Clinical pathway construction method, device, equipment and storage medium

Abstract

The present invention relates to the field of digital medicine, and discloses a method, device, equipment and storage medium for constructing a clinical pathway. The method includes: receiving a data acquisition request, and according to the request, obtaining the diagnosis and treatment process corresponding to the target disease; constructing a diagnosis and treatment node sequence according to the diagnosis and treatment process of the target disease; obtaining historical electronic medical records of multiple target patients, and determining the target diagnosis and treatment events of each standard diagnosis and treatment node according to the historical electronic medical records; analyzing each target diagnosis and treatment event according to preset analysis rules to obtain the diagnosis and treatment time plan for each target medical event; constructing a clinical pathway for the target disease according to the diagnosis and treatment node sequence, the target diagnosis and treatment event of each standard diagnosis and treatment node, and the diagnosis and treatment time plan of each target medical event. The present invention analyzes the diagnosis and treatment time plan of each target diagnosis and treatment event based on the plan review technology, and adds the diagnosis and treatment time plan to the clinical pathway, so as to obtain a more accurate clinical pathway.

Description

Technical Field

[0001] The present invention relates to the field of digital medicine, and in particular to a method, device, equipment and storage medium for constructing a clinical pathway. Background Art

[0002] Clinical pathway refers to the establishment of a set of standardized treatment models and treatment procedures for a certain disease. It is a comprehensive model of clinical treatment, which promotes treatment organization and disease management methods guided by evidence-based medicine and guidelines. It ultimately plays a role in standardizing medical behavior, reducing variation, reducing costs, and improving quality. After adopting clinical pathways, it can avoid the traditional pathway that causes different treatment plans for the same disease in different regions, different hospitals, different treatment groups, or different individual physicians, avoiding its arbitrariness. At the same time, the planned time for each diagnosis and treatment step in the clinical pathway is often evaluated, which is convenient for hospital managers to arrange medical resources rationally.

[0003] The existing clinical pathway construction method has low accuracy because the planned time for each diagnosis and treatment step in the clinical pathway is estimated by medical staff based on experience, and the estimated results are inaccurate, which affects the accuracy of the clinical pathway. When the estimated results are higher than the actual results, the hospital will suffer higher treatment costs and a large number of medical resources will be idle. When the estimated results are lower than the actual results, the hospital's medical service quality will be low and medical resources will be in short supply. Summary of the invention

[0004] The main purpose of the present invention is to solve the problem of low accuracy of existing clinical pathway construction methods.

[0005] The first aspect of the present invention provides a method for constructing a clinical pathway, comprising:

[0006] Receiving a data acquisition request sent by a terminal, and acquiring a diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0007] According to the diagnosis and treatment process corresponding to the target disease, a diagnosis and treatment node sequence corresponding to the target disease is constructed, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0008] Obtaining historical electronic medical records of multiple target patients, and determining the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patients are patients who suffer from the target disease and have been cured;

[0009] According to the preset analysis rules, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node are analyzed to obtain the diagnosis and treatment time plan for each target medical event;

[0010] A clinical pathway for the target disease is constructed based on the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0011] Optionally, in a first implementation of the first aspect of the present invention, the receiving terminal sends a data acquisition request, and acquiring the diagnosis and treatment process corresponding to the target disease according to the data acquisition request includes:

[0012] Receiving a data acquisition request sent by a terminal, wherein the data acquisition request includes a database identification parameter and a query condition parameter;

[0013] Calling the target database according to the database identification parameter;

[0014] According to the query condition parameters, the diagnosis and treatment process corresponding to the target disease is queried from the target database.

[0015] Optionally, in a second implementation of the first aspect of the present invention, the acquiring of historical electronic medical records of multiple target patients and determining, based on the historical electronic medical records, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node includes:

[0016] According to the target disease, obtaining historical electronic medical records of multiple target patients from a preset medical database, wherein the target patients are patients who suffer from the target disease and have been cured;

[0017] Based on natural language processing technology, events are extracted from the historical electronic medical records of each target patient to obtain multiple initial diagnosis and treatment events corresponding to each target patient;

[0018] Sequentially matching multiple initial diagnosis and treatment events corresponding to each target patient with each standard diagnosis and treatment node of the target disease to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, wherein the diagnosis and treatment event set includes at least one initial diagnosis and treatment event;

[0019] From the diagnosis and treatment event set corresponding to each diagnosis and treatment node, the target diagnosis and treatment event corresponding to each diagnosis and treatment node is screened out, wherein the target diagnosis and treatment event is the initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set.

[0020] Optionally, in a third implementation of the first aspect of the present invention, the event extraction of each target patient's historical electronic medical record based on natural language processing technology to obtain multiple initial diagnosis and treatment events corresponding to each target patient includes:

[0021] Extract text from the historical electronic medical records of each target patient in turn to obtain multiple target texts;

[0022] Based on the preset word segmentation tool, each target text is segmented to obtain the word segmentation result of each target text;

[0023] According to the word segmentation results of each target text, the event extraction template corresponding to each target text is matched in the preset event extraction template set;

[0024] Based on the word segmentation results of each target text and the event extraction template corresponding to each target text, multiple event attributes corresponding to each target text are generated, and multiple initial diagnosis and treatment events corresponding to each target patient are obtained.

[0025] Optionally, in a fourth implementation of the first aspect of the present invention, analyzing the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node according to a preset analysis rule to obtain a diagnosis and treatment time plan for each target medical event includes:

[0026] Obtaining event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter;

[0027] Based on a preset time calculation formula, the optimistic time parameter, the pessimistic time parameter and the most likely time parameter are calculated to obtain an average duration of each target diagnosis and treatment event;

[0028] Construct a PERT network diagram based on each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event;

[0029] Determine the critical path in the PERT network diagram, and calculate the slack time of each target diagnosis and treatment event based on the critical path;

[0030] Based on the average duration of each target diagnosis and treatment event and the slack time of each target diagnosis and treatment event, a diagnosis and treatment time plan for each target diagnosis and treatment event is generated.

