Error diagnosis and missed diagnosis guiding method and system for emergency admission patient

Abstract

The invention provides a wrong diagnosis and missed diagnosis guiding method and system for emergency admission patients, and the method comprises the steps: obtaining the case information of each historical emergency admission patient, and recognizing the diagnosis process and diagnosis information of the case information for each piece of case information; identifying an abnormal diagnosis process of the case information, and based on diagnosis information corresponding to the case information, identifying abnormal diagnosis content and a target diagnosis type of the case information through a diagnosis logic inverse deduction strategy; generating a target diagnosis process guide strategy and a target diagnosis logic guide strategy corresponding to each target diagnosis type, and comparing the target diagnosis process guide strategy corresponding to each target diagnosis type and the target diagnosis logic guide strategy corresponding to each target diagnosis type with the target diagnosis logic guide strategy corresponding to each target diagnosis type; and taking as a target diagnosis guidance strategy of each target diagnosis type. By adopting the scheme, the prevention and control effect on false diagnosis and missed diagnosis can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data and data analysis, and in particular to a method and system for guiding misdiagnosis and missed diagnosis of emergency hospitalized patients. Background Art

[0002] During the treatment of emergency patients, misdiagnosis or missed diagnosis may occur due to time constraints and complex conditions. The existing case management system lacks an effective tracking and screening mechanism, and is unable to detect and handle these situations in a timely manner. As a result, the management effect of emergency patients is poor. Therefore, how to improve the misdiagnosis and missed diagnosis of emergency patients is the current research focus.

[0003] The traditional way to optimize and improve misdiagnosis and missed diagnosis of emergency patients is to manually generate diagnostic process management specifications for patients under different medical conditions based on relevant cases of misdiagnosis and missed diagnosis, thereby reducing misdiagnosis and missed diagnosis. However, when emergency patients are admitted to the hospital, time is urgent and the circumstances are special, making it impossible for medical staff to fully follow the process management specifications, resulting in poor prevention and control of misdiagnosis and missed diagnosis. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and system for guiding misdiagnosis and missed diagnosis for emergency patients, aiming to solve the problem in the prior art that when emergency patients are admitted to the hospital, time is urgent and the circumstances are special, making it impossible for medical staff to operate in full accordance with process management specifications, resulting in poor prevention and control of misdiagnosis and missed diagnosis.

[0005] To achieve the above object, the present invention provides a method for guiding misdiagnosis and missed diagnosis of patients admitted to an emergency department, the method comprising:

[0006] Obtaining case information of each patient who has been admitted to the emergency department in history, and for each case information, identifying the diagnosis process of the case information and the diagnosis information of the case information;

[0007] Based on the diagnostic process corresponding to the case information, identify the abnormal diagnostic process of the case information, and based on the diagnostic information corresponding to the case information, identify the abnormal diagnostic content of the case information and the target diagnostic type corresponding to the case information through a diagnostic logic reverse inference strategy;

[0008] Based on the abnormal diagnosis process of each of the case information, the abnormal diagnosis content of each of the case information, and the target diagnosis type corresponding to each of the case information, a target diagnosis process guidance strategy corresponding to each of the target diagnosis types and a target diagnosis logic guidance strategy corresponding to each of the target diagnosis types are generated, and the target diagnosis process guidance strategy corresponding to each of the target diagnosis types and the target diagnosis logic guidance strategy corresponding to each of the target diagnosis types are used as the target diagnosis guidance strategy for each of the target diagnosis types.

[0009] Optionally, the diagnostic process for identifying the case information and the diagnostic information of the case information include:

[0010] Splitting the case information into diagnosis process record information and diagnosis content record information;

[0011] Identify the actual process content corresponding to each process node of the case diagnosis process record information and the diagnosis strategy corresponding to each process node, and use the actual process content corresponding to all process nodes and the diagnosis strategy corresponding to all process nodes as the diagnosis process of the case information;

[0012] Based on the diagnosis content record information, the sub-diagnosis results of the patient at each process node and the diagnosis logic of each process node are identified, and the sub-diagnosis results of all process nodes and the diagnosis logic of each process node are used as the diagnosis information of the case information.

[0013] Optionally, the step of identifying an abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information includes:

[0014] Based on the actual process content corresponding to each process node, query the sample diagnosis strategy corresponding to each process node in the diagnosis database, and extract each strategy feature of each diagnosis strategy and each sample strategy feature of the sample diagnosis strategy corresponding to each diagnosis strategy;

[0015] For each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy is calculated through a similarity recognition algorithm, and the diagnostic strategy corresponding to the similarity below the similarity threshold is used as an abnormal diagnostic strategy;

[0016] The process nodes corresponding to all abnormal diagnosis strategies are used as the abnormal diagnosis process of the case information.

