A method for automatic planning of clinical pathways

Abstract

The present invention relates to the technical field of health informatics, and in particular to a method for automatic planning of clinical pathways, the method comprising: performing DRG grouping according to case data of a target user to obtain a nursing purpose; determining a clinical pathway template according to the historical clinical pathways of historical users; determining similar users similar to the target user according to historical case data and case data of the target user; determining missing nursing measures using the historical clinical pathways of similar users; determining the weight of missing nursing measures based on the historical clinical pathways and the nursing purpose of the target user; determining target missing nursing measures using the weights, a first number of similar users, and a second number of similar users corresponding to the missing nursing measures; adding the target missing nursing measures to the clinical pathway template to obtain the final clinical pathway of the target user. The technical solution provided by the present application saves a lot of manpower and time, and improves the planning efficiency of clinical pathways.

Description

Technical Field

[0001] The present invention relates to the technical field of health informatics, and in particular to a method for automatic planning of a clinical pathway. Background Art

[0002] Clinical Pathway (CP), also known as clinical pathway or medical care pathway, is a standardized diagnosis and treatment and nursing program developed through interdisciplinary cooperation based on evidence-based medicine. It aims to provide patients with high-quality and efficient medical services, and through standardized processes and timetables, make service work more planned and predictable, and ensure that patients receive the best and consistent treatment and care throughout the entire medical process from admission to discharge.

[0003] In some scenarios, Diagnosis-Related Groups (DRGs) provide standardized classifications for different types of cases. The core of this is to classify patients' cases and group similar cases together by analyzing their clinical characteristics and resource consumption. However, after using DRGs to group patients, it is necessary to determine the personalized clinical pathway for each patient in turn based on factors such as the patient's characteristics, which is not only time-consuming and labor-intensive, but also inefficient. Summary of the invention

[0004] In order to solve the technical problems of time-consuming, labor-intensive and low efficiency in planning a personalized clinical pathway for each patient, the present invention aims to provide a method for automatic clinical pathway planning. The technical solution adopted is as follows:

[0005] An embodiment of the present application provides a method for automatic planning of a clinical pathway, including: performing DRG grouping on the target user according to the case data of the target user to obtain the target DRG group to which the target user belongs, and obtaining the nursing purpose of the target user; determining the clinical pathway template of the target DRG group according to the historical clinical pathways of all historical users of the target DRG group; determining similar users similar to the target user from each historical user according to the historical case data of each historical user of the target DRG group and the case data of the target user; determining missing nursing measures missing in the clinical pathway template by using the historical clinical pathways of the similar users; determining the weight of the missing nursing measures based on the historical clinical pathways of each historical user of the target DRG group and the nursing purpose of the target user; determining the target missing nursing measures for the target user by using the weight, the first number of similar users and the second number of similar users corresponding to the missing nursing measures in the clinical pathway template; adding the target missing nursing measures to the clinical pathway template to obtain the final clinical pathway of the target user.

[0006] Optionally, determining similar users who are similar to the target user from each historical user based on the historical case data of each historical user of the target DRG group and the case data of the target user includes: classifying each historical user based on the historical case data of each historical user of the target DRG group to obtain multiple user groups; determining the case similarity between each historical user in the target DRG group and the target user based on the historical case data of the user group to which each historical user of the target DRG group belongs, the historical case data of each historical user and the case data of the target user; determining similar users who are similar to the target user from each historical user in the target DRG group based on the case similarity.

[0007] Optionally, determining the case similarity between each historical user in the target DRG group and the target user based on the historical case data of the user group to which each historical user of the target DRG group belongs, the historical case data of each historical user and the case data of the target user includes: determining a third number of keyword intersections of a case keyword set of the target user's case data and a case keyword set of the historical case data of the historical user; determining a fourth number of keyword intersections of a case keyword set of the target user's case data and a case keyword set of the historical case data of the user group to which each historical user of the target DRG group belongs; determining a fifth number of case keywords of the historical case data of the historical users, and a sixth number of case keywords of the historical case data of the user group to which each historical user of the target DRG group belongs; calculating a first ratio of the third number to the fifth number, and a second ratio of the fourth number to the sixth number; and determining the superposition value of the first ratio and the second ratio as the case similarity.

[0008] Optionally, determining the clinical pathway template of the target DRG group based on the historical clinical pathways of all historical users of the target DRG group includes: serializing the historical clinical pathways of the historical users to obtain multiple sequence items; constructing a frequent pattern tree using each sequence item to determine the sequence items that appear repeatedly in the historical clinical pathways of multiple historical users through the frequent pattern tree to obtain a frequent item set; determining a clinical pathway pattern that meets the nursing objectives of the target users from the sequence items of the frequent item set, the clinical pathway pattern characterizing the nursing processes that frequently appear in the target DRG group; determining the frequent item set with the largest number of item sets and the highest frequency that meets the clinical pathway pattern, and the constructed path is the clinical pathway template.