[0031] Optionally, in a fifth implementation of the first aspect of the present invention, after calculating the optimistic time, the pessimistic time, and the most likely time based on a preset time calculation formula to obtain an average duration corresponding to each target diagnosis and treatment event, and before constructing a PERT network diagram based on each target diagnosis and treatment event and the average duration corresponding to each target diagnosis and treatment event, it also includes:

[0032] Based on the preset variance calculation formula, the variance of the average duration corresponding to each target diagnosis and treatment event is calculated to obtain the activity duration variance of each target medical event;

[0033] The activity duration variance of each target medical event is compared with a preset threshold, and the average duration corresponding to the target medical events whose activity duration variance is greater than the preset threshold is updated.

[0034] Optionally, in a sixth implementation of the first aspect of the present invention, constructing a clinical pathway for the target disease according to the sequence of diagnosis and treatment nodes, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target diagnosis and treatment event includes:

[0035] Based on the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, a directed edge corresponding to each target diagnosis and treatment event is constructed;

[0036] Connecting the directed edges corresponding to each target diagnosis and treatment event in sequence according to the arrangement order of the standard diagnosis and treatment nodes in the diagnosis and treatment node sequence;

[0037] Based on the diagnosis and treatment time plan for each target diagnosis and treatment event, a plan label is added to the directed edge corresponding to each target diagnosis and treatment event to obtain the clinical pathway of the target disease.

[0038] A second aspect of the present invention provides a clinical pathway construction device, comprising:

[0039] A diagnosis and treatment process acquisition module, used to receive a data acquisition request sent by a terminal, and acquire the diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0040] A node sequence construction module, used to construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0041] A diagnosis and treatment event extraction module is used to obtain historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patient is a patient who suffers from the target disease and has been cured;

[0042] The plan review and analysis module is used to analyze the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node according to the preset analysis rules, and obtain the diagnosis and treatment time plan for each target medical event;

[0043] The clinical pathway construction module is used to construct a clinical pathway for the target disease based on the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0044] Optionally, in a first implementation of the second aspect of the present invention, the diagnosis and treatment process acquisition module specifically includes:

[0045] A receiving unit, configured to receive a data acquisition request sent by a terminal, wherein the data acquisition request includes a database identification parameter and a query condition parameter;

[0046] A calling unit, used for calling a target database according to the database identification parameter;

[0047] A query unit is used to query the diagnosis and treatment process corresponding to the target disease from the target database according to the query condition parameters.

[0048] Optionally, in a second implementation of the second aspect of the present invention, the diagnosis and treatment event extraction module specifically includes:

[0049] A medical record acquisition unit, used to acquire historical electronic medical records of a plurality of target patients from a preset medical database according to the target disease, wherein the target patients are patients who suffer from the target disease and have been cured;

[0050] An event extraction unit is used to extract events from the historical electronic medical records of each target patient based on natural language processing technology to obtain multiple initial diagnosis and treatment events corresponding to each target patient;

[0051] A node matching unit, used to sequentially match multiple initial diagnosis and treatment events corresponding to each target patient with each standard diagnosis and treatment node of the target disease to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, wherein the diagnosis and treatment event set includes at least one initial diagnosis and treatment event;

[0052] The target screening unit is used to screen out the target diagnosis and treatment event corresponding to each diagnosis and treatment node from the diagnosis and treatment event set corresponding to each diagnosis and treatment node, wherein the target diagnosis and treatment event is the initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set.

[0053] Optionally, in a third implementation of the second aspect of the present invention, the event extraction unit is specifically used to:

[0054] Extract text from the historical electronic medical records of each target patient in turn to obtain multiple target texts;

[0055] Based on the preset word segmentation tool, each target text is segmented to obtain the word segmentation result of each target text;

[0056] According to the word segmentation results of each target text, the event extraction template corresponding to each target text is matched in the preset event extraction template set;

[0057] Based on the word segmentation results of each target text and the event extraction template corresponding to each target text, multiple event attributes corresponding to each target text are generated, and multiple initial diagnosis and treatment events corresponding to each target patient are obtained.

[0058] Optionally, in a fourth implementation of the second aspect of the present invention, the plan review and analysis module specifically includes:

[0059] A time parameter acquisition unit, which acquires event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter;

[0060] A first calculation unit, configured to calculate the optimistic time parameter, the pessimistic time parameter and the most likely time parameter based on a preset time calculation formula, to obtain an average duration of each target diagnosis and treatment event;

[0061] A network diagram construction unit, used to construct a PERT network diagram according to each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event;

[0062] A second calculation unit is used to determine the key path in the PERT network diagram, and calculate the relaxation time of each target diagnosis and treatment event based on the key path;

[0063] The plan generating unit is used to generate a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the relaxation time of each target diagnosis and treatment event.

[0064] Optionally, in a fifth implementation of the second aspect of the present invention, the plan review and analysis module specifically includes:

[0065] A time parameter acquisition unit, which acquires event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter;

[0066] A first calculation unit, configured to calculate the optimistic time parameter, the pessimistic time parameter and the most likely time parameter based on a preset time calculation formula, to obtain an average duration of each target diagnosis and treatment event;

[0067] A variance calculation unit, used to perform variance calculation on the average duration corresponding to each target diagnosis and treatment event based on a preset variance calculation formula, to obtain the activity duration variance of each target medical event;

[0068] A parameter updating unit, used to compare the activity duration variance of each target medical event with a preset threshold, and to update the average duration corresponding to the target medical events whose activity duration variance is greater than the preset threshold;

[0069] A network diagram construction unit, used to construct a PERT network diagram according to each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event;

[0070] A second calculation unit is used to determine the key path in the PERT network diagram, and calculate the relaxation time of each target diagnosis and treatment event based on the key path;

[0071] The plan generating unit is used to generate a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the relaxation time of each target diagnosis and treatment event.