[0017] Optionally, the identifying, based on the diagnosis information corresponding to the case information, the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information through a diagnostic logic reverse inference strategy includes:

[0018] According to the order from front to back in the process sequence of each process node, the target process node is screened, and based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node, the reverse input data of the target process node is identified through the diagnostic logic reverse strategy;

[0019] Based on the actual input data of the target process node and the reverse input data of the target process node, the difference input data of the target process node is identified through a data difference information identification strategy, and the proportion of the data volume of the difference input data to the data volume of the actual input data is calculated;

[0020] In the case where the proportion value is lower than the preset proportion value, after the input data in the process sequence, the target process node is re-screened, and the diagnostic logic based on the target process node and the sub-diagnosis result of the process node are returned to be executed, and the reverse input data step of the process node is identified through the diagnostic logic reverse strategy, until the proportion value is not lower than the preset proportion value, the diagnostic logic of the target process node, the sub-diagnosis result of the target process node, the diagnostic logic of all process nodes after the target process node, and the sub-diagnosis results of all process nodes after the target process node are used as the abnormal diagnosis content of the case information;

[0021] Obtain the historical diagnosis logic of the target process node, the historical diagnosis logic of all process nodes after the target process node, and the actual input data of the target process node, generate the historical diagnosis result of the last process node in the process sequence, and use the diagnosis type corresponding to the historical diagnosis result as the target diagnosis type corresponding to the case information.

[0022] Optionally, the step of identifying the reverse input data of the process node by using a reverse strategy of the diagnostic logic based on the target process node and the sub-diagnosis result of the target process node includes:

[0023] Based on the diagnostic logic of the target process node, identify the logical order of each logic strategy of the target process node, and query the reverse strategy corresponding to each logic strategy in the logic database;

[0024] The reverse strategies corresponding to each logical strategy are sorted in the reverse order of the logical order to obtain the reverse logical strategy of the target process node, and the reverse logical strategy is executed based on the sub-diagnosis result of the target process node to generate the reverse input data of the target process node.

[0025] Optionally, the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type are generated based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, including:

[0026] Classify each of the case information according to each of the target diagnosis types to obtain case groups of each of the target diagnosis types, and for each case group, based on the abnormal diagnosis process of each of the case information in the case group and the abnormal diagnosis content of each of the case information in the case group, count the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group;

[0027] In each of the abnormal diagnosis strategies, the target abnormal diagnosis strategies corresponding to each first abnormal frequency greater than the abnormal frequency threshold and the target abnormal diagnosis logic corresponding to each second abnormal frequency greater than the abnormal frequency threshold are screened, and based on each target abnormal diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormal diagnosis strategy, a target diagnosis strategy corresponding to each target abnormal diagnosis strategy is generated through a strategy optimization algorithm;

[0028] For each target abnormality diagnosis logic, based on each sub-diagnosis result corresponding to the target abnormality diagnosis logic, identify the abnormality cause of the target abnormality diagnosis logic, and based on the abnormality cause of the target abnormality diagnosis logic, generate the target diagnosis logic corresponding to each target abnormality diagnosis logic through a logic optimization algorithm;

[0029] All target diagnosis strategies of the case group are used as target diagnosis process guidance strategies for the target diagnosis type corresponding to the case group, and all target diagnosis logics of the case group are used as target diagnosis logic guidance strategies corresponding to the target diagnosis type corresponding to the case group.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also provides a misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients, the misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients comprising:

[0031] An acquisition module is used to acquire the case information of each patient who has been admitted to the emergency department in history, and for each case information, identify the diagnosis process of the case information and the diagnosis information of the case information;

[0032] an identification module, for identifying an abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information, and identifying the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information through a diagnostic logic reverse inference strategy based on the diagnosis information corresponding to the case information;

[0033] A guidance module is used to generate a target diagnosis process guidance strategy corresponding to each target diagnosis type and a target diagnosis logic guidance strategy corresponding to each target diagnosis type based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, and use the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type.

[0034] Optionally, the acquisition module is specifically used to:

[0035] Splitting the case information into diagnosis process record information and diagnosis content record information;

[0036] Identify the actual process content corresponding to each process node of the case diagnosis process record information and the diagnosis strategy corresponding to each process node, and use the actual process content corresponding to all process nodes and the diagnosis strategy corresponding to all process nodes as the diagnosis process of the case information;

[0037] Based on the diagnosis content record information, the sub-diagnosis results of the patient at each process node and the diagnosis logic of each process node are identified, and the sub-diagnosis results of all process nodes and the diagnosis logic of each process node are used as the diagnosis information of the case information.

[0038] Optionally, the identification module is specifically used to:

[0039] Based on the actual process content corresponding to each process node, query the sample diagnosis strategy corresponding to each process node in the diagnosis database, and extract each strategy feature of each diagnosis strategy and each sample strategy feature of the sample diagnosis strategy corresponding to each diagnosis strategy;

[0040] For each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy is calculated through a similarity recognition algorithm, and the diagnostic strategy corresponding to the similarity below the similarity threshold is used as an abnormal diagnostic strategy;

[0041] The process nodes corresponding to all abnormal diagnosis strategies are used as the abnormal diagnosis process of the case information.