[0009] Optionally, using the historical clinical pathways of similar users to determine missing nursing measures that are missing in the clinical pathway template includes: serializing the historical clinical pathways of similar users to obtain multiple first sequence items, and serializing the clinical pathway template to obtain multiple second sequence items; comparing each first sequence item with each second sequence item to determine the missing first sequence item in the clinical pathway template; and determining that the nursing measures corresponding to the missing first sequence items are the missing nursing measures.

[0010] Optionally, based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target users, determining the weights of missing nursing measures includes: determining the nursing similarity between the nursing objectives of each historical user in the target DRG group and the target user based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target users; determining the product of case similarity and nursing similarity as the weight of the missing nursing measures for similar users.

[0011] Optionally, based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target user, determining the nursing similarity between the nursing objectives of each historical user in the target DRG group and the target user includes: determining a keyword set of the target user's nursing objectives, and a keyword set of the nursing objectives in the historical clinical pathways of the historical users; calculating the seventh number of keyword intersections of the keyword set of the target user's nursing objectives and the keyword set of the nursing objectives in the historical clinical pathways of the historical users; determining the eighth number of keywords for the nursing objectives in the historical clinical pathways of the historical users; and determining the third ratio of the seventh number to the eighth number as the nursing similarity.

[0012] Optionally, determining the target missing nursing measures for the target user using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the clinical pathway template includes: determining the importance of the missing nursing measures for the similar users using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway, the importance representing the importance of the missing nursing measures to the care of the target user; determining the target missing nursing measures for the target user based on the importance.

[0013] Optionally, determining the importance of the missing nursing measures of similar users using weights, a first number of similar users, and a second number of similar users corresponding to the missing nursing measures existing in the clinical pathway template includes: calculating a fourth ratio of the second number to the first number, and superimposing the weights of the missing nursing measures of each similar user to obtain a superimposed weight; calculating the product of the fourth ratio and the superimposed weight; and determining the normalized product as the importance.

[0014] Optionally, determining the target missing care measures of the target user according to the importance includes: determining the missing care measures whose importance is greater than a threshold as the target missing care measures.

[0015] The present invention has the following beneficial effects: by performing DRG grouping on the target user according to the case data of the target user, the target DRG group to which the target user belongs is obtained, and the nursing purpose of the target user is obtained; then, based on the historical clinical pathways of all historical users of the target DRG group, the clinical pathway template of the target DRG group is determined; and based on the historical case data of each historical user of the target DRG group and the case data of the target user, similar users similar to the target user are determined from each historical user; then, the historical clinical pathways of the similar users are used to determine the missing nursing measures that are missing in the clinical pathway template; and based on the historical clinical pathways of each historical user of the target DRG group and the nursing purpose of the target user, the weight of the missing nursing measures is determined; then, the target missing nursing measures for the target user are determined using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures in the clinical pathway template; finally, the target missing nursing measures are added to the clinical pathway template to obtain the final clinical pathway of the target user.

[0016] In this way, for each user, this application determines a standardized clinical pathway template according to the historical clinical pathways of the historical users of the DRG group to which the user belongs, and then determines the missing nursing measures of the clinical pathway template of the DRG group to which the current user belongs based on the historical case data and historical clinical pathways of the historical users, and then determines the nursing measures that the user ultimately lacks based on the historical clinical pathways of the historical users and the nursing objectives of the target user, and adds the missing nursing measures to the clinical pathway template to obtain the user's final clinical pathway. Therefore, this application does not need to determine the personalized clinical pathway for each patient in turn based on factors such as the patient's characteristics, but only needs to add the missing nursing measures of the user to the clinical pathway template, which saves a lot of manpower and time and improves the planning efficiency of the clinical pathway. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0018] Figure 1 A flowchart of a method for automatic clinical pathway planning provided by one embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the module composition of a clinical pathway automatic planning device provided by one embodiment of the present invention;

[0020] Figure 3A schematic diagram of the structure of a clinical pathway automatic planning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the clinical pathway automatic planning method proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0022] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0023] The following is a detailed description of a clinical pathway automatic planning method provided by the present invention in conjunction with the accompanying drawings.

[0024] Embodiment 1:

[0025] See also Figure 1 , which shows a flow chart of a method for automatic clinical pathway planning provided by an embodiment of the present invention, including:

[0026] Step S101, DRG grouping the target user according to the case data of the target user, obtaining the target DRG group to which the target user belongs, and obtaining the nursing purpose of the target user.