[0072] Optionally, in a sixth implementation of the second aspect of the present invention, the clinical pathway construction module specifically includes:

[0073] A directed edge construction unit, used to construct a directed edge corresponding to each target diagnosis and treatment event based on the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node;

[0074] A connection unit, used to sequentially connect the directed edges corresponding to each target diagnosis and treatment event according to the arrangement order of the standard diagnosis and treatment nodes in the diagnosis and treatment node sequence;

[0075] The label adding unit is used to add a plan label to the directed edge corresponding to each target diagnosis and treatment event based on the diagnosis and treatment time plan of each target diagnosis and treatment event, so as to obtain the clinical pathway of the target disease.

[0076] A third aspect of the present invention provides a clinical pathway construction device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the clinical pathway construction device executes the above-mentioned clinical pathway construction method.

[0077] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for constructing a clinical pathway.

[0078] In the technical solution provided by the present invention, firstly, the diagnosis and treatment process of the target disease is obtained, and a diagnosis and treatment node sequence containing multiple standard diagnosis and treatment nodes is generated according to the diagnosis and treatment process. Secondly, multiple diagnosis and treatment events of each patient are extracted from the historical medical records of patients suffering from the target disease and cured, and matched with each standard diagnosis and treatment node to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment event with the most occurrences in each standard diagnosis and treatment node is used as the target diagnosis and treatment event of the node, and then each target diagnosis and treatment event is analyzed based on the plan review technique, so as to obtain the diagnosis and treatment time plan of each target diagnosis and treatment event, and finally, the clinical pathway of the target disease is constructed based on the target diagnosis and treatment event and the diagnosis and treatment time plan of each target diagnosis and treatment event. The present invention is based on the plan review technique in project management, so as to calculate the diagnosis and treatment time plan of each target diagnosis and treatment event, and mark the diagnosis and treatment time plan when constructing the clinical pathway, so as to obtain a more accurate clinical pathway. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 Schematic diagram of a first embodiment of a method for constructing a clinical pathway in an embodiment of the present invention;

[0080] Figure 2 Schematic diagram of a second embodiment of the method for constructing a clinical pathway in an embodiment of the present invention;

[0081] Figure 3 Schematic diagram of a third embodiment of the method for constructing a clinical pathway in an embodiment of the present invention;

[0082] Figure 4 Schematic diagram of a fourth embodiment of the method for constructing a clinical pathway in an embodiment of the present invention;

[0083] Figure 5 A schematic diagram of an embodiment of a device for constructing a clinical pathway in an embodiment of the present invention;

[0084] Figure 6 It is a schematic diagram of another embodiment of the device for constructing a clinical pathway in an embodiment of the present invention;

[0085] Figure 7 Schematic diagram of an embodiment of a clinical pathway construction device in an embodiment of the present invention. DETAILED DESCRIPTION

[0086] The embodiments of the present invention provide a method, device, equipment and storage medium for constructing a clinical pathway, which has higher monitoring efficiency.

[0087] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0088] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the method for constructing a clinical pathway in an embodiment of the present invention includes:

[0089] 101. Receive a data acquisition request sent by a terminal, and acquire a diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0090] It is understandable that in order to standardize medical services and reduce medical costs, domestic hospitals have established corresponding diagnosis and treatment process standards for various diseases. The server obtains the diagnosis and treatment process of the corresponding disease from the hospital's medical database based on the data acquisition request. The diagnosis and treatment process includes the entire process record of the patient from registration to discharge. For example, if the disease is knee bone damage and a knee replacement surgery is required, the process includes process 1 "Complete the hospitalization medical record" and process 2 "Complete the nursing assessment and record", etc.

[0091] 102. According to the diagnosis and treatment process corresponding to the target disease, a diagnosis and treatment node sequence corresponding to the target disease is constructed, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0092] It can be understood that each standard diagnosis and treatment node is determined by the diagnosis and treatment process, and different disease types correspond to different standard diagnosis and treatment nodes. The standard diagnosis and treatment nodes include but are not limited to admission day, pre-operative day, surgical day, post-operative day, discharge day, and hospitalization day.

[0093] 103. Obtain historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patients are patients who suffer from the target disease and have been cured;

[0094] It is understandable that the server extracts events from the historical electronic medical records of multiple target patients, for example, based on pattern matching or deep learning, which is not limited in this embodiment. The patients in the historical electronic medical records are patients who have suffered from the target disease and have been cured, and their medical records can reflect the effectiveness of their diagnosis and treatment plans to a certain extent, thereby extracting target diagnosis and treatment events that are more closely related to the target disease and unique.

[0095] 104. According to the preset analysis rules, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node are analyzed to obtain the diagnosis and treatment time plan for each target medical event;

[0096] It can be understood that this analysis rule is a rule based on the Program Evaluation and Review Technique (PERT), which obtains the time parameters defined for each target diagnosis and treatment event from multiple dimensions, and calculates the time parameters of multiple dimensions under each target diagnosis and treatment event through a preset calculation formula, thereby converting multiple uncertain time parameters into a deterministic time parameter, and then constructing a corresponding PERT network diagram for analysis, and obtaining the corresponding diagnosis and treatment time plan, thereby coordinating the time of each stage and step of the project, reasonably arranging manpower, material resources, time, and funds, and accelerating the completion of the plan.