[0042] Optionally, the identification module is specifically used to:

[0043] According to the order from front to back in the process sequence of each process node, the target process node is screened, and based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node, the reverse input data of the target process node is identified through the diagnostic logic reverse strategy;

[0044] Based on the actual input data of the target process node and the reverse input data of the target process node, the difference input data of the target process node is identified through a data difference information identification strategy, and the proportion of the data volume of the difference input data to the data volume of the actual input data is calculated;

[0045] In the case where the proportion value is lower than the preset proportion value, after the input data in the process sequence, the target process node is re-screened, and the diagnostic logic based on the target process node and the sub-diagnosis result of the process node are returned to be executed, and the reverse input data step of the process node is identified through the diagnostic logic reverse strategy, until the proportion value is not lower than the preset proportion value, the diagnostic logic of the target process node, the sub-diagnosis result of the target process node, the diagnostic logic of all process nodes after the target process node, and the sub-diagnosis results of all process nodes after the target process node are used as the abnormal diagnosis content of the case information;

[0046] Obtain the historical diagnosis logic of the target process node, the historical diagnosis logic of all process nodes after the target process node, and the actual input data of the target process node, generate the historical diagnosis result of the last process node in the process sequence, and use the diagnosis type corresponding to the historical diagnosis result as the target diagnosis type corresponding to the case information.

[0047] Optionally, the identification module is specifically used to:

[0048] Based on the diagnostic logic of the target process node, identify the logical order of each logic strategy of the target process node, and query the reverse strategy corresponding to each logic strategy in the logic database;

[0049] The reverse strategies corresponding to each logical strategy are sorted in the reverse order of the logical order to obtain the reverse logical strategy of the target process node, and the reverse logical strategy is executed based on the sub-diagnosis result of the target process node to generate the reverse input data of the target process node.

[0050] Optionally, the guidance module is specifically used to:

[0051] Classify each of the case information according to each of the target diagnosis types to obtain case groups of each of the target diagnosis types, and for each case group, based on the abnormal diagnosis process of each of the case information in the case group and the abnormal diagnosis content of each of the case information in the case group, count the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group;

[0052] In each of the abnormal diagnosis strategies, the target abnormal diagnosis strategies corresponding to each first abnormal frequency greater than the abnormal frequency threshold and the target abnormal diagnosis logic corresponding to each second abnormal frequency greater than the abnormal frequency threshold are screened, and based on each target abnormal diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormal diagnosis strategy, a target diagnosis strategy corresponding to each target abnormal diagnosis strategy is generated through a strategy optimization algorithm;

[0053] For each target abnormality diagnosis logic, based on each sub-diagnosis result corresponding to the target abnormality diagnosis logic, identify the abnormality cause of the target abnormality diagnosis logic, and based on the abnormality cause of the target abnormality diagnosis logic, generate the target diagnosis logic corresponding to each target abnormality diagnosis logic through a logic optimization algorithm;

[0054] All target diagnosis strategies of the case group are used as target diagnosis process guidance strategies for the target diagnosis type corresponding to the case group, and all target diagnosis logics of the case group are used as target diagnosis logic guidance strategies corresponding to the target diagnosis type corresponding to the case group.

[0055] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0056] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0057] In a fifth aspect, the present application provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0058] The present invention provides a method and system for guiding misdiagnosis and missed diagnosis of patients admitted to the hospital for emergency treatment. The method comprises: obtaining case information of each patient admitted to the hospital for emergency treatment in history, and identifying the diagnostic process of the case information and the diagnostic information of the case information for each case information; identifying the abnormal diagnostic process of the case information based on the diagnostic process corresponding to the case information, and identifying the abnormal diagnostic content of the case information and the target diagnosis type corresponding to the case information through a diagnostic logic reverse strategy based on the diagnostic information corresponding to the case information; generating a target diagnosis process guidance strategy corresponding to each target diagnosis type and a target diagnosis logic guidance strategy corresponding to each target diagnosis type based on the abnormal diagnostic process of each case information, the abnormal diagnostic content of each case information and the target diagnosis type corresponding to each case information, and using the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type. This solution separates the diagnosis process and diagnosis information of the case information of patients admitted to the emergency department in history, and then identifies the abnormal diagnosis process in the diagnosis process, and identifies the abnormal diagnosis content in the diagnosis process through the diagnostic logic reverse deduction strategy, thereby avoiding the error rate and inefficiency of manual analysis, and improving the comprehensiveness, accuracy and efficiency of the identification of misdiagnosis and missed diagnosis. Then, this solution combines the abnormal diagnosis process and abnormal diagnosis content of the case information of different target diagnosis types, so as to comprehensively generate the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type, so as to efficiently and accurately share and generate guidance for each abnormal diagnosis process and abnormal diagnosis logic, so as to provide efficient and convenient guidance strategies for the staff when diagnosing the patients admitted to the emergency department, and avoid the abnormal problems that the staff cannot execute according to the process management specifications due to time urgency or special circumstances. And the guidance strategy can provide auxiliary guidance to the staff's diagnosis process in real time, thereby effectively reducing the probability of misdiagnosis and missed diagnosis, and improving the prevention and control effect of misdiagnosis and missed diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 is a flow chart of a misdiagnosis and missed diagnosis guidance method for emergency hospitalized patients provided by an embodiment of the present invention;

[0061] Figure 2 is a structural schematic diagram of a misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients provided by an embodiment of the present invention;

[0062] Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The misdiagnosis and missed diagnosis guidance method for emergency hospitalized patients provided by an embodiment of the present invention is applied to the misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned figures are used to distinguish different objects, not to describe a specific order.