[0027] Specifically, the target user refers to the patient who currently needs clinical pathway planning. The case data includes but is not limited to the patient's basic information, the patient's disease information, the medical diagnostic center (MDC) to which the patient belongs, and the patient's treatment method. Basic information includes but is not limited to age, gender, contact information, height, and weight. The patient's disease information includes but is not limited to major diseases, complications and comorbidities, important complications and comorbidities, etc. MDC is usually based on anatomical and physiological systems, such as the circulatory system, digestive system, etc. The patient's treatment method includes but is not limited to surgery, non-surgical operations, internal medicine diagnosis and treatment, etc. Patients are grouped into DRGs according to the case data of the above patients. The nursing purpose of the target user refers to the nursing goal formulated according to the user's case data. For example, if the user's disease is a leg fracture, the nursing purpose is to care for the leg fracture.

[0028] Step S102, determining the clinical pathway template of the target DRG group based on the historical clinical pathways of all historical users of the target DRG group.

[0029] Specifically, after determining the DRG group to which the target user belongs, the DRG group also includes historical users, and the historical users have corresponding medical records, which include historical case data and historical clinical pathways. Historical case data includes but is not limited to the patient's basic information, the patient's disease information, the MDC to which the patient belongs, and the patient's treatment methods. Basic information includes but is not limited to age, gender, contact information, height, and weight. The patient's disease information includes but is not limited to major diseases, complications and comorbidities, important complications and comorbidities, etc. MDC is usually based on anatomical and physiological systems, such as the circulatory system, digestive system, etc. The patient's treatment methods include but are not limited to surgery, non-surgical operations, internal medicine diagnosis and treatment, etc. The patients are grouped into DRGs according to the case data of the above patients. The historical clinical pathway includes but is not limited to formulating a corresponding nursing plan with time as the horizontal axis and nursing measures as the vertical axis, and describing in detail the nursing time, nursing measures, and nursing purposes, etc. In addition, the medical records also include the expected diagnosis and treatment results, and how to allocate medical resources according to the DRG grouping of historical users, including the configuration of medical staff, the use of medical equipment, and the supply of drugs and consumables.

[0030] Furthermore, since there are commonalities in the cases and care of patients in the same DRG group, a standardized clinical pathway template can be determined through the historical clinical pathways of historical users in the DRG group, and the clinical pathway that appears more frequently in the current DRG group can be used as the clinical pathway template for the current DRG group.

[0031] As an optional embodiment of the present application, determining the clinical pathway template of the target DRG group based on the historical clinical pathways of all historical users of the target DRG group includes: serializing the historical clinical pathways of the historical users to obtain multiple sequence items; using each sequence item to construct a frequent pattern tree to determine the sequence items that appear repeatedly in the historical clinical pathways of multiple historical users through the frequent pattern tree to obtain a frequent item set; determining a clinical pathway pattern that meets the nursing purpose of the target user from the sequence items of the frequent item set, the clinical pathway pattern characterizing the nursing process that frequently appears in the target DRG group; determining the frequent item set with the maximum number of item sets and the highest frequency that meets the clinical pathway pattern, and the constructed path is the clinical pathway template.

[0032] Specifically, the historical clinical pathways can be obtained from the medical records of all patients in the current DRG group, and then the historical clinical pathways of each patient can be serialized to form sequence items. Frequent pattern trees (FP) are constructed using each sequence item, and the FP tree is used to mine frequent item sets, which are sequence items that appear repeatedly in the clinical pathways of multiple patients. The clinical pathway pattern that meets the nursing purpose of the target user is extracted from the frequent item set. The clinical pathway pattern represents the common nursing process in the current DRG group. Finally, the path consisting of the most frequent item sets that meet the current clinical pathway pattern and the highest frequency is determined as the clinical pathway template for the current DRG group.

[0033] Step S103, determining similar users who are similar to the target user from among the historical users based on the historical case data of the historical users of the target DRG group and the case data of the target user.

[0034] Specifically, for any patient (target user) in the current DRG group whose clinical pathway has not been determined, similar patients to the current patient can be determined based on the case data between the current patient and historical users. Since the clinical pathways of similar patients are likely to be similar to the current patient's, the nursing measures missing from the clinical pathway template of the current DRG group can be determined based on similar patients. Since the nursing purposes of different patients are different, the final missing nursing measures are screened out based on the nursing purposes of the current patient and historical patients.