[0097] 105. Construct a clinical pathway for the target disease based on the sequence of diagnosis and treatment nodes, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0098] It can be understood that the clinical pathway refers to the establishment of a set of standardized treatment models and procedures for a certain disease, thereby standardizing medical behavior, improving medical quality and reducing medical costs.

[0099] The adoption of clinical pathways can avoid the traditional pathway that results in different treatment plans for the same disease in different regions, different hospitals, different treatment groups or different individual physicians, avoid its arbitrariness, and improve the accuracy, prognosis, and other evaluability.

[0100] Specifically, the server uses the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node as the path, connects each path in sequence according to the arrangement order of the nodes in the standard diagnosis and treatment node sequence, and adds a data label to each path. The content of the data label is the diagnosis and treatment time plan corresponding to each path, thereby obtaining the clinical pathway of the target disease.

[0101] In this embodiment, the present invention is based on the plan review technology in project management to calculate the diagnosis and treatment time plan for each target diagnosis and treatment event, and mark the diagnosis and treatment time plan when constructing the clinical pathway, so as to obtain a more accurate clinical pathway.

[0102] See also Figure 2 The second embodiment of the method for constructing a clinical pathway in the embodiment of the present invention includes:

[0103] 201. Receive a data acquisition request sent by a terminal, wherein the data acquisition request includes a database identification parameter and a query condition parameter;

[0104] It can be understood that the database identification parameters include the IP address of the database server, the database name, the user name and password. The query condition parameters are used to perform conditional screening on the data, which can be specifically expressed as an attribute value or an attribute range. For example, the query condition parameter is "disease=1542", where the attribute disease indicates the type of disease, and 1542 is the number of a disease type.

[0105] 202. Call the target database according to the database identification parameter;

[0106] It can be understood that the server first queries the corresponding server according to the IP address of the database server to open the database service, then finds the corresponding database according to the database name, and finally verifies the access authority to the database according to the user name and password.

[0107] 203. According to the query condition parameters, query the diagnosis and treatment process corresponding to the target disease from the target database;

[0108] It is understandable that the server generates a corresponding database query statement based on the query condition parameters, so as to quickly index the data records that meet the conditions in the diagnosis and treatment process table. For example, if the query condition parameter is "disease = 1542", the table name of the diagnosis and treatment process table is "treatment_process", the corresponding query statement SQL = select * from treatment_process where disease = 1542;

[0109] 204. Construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0110] 205. Obtain historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patients are patients who suffer from the target disease and have been cured;

[0111] 206. According to the preset analysis rules, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node are analyzed to obtain the diagnosis and treatment time plan for each target medical event;

[0112] 207. Construct a clinical pathway for the target disease based on the sequence of diagnosis and treatment nodes, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0113] Among them, steps 204-207 are similar to the execution steps of the above steps 102-105, and will not be repeated here.

[0114] In this embodiment, the process of obtaining the diagnosis and treatment process is described in detail, and the diagnosis and treatment process corresponding to the target disease is quickly located through database identification parameters and query condition parameters, thereby improving data acquisition efficiency.

[0115] See also Figure 3 A third embodiment of the method for constructing a clinical pathway in an embodiment of the present invention includes:

[0116] 301. Receive a data acquisition request sent by a terminal, and acquire a diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0117] 302. Construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0118] Among them, steps 301-302 are similar to the execution steps of the above steps 101-102, and the details are not repeated here.

[0119] 303. According to the target disease, obtain historical electronic medical records of multiple target patients from a preset medical database, wherein the target patients are patients who suffer from the target disease and have been cured;

[0120] It is understandable that the medical database archives and stores each medical record data of each patient, and the server searches the medical database for the historical electronic medical records of patients with the target disease according to the disease type number of the target disease.

[0121] 304. Based on natural language processing technology, extract events from the historical electronic medical records of each target patient to obtain multiple initial diagnosis and treatment events corresponding to each target patient;

[0122] It can be understood that the present embodiment adopts natural language processing technology (NLP), for example, based on the statistical model pipeline extraction algorithm (pipeline), to extract events from the historical electronic medical records of each target patient, thereby converting the event extraction in the historical medical records into a multi-stage classification problem, including event trigger word classification (used to determine whether a word is an event trigger word and the event category), element classification (whether a phrase is an event element), element role classification (determining the role category of the element), attribute classification (determining event attributes), and reportability classification (determining whether there are event instances worthy of reporting), thereby obtaining multiple initial diagnosis and treatment events for each target patient. The initial diagnosis and treatment events include each patient's treatment events, medical orders, and nursing activities, such as admission procedures, determination of surgery date, signing of surgery consent forms, etc.

[0123] Specifically, the server extracts text from the historical electronic medical records of each target patient in turn to obtain multiple target texts. Next, based on a preset word segmentation tool, each target text is segmented to obtain the word segmentation result of each target text. Then, based on the word segmentation result of each target text, the target event extraction template corresponding to each target text is matched in the preset event extraction template set. Finally, based on the word segmentation result of each target text and the target event extraction template corresponding to each target text, the event attributes of each target text are generated.

[0124] It can be understood that text extraction is to recognize the text of the historical electronic medical record. Optical Character Recognition (OCR) technology can be used to directly extract text from the historical electronic medical record of each target patient to obtain the target text corresponding to each historical electronic medical record.

[0125] Preset word segmentation tools such as jieba and other Chinese word segmentation tools. Preferably, before segmenting the target text, the server performs named entity recognition (NER) on the target text based on an entity recognition algorithm (for example, a conditional random field algorithm, a recurrent neural network algorithm, etc.), thereby extracting structured entity words such as disease names and drug names from the unstructured text, and then dividing the text into a reasonable vocabulary sequence while ensuring that the entity words are not segmented.