[0064] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0065] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0066] The misdiagnosis and missed diagnosis guidance method for emergency hospitalized patients provided in the embodiment of the present application can be applied to the application environment of emergency patient admission and treatment. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. Among them, the terminal splits the diagnosis process and the diagnosis information of the case information of the patients with historical emergency hospitalization, and then identifies the abnormal diagnosis process in the diagnosis process, and identifies the abnormal diagnosis content in the diagnosis process through the diagnostic logic reverse strategy, thereby avoiding the error rate and inefficiency of manual analysis, and improving the comprehensiveness, accuracy and efficiency of the identification of misdiagnosis and missed diagnosis. Then, this solution combines the abnormal diagnosis process and abnormal diagnosis content of case information of different target diagnosis types, thereby comprehensively generating the target diagnosis process guidance strategy corresponding to each target diagnosis type, and the target diagnosis logic guidance strategy corresponding to each target diagnosis type, so as to efficiently and accurately share and generate guidance for each abnormal diagnosis process and abnormal diagnosis logic, so as to provide efficient and convenient guidance strategies for staff when diagnosing emergency patients, avoiding abnormal problems that staff cannot execute according to process management specifications due to time urgency or special circumstances. And this guidance strategy can provide auxiliary guidance for the staff's diagnosis process in real time, thereby effectively reducing the probability of misdiagnosis and missed diagnosis, and improving the prevention and control effect of misdiagnosis and missed diagnosis.

[0067] In one embodiment, Figure 1 As shown, a misdiagnosis and missed diagnosis guidance method for emergency hospitalized patients is provided, and the method is applied to a terminal as an example for explanation, including the following steps:

[0068] Step S101, obtaining the case information of each patient who has been admitted to the emergency department in history, and for each case information, identifying the diagnosis process of the case information and the diagnosis information of the case information.

[0069] In this embodiment, the terminal obtains the case information of each patient admitted to the emergency department in the hospital database, wherein the case information is the diagnosis record information of the patient, and the diagnosis record information includes the diagnosis process record information and the diagnosis content record information. The diagnosis process record information is the operation process of the medical staff during the emergency diagnosis of the patient, and the diagnosis strategy for each operation process. The operation process can be divided into the actual operation process content of each process node and the diagnosis strategy of each process node. The diagnosis strategy includes but is not limited to the diagnosis strategy of the detection data diagnosis strategy, the historical disease diagnosis strategy, the observation diagnosis strategy, the consultation diagnosis strategy and other diagnosis strategies, and the strategy execution process of different diagnosis strategies is different. The diagnosis content record information is the diagnosis logic of each process node and the sub-diagnosis result of each process node. Since the sub-diagnosis result of each process node will affect the sub-diagnosis result of the next process node, each sub-diagnosis result is the actual input data of the next process node. The diagnosis logic is the judgment logic of the sub-diagnosis result obtained by analyzing the sub-diagnosis result of the previous process node and the detection data of the process node. The terminal presets the judgment logic of each diagnosis result and the reverse logic of each judgment logic. The reverse logic is the judgment logic of obtaining the input data by reversely inferring the sub-diagnosis results. Finally, the terminal identifies the diagnosis process of the case information and the diagnosis information of the case information. The specific identification process will be described in detail later.

[0070] Step S102, based on the diagnostic process corresponding to the case information, identify the abnormal diagnostic process of the case information, and based on the diagnostic information corresponding to the case information, identify the abnormal diagnostic content of the case information and the target diagnostic type corresponding to the case information through the diagnostic logic reverse inference strategy.

[0071] In this embodiment, the terminal identifies the abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information, and identifies the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information through the diagnostic logic reverse inference strategy based on the diagnosis information corresponding to the case information. Among them, the abnormal diagnosis process is the process node corresponding to the diagnostic strategy with the same process content and different from the sample diagnosis strategy. The abnormal diagnosis content includes the abnormal diagnosis logic and the sub-diagnosis result corresponding to the abnormal diagnosis logic. The specific identification process will be described in detail later.

[0072] Step S103, based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, generate a target diagnosis process guidance strategy corresponding to each target diagnosis type, and a target diagnosis logic guidance strategy corresponding to each target diagnosis type, and use the target diagnosis process guidance strategy corresponding to each target diagnosis type, and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type.