[0035] Furthermore, when determining similar users, case texts such as disease names, symptoms, and examination items of historical users and target users can be extracted from the historical case data of historical users and the case data of target users. Natural language processing (NLP) technology is used to perform word segmentation, part-of-speech tagging, and entity recognition on the case text to accurately extract professional terms in the case text, and the extracted professional terms are determined to be the case keyword set of the current patient and historical users. Historical users with a high degree of overlap in case keywords are selected as similar users of the current patient.

[0036] Further, as an optional embodiment of the present application, determining similar users similar to the target user from each historical user according to the historical case data of each historical user of the target DRG group and the case data of the target user includes: classifying each historical user according to the historical case data of each historical user of the target DRG group to obtain multiple user groups; determining the case similarity between each historical user in the target DRG group and the target user according to the historical case data of the user group to which each historical user of the target DRG group belongs, the historical case data of each historical user and the case data of the target user; determining similar users similar to the target user from each historical user in the target DRG group based on the case similarity.

[0037] Specifically, patients with similar case characteristics are classified to avoid the situation where similar users cannot be identified due to incomplete case information of some patients. Specifically, classification can be performed based on the case keywords of the historical case data of each historical user in the current DRG group. More specifically, in order to improve the classification accuracy, the weighted technology (Term Frequency-Inverse Document Frequency, TF-IDF) used for information retrieval and text mining can be used to assign weights to each case keyword, and then the Jaccard similarity is used to calculate the similarity between the weighted case keywords, and finally the density-based clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) is used to classify historical users according to the similarity to obtain multiple user groups. In each user group, the case conditions of patients are similar.

[0038] Furthermore, the case similarity between the current target user and any historical user can be determined based on the intersection of case keywords between the current target user and historical users, and the intersection of case keywords of the current target user and the case keywords of the user group to which the historical user belongs. Case similarity characterizes the degree of similarity between the cases of the current target user and any historical user. The higher the case similarity, the higher the degree of similarity between the cases of the current target user and any historical user. When determining similar users similar to the target user from each historical user in the target DRG group based on case similarity, the case similarity can be normalized, and the normalized numerical range is [0, 1]. Historical users whose case similarity is greater than the threshold are regarded as similar users of the target user. Among them, the threshold can be determined according to the actual situation, such as a value of 0.7, which is not limited in the embodiments of the present application.

[0039] As an optional embodiment of the present application, determining the case similarity between each historical user in the target DRG group and the target user based on the historical case data of the user group to which each historical user of the target DRG group belongs, the historical case data of each historical user and the case data of the target user includes: determining the third number of keyword intersections of the case keyword set of the target user's case data and the case keyword set of the historical case data of the historical user; determining the fourth number of keyword intersections of the case keyword set of the target user's case data and the case keyword set of the historical case data of the user group to which each historical user of the target DRG group belongs; determining the fifth number of case keywords of the historical case data of the historical users, and the sixth number of case keywords of the historical case data of the user group to which each historical user of the target DRG group belongs; calculating a first ratio of the third number to the fifth number, and a second ratio of the fourth number to the sixth number; and determining the superposition value of the first ratio and the second ratio as the case similarity.

[0040] Specifically, the third quantity refers to the number of case keywords that are identical in the case keyword set of the target user's case data and the case keyword set of the historical case data of historical users; the fourth quantity refers to the number of case keywords that are identical in the case keyword set of the target user's case data and the keyword set of the historical case data of the user group to which each historical user of the target DRG group belongs.

[0041] Furthermore, the case similarity can be calculated using the following formula:

[0042]

[0043]

[0044]

[0045] In the above formula, Indicates the case similarity between the current target user and the vth historical user, Represents the case keyword set of the current target user, The case keyword set representing the historical case data of the vth historical user, represents the number of keyword intersections between the current target user and the vth historical user (the third quantity), The case keyword set representing the historical case data of the user group to which the vth historical user belongs, Indicates the number of keyword intersections between the case keyword set of the case data of the current target user and the case keyword set of the historical case data of the user group to which the v-th historical user belongs (the fourth quantity). represents the number of case keywords of the historical case data of the vth historical user (the fifth quantity), The sixth number of case keywords representing the historical case data of the user group to which each historical user of the target DRG group belongs. Indicates the consistency between the case data of the current target user and the historical case data of the vth historical user; Indicates the consistency between the case data of the current target user and the historical case data of the user group to which the vth historical user belongs. is a counting function.

[0046] Furthermore, the case similarity between the current target user and the vth historical user The larger the value of , the more similar the target user is to the vth historical user.

[0047] Step S104, using the historical clinical pathways of similar users to determine missing nursing measures that are missing in the clinical pathway template.