[0126] Each event extraction template in the event extraction template set can be represented as an ordered sequence consisting of at least one template element. Template elements can be divided into three types: "lexical matcher", "entity matcher" and "wildcard". Lexical matchers can be used to indicate event key information, and entity matchers can be used to indicate event key entities. Each event extraction template can include one or more of these three types of template elements.

[0127] The target event extraction template includes an attribute extraction rule for indicating the method of extracting event attribute data from the word segmentation result. The attribute extractor can be specifically represented as a mapping relationship between at least one attribute name and at least one element index. Each element index indicates a template element in the target event extraction template. This mapping relationship can be used to indicate the attribute content corresponding to each attribute name and the matching vocabulary indicated by the element index mapped to the attribute name.

[0128] 305. Matching multiple initial diagnosis and treatment events corresponding to each target patient with each standard diagnosis and treatment node of the target disease in sequence to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, wherein the diagnosis and treatment event set includes at least one initial diagnosis and treatment event;

[0129] It is understandable that each standard diagnosis and treatment node corresponds to multiple initial diagnosis and treatment events. For example, if the standard diagnosis and treatment node is the day before surgery, the corresponding initial diagnosis and treatment events are "Patient A—Preoperative—Routine Care", "Patient A—Preoperative—Psychological Care", "Patient B—Preoperative—Skin Preparation, Bathing, Changing Clothes, Enema", "Patient B—Preoperative—Psychological Care", etc.

[0130] 306. Filter out a target diagnosis and treatment event corresponding to each diagnosis and treatment node from the diagnosis and treatment event set corresponding to each diagnosis and treatment node, wherein the target diagnosis and treatment event is an initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set;

[0131] It can be understood that each standard diagnosis and treatment node corresponds to a unique initial diagnosis and treatment event. This embodiment performs data statistics on each initial diagnosis and treatment event in the diagnosis and treatment event set, and takes the initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set corresponding to each standard diagnosis and treatment node as its unique target diagnosis and treatment event.

[0132] 307. According to the preset analysis rules, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node are analyzed to obtain the diagnosis and treatment time plan for each target medical event;

[0133] 308. Construct a clinical pathway for the target disease based on the sequence of diagnosis and treatment nodes, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0134] Among them, steps 307-308 are similar to the execution steps of the above steps 104-105, and will not be repeated here.

[0135] In this embodiment, the process of extracting target diagnosis and treatment events is described in detail. By taking the event with the highest frequency of occurrence as the target diagnosis and treatment event that uniquely corresponds to the diagnosis and treatment node, the target diagnosis and treatment event is made more consistent with the diagnosis and treatment process standards, thereby improving the accuracy of the clinical pathway.

[0136] See also Figure 4 The fourth embodiment of the method for constructing a clinical pathway in the embodiment of the present invention includes:

[0137] 401. Receive a data acquisition request sent by a terminal, and acquire a diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0138] 402. Construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0139] 403. Obtain historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patients are patients who suffer from the target disease and have been cured;

[0140] 404. Obtaining event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter;

[0141] It is understandable that during the plan review and analysis process, the server uses "optimistic time (shortest time)", "pessimistic time (longest time)", and "most likely time" to reflect the "uncertainty" of each target diagnosis and treatment event. Among them, the optimistic time is the duration of the activity if the work goes smoothly, the pessimistic time is the duration of the activity based on the situation that the work does not go smoothly, and the most likely time is the duration of the activity under normal circumstances. These three parameters can be estimated by the person who is most familiar with the project and stored in the database, and then obtained by the server, or they can be calculated by the server based on a large amount of data statistics, and they are not limited in this embodiment.

[0142] 405. Based on a preset time calculation formula, the optimistic time parameter, the pessimistic time parameter and the most likely time parameter are calculated to obtain the average duration of each target diagnosis and treatment event;

[0143] It is understandable that in order to facilitate analysis and calculation, the server combines the optimistic time, pessimistic time and most likely time of each target diagnosis and treatment event into a single time (i.e., the average duration) based on a preset calculation formula, thereby converting the non-affirmative question into an affirmative question for further analysis and calculation. For the time calculation formula, please refer to Formula 1.

[0144]

[0145] Among them, t i is the average duration of target treatment event i, a i is the optimistic time of target diagnosis and treatment event i, b i is the pessimistic time of target diagnosis and treatment event i, c i is the most likely time of target diagnosis and treatment event i.

[0146] Optionally, after step 405, the server also performs variance calculation on the average duration corresponding to each target diagnosis and treatment event based on a preset variance calculation formula to obtain the activity duration variance of each target medical event, compares the activity duration variance of each target medical event with a preset threshold, and updates the average duration corresponding to the target medical events whose activity duration variance is greater than the preset threshold.

[0147] It is understandable that in order to ensure the accuracy of the time parameters of each target diagnosis and treatment task, the server performs time deviation analysis on it, and calculates the variance of the activity duration to reflect the discrete degree of the data. If the time parameters corresponding to a target diagnosis and treatment event are too discrete, it is necessary to re-determine the time parameters of the target diagnosis and treatment task. Specifically, it can be re-estimated by personnel familiar with the project or re-calculated by the server. For the variance calculation formula, please refer to Formula 2:

[0148]

[0149] Among them, β i is the variance of target diagnosis and treatment event i, a i is the optimistic time of target diagnosis and treatment event i, b i is the pessimistic time of target diagnosis and treatment event i.

[0150] 406. Construct a PERT network diagram based on each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event;

[0151] It should be understood that the PERT network is an arrow diagram similar to a flow chart, which depicts the sequence of each target diagnosis and treatment event and indicates the average duration of each event.