[0073] In this embodiment, the terminal generates a target diagnosis process guidance strategy corresponding to each target diagnosis type and a target diagnosis logic guidance strategy corresponding to each target diagnosis type based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, and uses the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type. Among them, the target diagnosis process guidance strategy includes the target diagnosis strategy corresponding to each target abnormal diagnosis strategy, and the target diagnosis logic guidance strategy includes the target diagnosis logic corresponding to each target abnormal diagnosis logic. The specific identification process and subsequent description will be described in detail.

[0074] Based on the above scheme, after splitting the case information of patients admitted to the emergency department into diagnostic processes and diagnostic information, the abnormal diagnostic processes in the diagnostic process are identified respectively, and the abnormal diagnostic content in the diagnostic process is identified respectively through the diagnostic logic reverse deduction strategy, thereby avoiding the error rate and inefficiency of manual analysis and improving the comprehensiveness, accuracy and efficiency of the identification of misdiagnosis and missed diagnosis. Then, this scheme combines the abnormal diagnostic processes and abnormal diagnostic content of case information of different target diagnostic types to comprehensively generate the target diagnostic process guidance strategy corresponding to each target diagnostic type and the target diagnostic logic guidance strategy corresponding to each target diagnostic type, so as to efficiently and accurately share and generate guidance for each abnormal diagnostic process and abnormal diagnostic logic, so as to provide efficient and convenient guidance strategies for staff when diagnosing patients admitted to the emergency department, avoiding the abnormal problem that staff cannot perform according to the process management specifications due to urgent time or special circumstances. And the guidance strategy can provide auxiliary guidance to the staff's diagnosis process in real time, thereby effectively reducing the probability of misdiagnosis and missed diagnosis, and improving the prevention and control effect of misdiagnosis and missed diagnosis.

[0075] Optionally, identifying the diagnostic process of case information and the diagnostic information of case information includes: splitting the case information into diagnostic process record information and diagnostic content record information; identifying the actual process content corresponding to each process node of the case diagnostic process record information and the diagnostic strategy corresponding to each process node, and using the actual process content corresponding to all process nodes and the diagnostic strategy corresponding to all process nodes as the diagnostic process of the case information; based on the diagnostic content record information, identifying the patient's sub-diagnosis results at each process node and the diagnostic logic of each process node, and using the sub-diagnosis results of all process nodes and the diagnostic logic of each process node as the diagnostic information of the case information.

[0076] In this embodiment, the terminal splits the case information into diagnostic process record information and diagnostic content record information. Then, the terminal identifies the actual process content corresponding to each process node of the case diagnosis process record information, and the diagnostic strategy corresponding to each process node, and uses the actual process content corresponding to all process nodes, and the diagnostic strategy corresponding to all process nodes as the diagnostic process of the case information. Among them, the actual process content corresponding to all process nodes is the full process content of the case diagnosis, and each process node corresponds to an actual process content (i.e., the sub-process content of the full process content). The process content is the process content preset by the staff in the terminal, and the full process content of the same diagnosis type is the same. The diagnostic strategy of the same process content can be the same or different, and the diagnostic logic of each process content is determined by the staff who executes each process content. The diagnostic logic of the same process content can be the same or different.

[0077] The terminal records information based on the diagnosis content, identifies the patient's sub-diagnosis results at each process node and the diagnostic logic of each process node, and uses the sub-diagnosis results of all process nodes and the diagnostic logic of each process node as the diagnostic information of the case information.

[0078] Based on the above solution, by splitting the case information into the actual process content and diagnosis strategy of each process node, the diagnosis process is obtained, and then the diagnosis logic of each process node and the sub-diagnosis results are identified, thereby improving the comprehensiveness and accuracy of the identification of diagnostic information and diagnostic processes.

[0079] Optionally, based on the diagnostic process corresponding to the case information, identifying abnormal diagnostic processes of the case information, including: based on the actual process content corresponding to each process node, querying the sample diagnostic strategy corresponding to each process node in the diagnostic database, and respectively extracting each strategy feature of each diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to each diagnostic strategy; for each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, calculating the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy through a similarity recognition algorithm, and treating the diagnostic strategy corresponding to the similarity below the similarity threshold as an abnormal diagnostic strategy; treating the process nodes corresponding to all abnormal diagnostic strategies as abnormal diagnostic processes of the case information.

[0080] In this embodiment, based on the actual process content corresponding to each process node, the terminal queries the sample diagnostic strategy corresponding to each process node in the diagnostic database, and extracts each strategy feature of each diagnostic strategy, and each sample strategy feature of the sample diagnostic strategy corresponding to each diagnostic strategy. Wherein, each diagnostic strategy and each sample diagnostic strategy are text information, and the terminal extracts the strategy features of each diagnostic strategy through a text extraction neural network based on natural language processing technology.

[0081] For each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy is calculated by a similarity recognition algorithm. The similarity recognition algorithm is a cosine similarity recognition algorithm. The similarity between each diagnostic strategy and the sample diagnostic strategy is the average of the similarities between each strategy feature and each sample strategy feature.