[0048] Specifically, the missing missing nursing measures refer to: the nursing measures existing in the historical clinical pathways of similar users do not exist in the clinical pathway template. When determining the missing missing nursing measures, each nursing measure can be extracted from the historical clinical pathway, each nursing measure can be extracted from the clinical pathway template, and then the nursing measures existing in the historical clinical pathway but not in the clinical pathway template are regarded as missing nursing measures.

[0049] As an optional embodiment of the present application, using the historical clinical pathways of similar users to determine missing nursing measures that are missing in the clinical pathway template includes: serializing the historical clinical pathways of similar users to obtain multiple first sequence items, and serializing the clinical pathway template to obtain multiple second sequence items; comparing each first sequence item with each second sequence item to determine the missing first sequence item in the clinical pathway template; and determining that the nursing measures corresponding to the missing first sequence items are missing nursing measures.

[0050] Specifically, after determining the clinical pathways of similar users, the clinical pathways of similar users and the clinical pathway templates of the current DRG group are serialized to form sequence items. The sequence items of the clinical pathways of similar users are compared with the sequence items of the clinical pathway templates of the current DRG group to determine the sequence items missing from the clinical pathway templates in the current DRG group. The nursing measures represented by the sequence items are the nursing measures missing for the current target user.

[0051] Step S105, determining the weight of the missing nursing measures based on the historical clinical pathways of each historical user of the target DRG group and the nursing purpose of the target user.

[0052] Specifically, the nursing purpose refers to the nursing goal set for the target user's disease condition. Furthermore, since similar users have similar symptoms to the current target user, but their nursing goals may be different. Therefore, it is necessary to further screen the missing nursing measures based on the comparison between the nursing goals of the current target user and the nursing goals of similar users, and determine the nursing measures most needed by the current target user. Therefore, the weight of each missing nursing measure can be determined by the nursing goal of the target user and the historical clinical pathway of the historical user. The missing nursing measures with high weights are more likely to be the nursing measures most needed by the target user.

[0053] As an optional embodiment of the present application, determining the weight of missing nursing measures based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target user includes: determining the nursing similarity between the nursing objectives of each historical user in the target DRG group and the target user based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target user; determining the product of case similarity and nursing similarity as the weight of the missing nursing measures for similar users.

[0054] Specifically, the nursing similarity refers to the degree of similarity between the nursing objectives in the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target user. Specifically, the nursing objectives in the historical clinical pathways of each historical user of the target DRG group can be compared with the nursing objectives of the target user to determine the nursing similarity.

[0055] As an optional embodiment of the present application, based on the historical clinical pathways of each historical user of the target DRG group and the nursing objectives of the target user, determining the nursing similarity between the nursing objectives of each historical user in the target DRG group and the target user includes: determining a keyword set of the target user's nursing objectives, and a keyword set of the nursing objectives in the historical clinical pathways of the historical users; calculating the seventh number of keyword intersections of the keyword set of the target user's nursing objectives and the keyword set of the nursing objectives in the historical clinical pathways of the historical users; determining the eighth number of keywords for the nursing objectives in the historical clinical pathways of the historical users; and determining the third ratio of the seventh number to the eighth number as the nursing similarity.

[0056] Specifically, the keywords of the nursing objectives of the target user and the keywords of the nursing objectives in the historical clinical pathways of the historical users can use NLP technology to perform word segmentation, part-of-speech tagging and entity recognition on the nursing objectives, so as to accurately extract the professional terms in the nursing objectives, and determine the extracted professional terms as the keywords of the nursing objectives of the current target user and the historical users. The keywords of the nursing objectives of the target user and the historical users respectively form the keyword set of the nursing objectives of the target user and the keyword set of the nursing objectives in the historical clinical pathways.

[0057] Furthermore, the nursing similarity can be calculated using the following formula:

[0058]

[0059]

[0060] In the above formula, represents the nursing similarity between the current target user and the vth historical user, A set of keywords representing the care purpose of the current target user, represents the nursing purpose keyword set of the vth historical user, represents the number of intersections between the current target user and the nursing purpose keywords of the vth historical user (the seventh quantity), The number of keywords representing the nursing purpose of the vth historical user (the eighth number), It represents the intersection of the nursing purpose of the current template user and the nursing purpose of the v-th historical user, and it represents the nursing similarity between the nursing purpose of the current target user and the nursing purpose of the v-th historical user.

[0061] Furthermore, the nursing similarity between the current target user and the nursing purpose of the vth historical user is The larger it is, the closer the care purpose of the current target user is to the care purpose of the vth historical user.