[0152] 407. Determine the critical path in the PERT network diagram, and calculate the slack time of each target diagnosis and treatment event based on the critical path;

[0153] It can be understood that the critical path is the longest event sequence in the PERT network diagram. The server adds up the average duration of all activities in each path to obtain the duration of each path, and takes the path with the longest duration as the critical path. The slack time of the target diagnosis and treatment event is the difference between the latest execution time and the earliest execution time of the target diagnosis and treatment event. For example, in a PERT network diagram, the critical path is ACHJK, and the longest path where the target diagnosis and treatment event HN is located is ACHNK. Among them, the average duration T(AC) of event AC is 5 days, the average duration T(CH) of event CH is 3 days, the average duration T(HJ) of event HJ is 8 days, the average duration T(HJ) of event JK is 6 days, the average duration T(HJ) of event HN is 4 days, and the average duration T(HJ) of event NK is 2 days. Then the activity duration of the critical path L = T(AC) + T(CH) + T(HJ) + T(HJ) = 22, that is, the latest execution time of the target diagnosis and treatment event HN is the 22nd day, and the earliest execution time of the target diagnosis and treatment event HN is F = T(AC) + T(CH) + T(HN) + T(NK) = 14, then the slack time Z of the target diagnosis and treatment event HN = LF = 8 days.

[0154] 408. Generate a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the relaxation time of each target diagnosis and treatment event;

[0155] It is understandable that the diagnosis and treatment time plan is used to plan the execution time of the target diagnosis and treatment events. For example, the event of the patient signing the surgical consent form has an average duration of 0.5 days and a slack time of 1 day. This means that under normal circumstances, the patient should complete the signing of the surgical consent form within 0.5 days, with a maximum delay of 1 day, that is, complete the signing of the surgical consent form within 1.5 days.

[0156] 409. Construct a clinical pathway for the target disease based on the sequence of diagnosis and treatment nodes, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0157] In this embodiment, the process of analyzing the treatment time plan for each target treatment event based on the plan review technology is described in detail. The average duration of each target treatment event is calculated by the three-point estimation method, and the relationship expression of each target treatment event is constructed by constructing a PERT network diagram, and then the slack time of each target treatment event is analyzed to obtain an accurate treatment time plan for each target treatment event.

[0158] The above describes the method for constructing a clinical pathway in an embodiment of the present invention. The following describes the device for constructing a clinical pathway in an embodiment of the present invention. Figure 5 , an embodiment of a device for constructing a clinical pathway in an embodiment of the present invention includes:

[0159] The diagnosis and treatment process acquisition module 501 is used to receive a data acquisition request sent by a terminal, and acquire the diagnosis and treatment process corresponding to the target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0160] A node sequence construction module 502 is used to construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0161] The diagnosis and treatment event extraction module 503 is used to obtain the historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node according to the historical electronic medical records, wherein the target patient is a patient who suffers from the target disease and has been cured;

[0162] The plan review and analysis module 504 is used to analyze the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node according to the preset analysis rules to obtain the diagnosis and treatment time plan for each target medical event;

[0163] The clinical pathway construction module 505 is used to construct a clinical pathway for the target disease according to the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0164] In this embodiment, the present invention is based on the plan review technology in project management to calculate the diagnosis and treatment time plan for each target diagnosis and treatment event, and mark the diagnosis and treatment time plan when constructing the clinical pathway, so as to obtain a more accurate clinical pathway.

[0165] See also Figure 6 Another embodiment of the device for constructing a clinical pathway in the embodiment of the present invention includes:

[0166] The diagnosis and treatment process acquisition module 501 is used to receive a data acquisition request sent by a terminal, and acquire the diagnosis and treatment process corresponding to the target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed;

[0167] A node sequence construction module 502 is used to construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes;

[0168] The diagnosis and treatment event extraction module 503 is used to obtain the historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node according to the historical electronic medical records, wherein the target patient is a patient who suffers from the target disease and has been cured;

[0169] The plan review and analysis module 504 is used to analyze the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node according to the preset analysis rules to obtain the diagnosis and treatment time plan for each target medical event;

[0170] The clinical pathway construction module 505 is used to construct a clinical pathway for the target disease according to the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target medical event.

[0171] The diagnosis and treatment process acquisition module 501 specifically includes:

[0172] The receiving unit 5011 is used to receive a data acquisition request sent by a terminal, wherein the data acquisition request includes a database identification parameter and a query condition parameter;

[0173] A calling unit 5012, configured to call a target database according to the database identification parameter;

[0174] The query unit 5013 is used to query multiple diagnosis and treatment processes corresponding to the target disease from the target database according to the query condition parameters.

[0175] The diagnosis and treatment event extraction module 503 specifically includes:

[0176] The medical record acquisition unit 5031 is used to acquire historical electronic medical records of multiple target patients from a preset medical database according to the target disease, wherein the target patients are patients who suffer from the target disease and have been cured;

[0177] The event extraction unit 5032 is used to extract events from the historical electronic medical records of each target patient based on natural language processing technology to obtain multiple initial diagnosis and treatment events corresponding to each target patient;

[0178] The node matching unit 5033 is used to sequentially match the multiple initial diagnosis and treatment events corresponding to each target patient with each standard diagnosis and treatment node of the target disease to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, wherein the diagnosis and treatment event set includes at least one initial diagnosis and treatment event;

[0179] The target screening unit 5034 is used to screen out the target diagnosis and treatment event corresponding to each diagnosis and treatment node from the diagnosis and treatment event set corresponding to each diagnosis and treatment node, wherein the target diagnosis and treatment event is the initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set.