[0082] Then, the terminal uses the diagnosis strategy corresponding to the similarity lower than the similarity threshold preset in the terminal as the abnormal diagnosis strategy, and uses the process nodes corresponding to all abnormal diagnosis strategies as the abnormal diagnosis process of the case information.

[0083] Based on the above scheme, after feature extraction, similarity recognition is performed, and then the abnormal diagnosis strategy is screened, which improves the accuracy and comprehensiveness of identifying abnormal diagnosis strategies.

[0084] Optionally, based on the diagnostic information corresponding to the case information, a diagnostic logic reverse strategy is used to identify the abnormal diagnostic content of the case information and the target diagnostic type corresponding to the case information, including: screening the target process nodes in order from front to back in the process sequence of each process node, and based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node, identifying the reverse input data of the target process node through a diagnostic logic reverse strategy; based on the actual input data of the target process node and the reverse input data of the target process node, identifying the difference input data of the target process node through a data difference information identification strategy, and calculating the proportion of the data volume of the difference input data to the data volume of the actual input data; when the proportion is lower than a preset proportion, re-screen the target process node after the input data in the process sequence. Process node, returns to execute the diagnostic logic based on the target process node, and the sub-diagnosis result of the process node, and identifies the reverse input data step of the process node through the diagnostic logic reverse strategy, until the proportion value is not less than the preset proportion value, the diagnostic logic of the target process node, the sub-diagnosis result of the target process node, the diagnostic logic of all process nodes after the target process node, and the sub-diagnosis result of all process nodes after the target process node are used as the abnormal diagnosis content of the case information; obtains the historical diagnostic logic of the target process node, the historical diagnostic logic of all process nodes after the target process node, and the actual input data of the target process node, generates the historical diagnostic result of the last process node in the process sequence, and uses the diagnosis type corresponding to the historical diagnostic result as the target diagnosis type corresponding to the case information.

[0085] In this embodiment, the terminal screens the target process nodes according to the order from front to back in the process sequence of each process node, and identifies the reverse input data of the target process node through the diagnostic logic reverse strategy based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node. The specific identification process of the diagnostic logic reverse strategy will be described in detail later. Among them, the target process nodes are screened according to the order from front to back in the process sequence of each process node, that is, the logical reverse is performed on each process node from front to back according to the process sequence. If there is an abnormal diagnostic logic, since the diagnostic logic of each process node is screened based on the sub-diagnosis result of the previous process node of the process node, and in the case of abnormal diagnostic logic, the diagnostic logic from the process node onwards will be abnormal, and the sub-diagnosis result corresponding to each diagnostic logic will also be abnormal.

[0086] Afterwards, the terminal identifies the difference input data of the target process node based on the actual input data of the target process node and the reverse input data of the target process node through the data difference information identification strategy, and calculates the proportion of the data volume of the difference input data to the data volume of the actual input data. Among them, the difference input data is the different data content in the two input data. When there is an abnormality in the diagnostic logic, in most cases, the two input data are completely different. Therefore, although the ratio value preset by the terminal is the ratio value preset by the staff in the terminal, the range of the ratio value should be between 80% and 90%.

[0087] Then, when the proportion value is lower than the preset proportion value, the terminal re-screens the target process node after the input data in the process sequence, returns to execute the diagnosis logic based on the target process node, and the sub-diagnosis result of the process node, and identifies the reverse input data steps of the process node through the diagnosis logic reverse strategy, until the proportion value is not lower than the preset proportion value, the diagnosis logic of the target process node, the sub-diagnosis result of the target process node, the diagnosis logic of all process nodes after the target process node, and the sub-diagnosis results of all process nodes after the target process node are used as the abnormal diagnosis content of the case information.

[0088] After that, the terminal obtains the historical diagnosis logic of the target process node, the historical diagnosis logic of all process nodes after the target process node, and the actual input data of the target process node, generates the historical diagnosis result of the last process node in the process sequence, and uses the diagnosis type corresponding to the historical diagnosis result as the target diagnosis type corresponding to the case information. Among them, the terminal presets the diagnosis procedure of each diagnostic logic, and through the actual input data of the target process node, according to the sequence of each process node, the actual input data is logically judged to obtain the diagnosis result of the last process node, and the diagnosis result is used as the historical diagnosis result of the last process node. Each diagnosis result contains an identifier of a diagnosis type. The terminal identifies the identifier of the diagnosis type contained in the historical diagnosis result, and queries the diagnosis type corresponding to the identifier of the diagnosis type in the diagnosis database to obtain the target diagnosis type corresponding to the case information. Among them, the target diagnosis type is the type of diagnosis for different emergency conditions of the patient, such as ophthalmology diagnosis type, internal medicine diagnosis type, surgical diagnosis type, etc., which are divided according to the diagnosis type of each department.