[0062] Furthermore, the case similarity between the current target user and the vth historical user is collected , determine the weights of missing care measures provided by different historical users, which are calculated using the following formula:

[0063]

[0064] In the above formula, represents the weight of the missing care measure provided by the vth historical user, Indicates the case similarity between the current target user and the vth historical user, Represents the nursing similarity between the nursing purpose of the current target user and the vth historical user.

[0065] Step S106 , determining the target missing nursing measures for the target user by using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway.

[0066] Specifically, the weights of each missing nursing measure are determined by case similarity and nursing purpose nursing similarity, so as to further screen the missing nursing measures and determine the nursing measures most needed by the current target user. If the current missing nursing measures appear frequently in the nursing measures of the current similar users, it can also be said that the current missing nursing measures are more important for the current patient's care. Therefore, the final missing nursing measures for the target user can be determined based on the number of similar users and the number of similar users corresponding to the missing nursing measures in the clinical pathway template.

[0067] As an optional embodiment of the present application, determining the target missing nursing measures for the target user using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway includes: determining the importance of the missing nursing measures for the similar users using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway, the importance representing the importance of the missing nursing measures to the care of the target user; determining the target missing nursing measures for the target user based on the importance.

[0068] Specifically, the importance of each missing nursing measure is determined based on the number of similar users and the number of similar users corresponding to the missing nursing measures in the clinical pathway template. If the importance is high, it means that the missing nursing measure is relatively important to the nursing process of the target user. It can be used as the final missing nursing measure of the target user.

[0069] As an optional embodiment of the present application, the importance of the missing nursing measures of similar users is determined by using weights, a first number of similar users, and a second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway, including: calculating a fourth ratio of the second number to the first number, and superimposing the weights of the missing nursing measures of each similar user to obtain a superimposed weight; calculating the product of the fourth ratio and the superimposed weight; and determining the normalized product as the importance.

[0070] Specifically, the importance can be calculated using the following formula:

[0071]

[0072] In the above formula, represents the importance of the u-th missing nursing measure, represents the number of similar users with the u-th missing nursing measure in their historical clinical pathways (the second quantity), Indicates the number of users similar to the current user (the first number). represents the importance of the u-th missing care measure among the similar users of the current target user. represents the weight of similar users who have the missing nursing measure in the i-th historical clinical pathway for the u-th missing nursing measure; represents the overall importance (superimposed weight) of the u-th missing care measure among similar users. The function is a normalization function, and the normalized data is [0, 1]. The importance of the u-th missing nursing measure The larger the value of , the more important the u-th missing care measure is to the target user.

[0073] As an optional embodiment of the present application, determining the target missing care measures of the target user according to the importance includes: determining the missing care measures with an importance greater than a threshold as the target missing care measures.

[0074] Specifically, the threshold value can be determined according to the actual scenario, such as 0.5, which is not limited in the present embodiment. If the importance is greater than the threshold value, the missing care measure is determined to be the final missing care measure of the current target user.

[0075] Step S107, adding the target missing nursing measures to the clinical pathway template to obtain the final clinical pathway of the target user.

[0076] Specifically, after determining the target missing nursing measures of the current target user, add them to the clinical pathway template of the current DRG group, and determine that the clinical pathway template after adding the missing nursing measures is the final clinical pathway of the current target user. The final clinical pathway is the clinical pathway planned by the target user.

[0077] The embodiment of the present application determines a standardized clinical pathway template for each user according to the historical clinical pathways of the historical users of the DRG group to which the user belongs, and then determines the missing nursing measures of the clinical pathway template of the DRG group to which the current user belongs according to the historical case data and historical clinical pathways of the historical users, and then determines the nursing measures that the user ultimately lacks according to the historical clinical pathways of the historical users and the nursing objectives of the target user, and adds the missing nursing measures to the clinical pathway template to obtain the user's final clinical pathway. Therefore, the present application does not need to determine the personalized clinical pathway for each patient in turn according to factors such as the patient's characteristics, but only needs to add the missing nursing measures of the user to the clinical pathway template, which saves a lot of manpower and time and improves the planning efficiency of the clinical pathway.