[0180] Wherein, the event extraction unit is specifically used for:

[0181] Extract text from the historical electronic medical records of each target patient in turn to obtain multiple target texts;

[0182] Based on the preset word segmentation tool, each target text is segmented to obtain the word segmentation result of each target text;

[0183] According to the word segmentation results of each target text, the event extraction template corresponding to each target text is matched in the preset event extraction template set;

[0184] Based on the word segmentation results of each target text and the event extraction template corresponding to each target text, multiple event attributes corresponding to each target text are generated, and multiple initial diagnosis and treatment events corresponding to each target patient are obtained.

[0185] The plan review and analysis module 504 specifically includes:

[0186] The time parameter acquisition unit 5041 acquires the event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter;

[0187] A first calculation unit 5042 is used to calculate the optimistic time parameter, the pessimistic time parameter and the most likely time parameter based on a preset time calculation formula to obtain an average duration of each target diagnosis and treatment event;

[0188] A network diagram construction unit 5043 is used to construct a PERT network diagram according to each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event;

[0189] The second calculation unit 5044 is used to determine the key path in the PERT network diagram, and calculate the relaxation time of each target diagnosis and treatment event based on the key path;

[0190] The plan generating unit 5045 is used to generate a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the relaxation time of each target diagnosis and treatment event.

[0191] The clinical pathway construction module 505 specifically includes:

[0192] A directed edge construction unit 5051 is used to construct a directed edge corresponding to each target diagnosis and treatment event based on the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node;

[0193] A connecting unit 5052, used to sequentially connect the directed edges corresponding to each target diagnosis and treatment event according to the arrangement order of the standard diagnosis and treatment nodes in the diagnosis and treatment node sequence;

[0194] The label adding unit 5053 is used to add a plan label to the directed edge corresponding to each target diagnosis and treatment event based on the diagnosis and treatment time plan of each target diagnosis and treatment event, so as to obtain the clinical pathway of the target disease.

[0195] In the embodiment of the present invention, the modular design allows the hardware of each part of the clinical pathway construction device to focus on the realization of a certain function, thereby maximizing the performance of the hardware. At the same time, the modular design also reduces the coupling between the modules of the device, making maintenance more convenient.

[0196] above Figure 5 and Figure 6 The clinical pathway construction device in the embodiment of the present invention is described in detail from the perspective of modular functional entities. The clinical pathway construction device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0197] Figure 7 7 is a schematic diagram of the structure of a clinical pathway construction device provided by an embodiment of the present invention. The clinical pathway construction device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 may be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the clinical pathway construction device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the clinical pathway construction device 700.

[0198] The clinical pathway construction device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input and output interfaces 760, and / or one or more operating systems 731, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Figure 7 The structure of the clinical pathway construction device shown does not constitute a limitation on the clinical pathway construction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0199] The present invention also provides a clinical pathway construction device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the clinical pathway construction method in the above-mentioned embodiments.

[0200] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein instructions are stored in the computer, and when the instructions are executed on a computer, the computer executes the steps of the method for constructing a clinical pathway.

[0201] Those skilled in the art can 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.

[0202] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or 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, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0203] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a clinical pathway, characterized in that: The method for constructing the clinical pathway includes: Receiving a data acquisition request sent by a terminal, and acquiring a diagnosis and treatment process corresponding to a target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed, and the diagnosis and treatment process includes a record of the entire process from registration to discharge of a patient; According to the diagnosis and treatment process corresponding to the target disease, a diagnosis and treatment node sequence corresponding to the target disease is constructed, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes; Obtaining historical electronic medical records of multiple target patients, and determining the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patients are patients who suffer from the target disease and have been cured; According to the preset analysis rules, the time parameters for each target diagnosis and treatment event are obtained from multiple dimensions, and the time parameters for multiple dimensions under each target diagnosis and treatment event are calculated through the preset calculation formula, and the corresponding PERT network diagram is constructed for analysis to obtain the corresponding diagnosis and treatment time plan; Constructing a clinical pathway for the target disease according to the sequence of diagnosis and treatment nodes, the target diagnosis and treatment events corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target diagnosis and treatment event; The method of obtaining the time parameters for defining each target diagnosis and treatment event from multiple dimensions according to the preset analysis rules, and calculating the time parameters of multiple dimensions under each target diagnosis and treatment event through the preset calculation formula, constructing a corresponding PERT network diagram for analysis, and obtaining a corresponding diagnosis and treatment time plan includes: obtaining the event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter, and a most likely time parameter; calculating the optimistic time parameter, the pessimistic time parameter, and the most likely time parameter based on the preset time calculation formula to obtain the average duration of each target diagnosis and treatment event; constructing a PERT network diagram according to each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event; determining the critical route in the PERT network diagram, and calculating the slack time of each target diagnosis and treatment event based on the critical route; generating a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the slack time of each target diagnosis and treatment event; After calculating the optimistic time, the pessimistic time and the most likely time based on the preset time calculation formula to obtain the average duration corresponding to each target diagnosis and treatment event, and before constructing the PERT network diagram based on each target diagnosis and treatment event and the average duration corresponding to each target diagnosis and treatment event, it also includes: performing variance calculation on the average duration corresponding to each target diagnosis and treatment event based on the preset variance calculation formula to obtain the activity duration variance of each target diagnosis and treatment event; comparing the activity duration variance of each target diagnosis and treatment event with a preset threshold, and updating the average duration corresponding to the target diagnosis and treatment events whose activity duration variance is greater than the preset threshold.