[0089] Based on the above solution, the abnormal diagnosis logic is identified by logical inversion, which avoids the inefficiency of manual identification and improves the recognition efficiency and accuracy of the abnormal diagnosis logic.

[0090] Optionally, based on the diagnostic logic of the target process node and the sub-diagnostic result of the target process node, the reverse input data of the process node is identified through the diagnostic logic reverse strategy, including: based on the diagnostic logic of the target process node, identifying the logical order of each logical strategy of the target process node, and querying the reverse strategy corresponding to each logical strategy in the logical database; sorting the reverse strategy corresponding to each logical strategy in the reverse order of the logical order to obtain the reverse logical strategy of the target process node, and executing the reverse logical strategy based on the sub-diagnostic result of the target process node to generate the reverse input data of the target process node.

[0091] In this embodiment, the terminal identifies the logical order of each logical strategy of the target process node based on the diagnostic logic of the target process node, and queries the reverse strategy corresponding to each logical strategy in the logic database. Among them, the logical strategy is the judgment order of logical judgment. For example, to obtain the D result based on the A data, it is necessary to first judge the B type represented by the A data, and then judge the D result based on the B type and the C common sense. Therefore, the two processes from A to B and B, C to D are two logical strategies in place, and the order of A to B first, then B, C to D is the logical order of each logical strategy. Among them, the corresponding reverse strategy of each logical strategy, for example, the reverse strategy of A to B is B to A, and the reverse strategy of D may correspond to D to (one of C, E, F) and B. In the reverse process, as long as the process of D to C and B can be obtained, it is characterized that there is no abnormality in the logical strategy.

[0092] Finally, the terminal sorts the reverse strategies corresponding to each logic strategy in the reverse order of the logical order, obtains the reverse logic strategy of the target process node, and executes the reverse logic strategy based on the sub-diagnosis result of the target process node to generate the reverse input data of the target process node. Among them, there may be multiple reverse input data, that is, multiple input data are reversed, and the terminal selects the reverse input data with the smallest difference between the input data and the actual input data as the reverse input data of the reverse logic strategy corresponding to this logic.

[0093] Based on the above solution, by splitting the diagnostic logic into various logical strategies in a logical sequence, the comprehensiveness and accuracy of the reverse reasoning of the logical sequence are improved.

[0094] Optionally, based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, a target diagnosis process guidance strategy corresponding to each target diagnosis type, and a target diagnosis logic guidance strategy corresponding to each target diagnosis type are generated, including: classifying each case information according to each target diagnosis type to obtain a case group of each target diagnosis type, and for each case group, based on the abnormal diagnosis process of each case information in the case group, and the abnormal diagnosis content of each case information in the case group, counting the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group; in each abnormal diagnosis strategy, screening the target abnormal diagnosis strategy corresponding to each first abnormal frequency greater than the abnormal frequency threshold, and screening the target abnormal diagnosis strategy corresponding to each first abnormal frequency greater than the abnormal frequency threshold The target abnormality diagnosis logic corresponding to each second abnormal frequency of the rate threshold is obtained, and based on each target abnormality diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormality diagnosis strategy, a target diagnosis strategy corresponding to each target abnormality diagnosis strategy is generated through a strategy optimization algorithm; for each target abnormality diagnosis logic, based on each sub-diagnosis result corresponding to the target abnormality diagnosis logic, the abnormal cause of the target abnormality diagnosis logic is identified, and based on the abnormal cause of the target abnormality diagnosis logic, a target diagnosis logic corresponding to each target abnormality diagnosis logic is generated through a logic optimization algorithm; all target diagnosis strategies of the case group are used as the target diagnosis process guidance strategy of the target diagnosis type corresponding to the case group, and all target diagnosis logics of the case group are used as the target diagnosis logic guidance strategy corresponding to the target diagnosis type corresponding to the case group.

[0095] In this embodiment, the terminal classifies each case information according to each target diagnosis type to obtain a case group of each target diagnosis type, and for each case group, based on the abnormal diagnosis process of each case information in the case group and the abnormal diagnosis content of each case information in the case group, the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group are counted. Among them, since the full process content of the same diagnosis type is the same, the similarity of the diagnosis strategy and diagnosis logic of each process node of each case information is high, so that the recognition accuracy of the abnormal frequency of the abnormal diagnosis strategy and the abnormal frequency of the abnormal diagnosis logic is also high.

[0096] In each abnormal diagnosis strategy, the target abnormal diagnosis strategy corresponding to each first abnormal frequency greater than the abnormal frequency threshold preset in the terminal and the target abnormal diagnosis logic corresponding to each second abnormal frequency greater than the abnormal frequency threshold preset in the terminal are screened, and based on each target abnormal diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormal diagnosis strategy, a target diagnosis strategy corresponding to each target abnormal diagnosis strategy is generated through a strategy optimization algorithm. The strategy optimization algorithm is generated by converting the target sample diagnosis strategy into a program text, optimizing and adjusting the execution strategy of the program text, and obtaining the target diagnosis strategy. The strategy optimization algorithm can be an Actor-Critic algorithm.