[0078] Embodiment 2:

[0079] Corresponding to the clinical pathway automatic planning method provided in the above embodiment, based on the same technical concept, the embodiment of the present application also provides a clinical pathway automatic planning device, Figure 2 A schematic diagram of the module composition of a clinical pathway automatic planning device provided in an embodiment of the present application, wherein the clinical pathway automatic planning device is used to execute Figure 1 The clinical pathway automatic planning method described in Figure 2 As shown, the clinical pathway automatic planning device 200 includes: a grouping module 201, which is used to perform DRG grouping on the target user according to the case data of the target user, obtain the target DRG group to which the target user belongs, and obtain the nursing purpose of the target user; a determination module 202, which is used to determine the clinical pathway template of the target DRG group according to the historical clinical pathways of all historical users of the target DRG group; the determination module 202 is also used to determine similar users similar to the target user from each historical user according to the historical case data of each historical user of the target DRG group and the case data of the target user; the determination module 202 is also used to determine the missing nursing measures missing in the clinical pathway template using the historical clinical pathways of the similar users; the determination module 202 is also used to determine the weight of the missing nursing measures based on the historical clinical pathways of each historical user of the target DRG group and the nursing purpose of the target user; the determination module 202 is also used to determine the target missing nursing measures of the target user using the weight, the first number of similar users and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway; the adding module 203 is used to add the target missing nursing measures to the clinical pathway template to obtain the final clinical pathway of the target user.

[0080] The embodiment of the present application determines a standardized clinical pathway template for each user according to the historical clinical pathways of the historical users of the DRG group to which the user belongs, and then determines the missing nursing measures of the clinical pathway template of the DRG group to which the current user belongs according to the historical case data and historical clinical pathways of the historical users, and then determines the nursing measures that the user ultimately lacks according to the historical clinical pathways of the historical users and the nursing objectives of the target user, and adds the missing nursing measures to the clinical pathway template to obtain the user's final clinical pathway. Therefore, the present application does not need to determine the personalized clinical pathway for each patient in turn according to factors such as the patient's characteristics, but only needs to add the missing nursing measures of the user to the clinical pathway template, which saves a lot of manpower and time and improves the planning efficiency of the clinical pathway.

[0081] It should be noted that the automatic clinical pathway planning device provided in the embodiment of the present application and the automatic clinical pathway planning method provided in the embodiment of the present application are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned automatic clinical pathway planning method, and has the same or similar beneficial effects, and the repetitive parts will not be repeated.

[0082] Embodiment three:

[0083] Corresponding to the clinical pathway automatic planning method provided in the above embodiment, based on the same technical concept, the embodiment of the present application also provides a clinical pathway automatic planning system, which is used to execute the above clinical pathway automatic planning method. Figure 3 A schematic diagram of a clinical pathway automatic planning system for implementing various embodiments of the present application is shown in FIG. Figure 3 The clinical pathway automatic planning system may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and memory 302, wherein the memory 302 is used to store computer programs that can be run on the processor, and the processor is used to execute the program stored in the memory to achieve the above Figure 1 The various steps in the method embodiment. The memory 302 may be a temporary storage or a permanent storage. The application stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the clinical pathway automatic planning system.

[0084] Furthermore, the processor 301 can be configured to communicate with the memory 302, and execute a series of computer executable instructions in the memory 302 on the clinical pathway automatic planning system. The clinical pathway automatic planning system can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, and one or more keyboards 306.

[0085] Specifically in this embodiment, the clinical pathway automatic planning system includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to achieve the above Figure 1 The various steps in the method embodiment are similar to those in the method embodiment, and have the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present application will not be described again here.

[0086] It should be noted that the clinical pathway automatic planning system provided in the embodiment of the present application and the clinical pathway automatic planning method provided in the embodiment of the present application are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned clinical pathway automatic planning method, and has the same or similar beneficial effects, and the repetitive parts will not be repeated.