2. The method for constructing a clinical pathway according to claim 1, characterized in that: The receiving terminal sends a data acquisition request, and acquiring the diagnosis and treatment process corresponding to the target disease according to the data acquisition request includes: Receiving a data acquisition request sent by a terminal, wherein the data acquisition request includes a database identification parameter and a query condition parameter; Calling the target database according to the database identification parameter; According to the query condition parameters, the diagnosis and treatment process corresponding to the target disease is queried from the target database.

3. The method for constructing a clinical pathway according to claim 2, characterized in that: The step of obtaining the historical electronic medical records of multiple target patients and determining the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node according to the historical electronic medical records includes: According to the target disease, obtaining historical electronic medical records of multiple target patients from a preset medical database, wherein the target patients are patients who suffer from the target disease and have been cured; Based on natural language processing technology, events are extracted from the historical electronic medical records of each target patient to obtain multiple initial diagnosis and treatment events corresponding to each target patient; Sequentially matching multiple initial diagnosis and treatment events corresponding to each target patient with each standard diagnosis and treatment node of the target disease to obtain a diagnosis and treatment event set corresponding to each standard diagnosis and treatment node, wherein the diagnosis and treatment event set includes at least one initial diagnosis and treatment event; From the diagnosis and treatment event set corresponding to each diagnosis and treatment node, the target diagnosis and treatment event corresponding to each diagnosis and treatment node is screened out, wherein the target diagnosis and treatment event is the initial diagnosis and treatment event with the highest frequency in the diagnosis and treatment event set.

4. The method for constructing a clinical pathway according to claim 3, characterized in that: Based on the natural language processing technology, the historical electronic medical records of each target patient are extracted to obtain multiple initial diagnosis and treatment events corresponding to each target patient, including: Extract text from the historical electronic medical records of each target patient in turn to obtain multiple target texts; Based on the preset word segmentation tool, each target text is segmented to obtain the word segmentation result of each target text; According to the word segmentation results of each target text, the event extraction template corresponding to each target text is matched in the preset event extraction template set; Based on the word segmentation results of each target text and the event extraction template corresponding to each target text, multiple event attributes corresponding to each target text are generated, and multiple initial diagnosis and treatment events corresponding to each target patient are obtained.

5. The method for constructing a clinical pathway according to any one of claims 1 to 4, characterized in that: The constructing of the clinical pathway of the target disease according to the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target diagnosis and treatment event includes: Based on the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, a directed edge corresponding to each target diagnosis and treatment event is constructed; Connecting the directed edges corresponding to each target diagnosis and treatment event in sequence according to the arrangement order of the standard diagnosis and treatment nodes in the diagnosis and treatment node sequence; Based on the diagnosis and treatment time plan for each target diagnosis and treatment event, a plan label is added to the directed edge corresponding to each target diagnosis and treatment event to obtain the clinical pathway of the target disease.

6. A device for constructing a clinical pathway, characterized in that: The clinical pathway construction device comprises: A diagnosis and treatment process acquisition module is used to receive a data acquisition request sent by a terminal, and acquire the diagnosis and treatment process corresponding to the target disease according to the data acquisition request, wherein the target disease is a disease for which a clinical pathway is to be constructed, and the diagnosis and treatment process includes the entire process record of the patient from registration to discharge; A node sequence construction module, used to construct a diagnosis and treatment node sequence corresponding to the target disease according to the diagnosis and treatment process corresponding to the target disease, wherein the diagnosis and treatment node sequence includes a plurality of standard diagnosis and treatment nodes; A diagnosis and treatment event extraction module is used to obtain historical electronic medical records of multiple target patients, and determine the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node based on the historical electronic medical records, wherein the target patient is a patient who suffers from the target disease and has been cured; The plan review and analysis module is used to obtain the time parameters defined for each target diagnosis and treatment event from multiple dimensions according to the preset analysis rules, and calculate the time parameters of multiple dimensions under each target diagnosis and treatment event through the preset calculation formula, construct the corresponding PERT network diagram for analysis, and obtain the corresponding diagnosis and treatment time plan; A clinical pathway construction module, used to construct a clinical pathway for the target disease according to the diagnosis and treatment node sequence, the target diagnosis and treatment event corresponding to each standard diagnosis and treatment node, and the diagnosis and treatment time plan for each target diagnosis and treatment event; The plan review and analysis module includes: a time parameter acquisition unit, which acquires the event time parameters corresponding to each target diagnosis and treatment event from a preset database, wherein the event time parameters include an optimistic time parameter, a pessimistic time parameter and a most likely time parameter; a first calculation unit, which is used to calculate the optimistic time parameter, the pessimistic time parameter and the most likely time parameter based on a preset time calculation formula to obtain the average duration of each target diagnosis and treatment event; a network diagram construction unit, which is used to construct a PERT network diagram according to each target diagnosis and treatment event and the average duration of each target diagnosis and treatment event; a second calculation unit, which is used to determine the critical path in the PERT network diagram, and calculate the slack time of each target diagnosis and treatment event based on the critical path; a plan generation unit, which is used to generate a diagnosis and treatment time plan for each target diagnosis and treatment event according to the average duration of each target diagnosis and treatment event and the slack time of each target diagnosis and treatment event; After the first calculation unit and before the network diagram construction unit, it also includes: based on a preset variance calculation formula, performing variance calculation on the average duration corresponding to each target diagnosis and treatment event to obtain the activity duration variance of each target diagnosis and treatment event; comparing the activity duration variance of each target diagnosis and treatment event with a preset threshold, and updating the average duration corresponding to the target diagnosis and treatment events whose activity duration variance is greater than the preset threshold.

7. A clinical pathway construction device, characterized in that: The clinical pathway construction device includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the clinical pathway construction device to execute the clinical pathway construction method according to any one of claims 1 to 5.

8. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the method for constructing a clinical pathway according to any one of claims 1 to 5 is implemented.

Images