychological status, and nutritional status. Based on the final pathway data of various types of medical indications of the patients, the diagnosis and treatment direction of each patient entity is determined, and a clinical pathway simulation model is constructed.

3. The clinical pathway-based decision support system according to claim 1, characterized in that: The path diagnosis and treatment value of the clinical simulation path is obtained as follows: during the simulation diagnosis and treatment process, the diagnosis and treatment disassembly time is set, and an indication performance time node is set after each diagnosis and treatment disassembly time, and the diagnosis and treatment path payment value of the diagnosis and treatment disassembly time and the node indication performance value of the indication performance time node are obtained. At the end of the simulation diagnosis and treatment, the path payment fluctuation value Rce and the number of path performance optimizations Bvx are obtained, and the diagnosis and treatment path payment values ​​of all diagnosis and treatment disassembly times are summed and averaged to obtain the diagnosis and treatment path payment mean Ve, and the node indication performance values ​​of all indication performance time nodes are summed and averaged to obtain the node indication performance mean Mt. The formula is used. The path diagnosis and treatment value Ysaw of the clinical simulation pathway is obtained, where u1 is the path effort fluctuation coefficient, u2 is the path performance optimization coefficient, u3 is the path effort mean coefficient, and u4 is the indication performance mean coefficient.

4. The clinical pathway-based decision support system according to claim 3, characterized in that: The path payment fluctuation value Rce is obtained as follows: all diagnosis and treatment path payment values ​​are sorted in order according to the length of diagnosis and treatment decomposition, and the difference between the two adjacent diagnosis and treatment path payment values ​​after sorting is calculated and the absolute value is taken to obtain the path payment fluctuation value Rce.

5. The clinical pathway-based decision support system according to claim 3, characterized in that: The path performance optimization times Bvx are obtained as follows: all node indicator performance values ​​are sorted in the order of the indicator performance time nodes, and the indicator performance value of the previous node after sorting is compared with the indicator performance value of the next node. When the indicator performance value of the previous node is greater than or equal to the indicator performance value of the next node, no further processing is performed. When the indicator performance value of the previous node is less than the indicator performance value of the next node, the path performance optimization times are increased by one, and the path performance optimization times are marked as Bvx.

6. The clinical pathway-based decision support system according to claim 3, characterized in that: The node indication performance value of the indication performance time node is obtained as follows: obtain the comprehensive indication performance value of each patient entity, match all patient entities in pairs, calculate the difference between the comprehensive indication performance values ​​of the two matched patient entities and take the absolute value to obtain the indicator performance gap value, sum up all the indicator performance gap values ​​to obtain the total indicator performance gap value Jcvt, sum up the comprehensive indication performance values ​​of all patient entities to obtain the total comprehensive indication performance value Trgb, and use the formula The node indicator performance value Shyb of the indicator performance time node is obtained, where v1 is the indicator performance gap coefficient and v2 is the comprehensive indicator performance coefficient.

7. The clinical pathway-based decision support system according to claim 6, characterized in that: The method for obtaining the comprehensive indication performance value of the patient entity is as follows: collecting the indication data of various types of medical indications when the patient entity is at the indication performance time node, extracting features of the indication data of various types of medical indications and fusing them into comprehensive medical indication features, obtaining a comprehensive indication performance model, inputting the comprehensive medical indication features into the comprehensive indication performance model, and the comprehensive indication performance model outputs the comprehensive indication performance value of the patient entity.

8. The clinical pathway-based decision support system according to claim 3, characterized in that: The method for obtaining the treatment path payment value of the treatment disassembly time is as follows: collect all activity logs within the treatment disassembly time, the activity log includes the activity type, patient entity name, activity start time, and activity end time, obtain the patient entity name of the activity log, mark the activity log of the same patient entity as the same patient activity log, and then obtain the treatment payment value Zsw of each patient entity, s=1, 2, …, S, s is the patient entity number, S is the total number of patient entities, set the treatment payment coefficient to pw, w=1, 2, 3, …, w-1, w, p1<p2<p3<…<pw-1<pw, use the formula Get the treatment path payment value Diam of the treatment breakdown time.

9. The clinical pathway-based decision support system according to claim 8, characterized in that: The method for obtaining the diagnosis and treatment payment value of a patient entity is as follows: sort all the patient activity logs of a patient entity in the order of the activities, compare the activity types of two adjacent patient activity logs after sorting, when the activity types of two adjacent patient activity logs are the same, increase the number of activity repetitions by one, when the activity types of two adjacent patient activity logs are different, no further processing is done, mark the number of activity repetitions as Ysg, calculate the time difference between the end time and the start time of the activity in the patient activity log, obtain the activity payment duration, sum up all the activity payment durations and take the average to obtain the average activity payment duration Tmg, mark the total number of patient activity logs as Nge, and use the formula The diagnosis and treatment payment value Zsw of the patient entity is obtained, where ha is the activity repetition coefficient, hb is the activity payment duration coefficient, and hc is the activity log quantity coefficient.

10. A clinical pathway-based decision support method, applied to a clinical pathway-based decision support system according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Collect initial pathway data for all types of medical indications for all patients; Step 2: Determine the pathway end data for each type of medical indication for all patients; Step 3: Construct a clinical pathway simulation model based on the initial and final pathway data of all patients with various medical indications; Step 4: The clinical pathway simulation model generates multiple clinical simulation pathways and obtains the pathway diagnosis and treatment value of each clinical simulation pathway; Step 5: Based on the comparison results of the pathway diagnosis and treatment value and the pathway diagnosis and treatment threshold, determine whether to mark the clinical simulation pathway as an auxiliary decision-making clinical pathway.

Images