[0087] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for automatic clinical pathway planning, characterized in that: The clinical pathway automatic planning method comprises: DRG grouping is performed on the target user according to the case data of the target user, the target DRG group to which the target user belongs is obtained, and the nursing purpose of the target user is obtained; Determine a clinical pathway template for the target DRG group based on the historical clinical pathways of all historical users of the target DRG group; Determine similar users who are similar to the target user from among the historical users according to the historical case data of each of the historical users of the target DRG group and the case data of the target user; using the historical clinical pathways of the similar users to determine missing care measures that are missing from the clinical pathway template; Determining the weight of the missing nursing measures based on the historical clinical pathways of each of the historical users of the target DRG group and the nursing purpose of the target user; Determine a target missing nursing measure for the target user by using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures existing in the historical clinical pathway; Adding the target missing nursing measures to the clinical pathway template to obtain the final clinical pathway for the target user; Determining similar users similar to the target user from the historical users according to the historical case data of the historical users of the target DRG group and the case data of the target user comprises: Classify each of the historical users according to the historical case data of each of the historical users of the target DRG group to obtain multiple user groups; Determine the case similarity between each of the historical users in the target DRG group and the target user based on the historical case data of the user group to which each of the historical users of the target DRG group belongs, the historical case data of each of the historical users, and the case data of the target user; Determine similar users who are similar to the target user from each of the historical users in the target DRG group based on the case similarity; The determining the weight of the missing nursing measures based on the historical clinical pathways of each of the historical users of the target DRG group and the nursing purpose of the target user includes: Determine the nursing similarity between the nursing purpose of each historical user in the target DRG group and the target user based on the historical clinical pathway of each historical user in the target DRG group and the nursing purpose of the target user; the historical clinical pathway includes the nursing purpose; Determine the product of the case similarity and the nursing similarity as the weight of the missing nursing measures of the similar user; Determining the target missing nursing measures for the target user by using the weight, the first number of similar users, and the second number of similar users corresponding to the missing nursing measures in the historical clinical pathway includes: Determine the importance of the missing nursing measures of the similar users by using the weight, the first number of the similar users, and the second number of the similar users corresponding to the missing nursing measures in the historical clinical pathway, wherein the importance represents the importance of the missing nursing measures to the nursing of the target user; Determining a target missing care measure for the target user according to the importance level; Determining the importance of the missing nursing measures of the similar users by using the weight, the first number of the similar users, and the second number of similar users corresponding to the missing nursing measures in the historical clinical pathway includes: calculating a fourth ratio of the second number to the first number, and superimposing weights of missing nursing measures of each of the similar users to obtain a superimposed weight; Calculating a product of the fourth ratio and the superposition weight; The normalized product is determined as the importance level.

2. The method for automatic clinical pathway planning according to claim 1, characterized in that: Determining the case similarity between each of the historical users in the target DRG group and the target user based on the historical case data of the user group to which each of the historical users in the target DRG group belongs, the historical case data of each of the historical users, and the case data of the target user comprises: Determine a third number of keyword intersections of the case keyword set of the case data of the target user and the case keyword set of the historical case data of the historical user; Determine a fourth number of keyword intersections of the case keyword set of the case data of the target user and the case keyword set of the historical case data of the user group to which each of the historical users of the target DRG group belongs; Determine a fifth number of case keywords of the historical case data of the historical users, and a sixth number of case keywords of the historical case data of the user group to which each of the historical users of the target DRG group belongs; calculating a first ratio of the third quantity to the fifth quantity, and a second ratio of the fourth quantity to the sixth quantity; The superposition value of the first ratio and the second ratio is determined as the case similarity.

3. The method for automatic clinical pathway planning according to claim 1, characterized in that: Determining the clinical pathway template of the target DRG group according to the historical clinical pathways of all historical users of the target DRG group includes: Serializing the historical clinical pathways of the historical user to obtain multiple sequence items; Using each of the sequence items to construct a frequent pattern tree, so as to determine sequence items that appear repeatedly in historical clinical pathways of multiple historical users through the frequent pattern tree, and obtain a frequent item set; Determine a clinical pathway pattern that satisfies the nursing purpose of the target user from the sequence items of the frequent item set, wherein the clinical pathway pattern represents the nursing process that frequently appears in the target DRG group; The frequent item set with the maximum number of item sets and the highest frequency that satisfies the clinical pathway pattern is determined, and the pathway formed is the clinical pathway template.

4. The method for automatic clinical pathway planning according to claim 1, characterized in that: The method of using the historical clinical pathway of the similar user to determine the missing nursing measures that are missing in the clinical pathway template includes: Serializing the historical clinical pathways of the similar users to obtain a plurality of first sequence items, and serializing the clinical pathway template to obtain a plurality of second sequence items; Comparing each of the first sequence items with each of the second sequence items to determine the first sequence items that are missing in the clinical pathway template; Determine that the nursing measure corresponding to the missing first sequence item is the missing nursing measure.

5. The method for automatic clinical pathway planning according to claim 1, characterized in that: The determining of the nursing similarity between the nursing purpose of each historical user in the target DRG group and the target user based on the historical clinical pathway of each historical user in the target DRG group and the nursing purpose of the target user comprises: Determine a keyword set of the nursing purpose of the target user and a keyword set of the nursing purpose in the historical clinical pathway of the historical user; Calculating a seventh number of keyword intersections of the keyword set of the nursing purpose of the target user and the keyword set of the nursing purpose in the historical clinical pathway of the historical user; determining an eighth number of keywords of care intent in a historical clinical pathway of the historical user; A third ratio of the seventh number to the eighth number is determined as the care similarity.

6. The method for automatic clinical pathway planning according to claim 1, characterized in that: Determining the target missing care measures for the target user according to the importance level includes: The missing nursing measures with an importance greater than a threshold are determined as the target missing nursing measures.

Images