[0097] For each target abnormal diagnosis logic, the terminal identifies the abnormal cause of the target abnormal diagnosis logic based on each sub-diagnosis result corresponding to the target abnormal diagnosis logic. Specifically, the terminal selects the diagnosis result with the highest frequency among the sub-diagnosis results, and uses the sub-diagnosis result as the abnormal cause of the target diagnosis logic.

[0098] Then, based on the abnormal cause of the target abnormal diagnosis logic, the terminal generates the target diagnosis logic corresponding to each target abnormal diagnosis logic through the logic optimization algorithm. Specifically, the terminal first includes the sub-diagnosis result corresponding to the abnormal cause in the blacklist of the logic optimization algorithm, so that the logic optimization algorithm uses the sub-diagnosis result in the iterative training process, and then uses the trained logic optimization algorithm to perform logic optimization on the target abnormal diagnosis logic to obtain the diagnosis logic. The logic optimization algorithm can be an Actor-Critic algorithm.

[0099] Finally, the terminal uses all the target diagnosis strategies of the case group as the target diagnosis process guidance strategies for the target diagnosis type corresponding to the case group, and uses all the target diagnosis logics of the case group as the target diagnosis logic guidance strategies corresponding to the target diagnosis type corresponding to the case group.

[0100] Based on the above scheme, combined with the abnormal diagnosis process and abnormal diagnosis content of case information of different target diagnosis types, the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type are comprehensively generated, so as to efficiently and accurately share and generate guidance for each abnormal diagnosis process and abnormal diagnosis logic, so as to provide efficient and convenient guidance strategies for staff when diagnosing emergency patients, avoiding abnormal problems that staff cannot execute according to process management specifications due to time urgency or special circumstances. And the guidance strategy can provide auxiliary guidance for the staff's diagnosis process in real time, thereby effectively reducing the probability of misdiagnosis and improving the prevention and control effect of misdiagnosis.

[0101] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0102] Based on the same inventive concept, the embodiment of the present application also provides a system for guiding emergency patients for missed diagnosis and misdiagnosis, which is used to implement the method for guiding emergency patients for missed diagnosis and misdiagnosis involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the system for guiding emergency patients for missed diagnosis and misdiagnosis provided below can be referred to the limitations of the method for guiding emergency patients for missed diagnosis and misdiagnosis above, and will not be repeated here.

[0103] Further references Figure 2 , as a response to the above Figure 1 The present application provides an embodiment of a misdiagnosis and missed diagnosis guidance system 200 for emergency hospitalized patients, the misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients comprising an acquisition module 210, an identification module 220 and a guidance module 230, wherein:

[0104] The acquisition module 210 is used to acquire the case information of each patient who has been admitted to the emergency department in history, and for each case information, identify the diagnosis process of the case information and the diagnosis information of the case information;

[0105] An identification module 220 is used to identify the abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information, and identify the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information through a diagnostic logic reverse inference strategy based on the diagnosis information corresponding to the case information;

[0106] Guidance module 230 is used to generate a target diagnosis process guidance strategy corresponding to each target diagnosis type and a target diagnosis logic guidance strategy corresponding to each target diagnosis type based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, and use the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type.

[0107] Optionally, the acquisition module 210 is specifically configured to:

[0108] Splitting the case information into diagnosis process record information and diagnosis content record information;

[0109] Identify the actual process content corresponding to each process node of the case diagnosis process record information and the diagnosis strategy corresponding to each process node, and use the actual process content corresponding to all process nodes and the diagnosis strategy corresponding to all process nodes as the diagnosis process of the case information;

[0110] Based on the diagnosis content record information, the sub-diagnosis results of the patient at each process node and the diagnosis logic of each process node are identified, and the sub-diagnosis results of all process nodes and the diagnosis logic of each process node are used as the diagnosis information of the case information.

[0111] Optionally, the identification module 220 is specifically configured to:

[0112] Based on the actual process content corresponding to each process node, query the sample diagnosis strategy corresponding to each process node in the diagnosis database, and extract each strategy feature of each diagnosis strategy and each sample strategy feature of the sample diagnosis strategy corresponding to each diagnosis strategy;

[0113] For each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy is calculated through a similarity recognition algorithm, and the diagnostic strategy corresponding to the similarity below the similarity threshold is used as an abnormal diagnostic strategy;

[0114] The process nodes corresponding to all abnormal diagnosis strategies are used as the abnormal diagnosis process of the case information.

[0115] Optionally, the identification module 220 is specifically configured to:

[0116] According to the order from front to back in the process sequence of each process node, the target process node is screened, and based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node, the reverse input data of the target process node is identified through the diagnostic logic reverse strategy;

[0117] Based on the actual input data of the target process node and the reverse input data of the target process node, the difference input data of the target process node is identified through a data difference information identification strategy, and the proportion of the data volume of the difference input data to the data volume of the actual input data is calculated;

[0118] In the case where the proportion value is lower than the preset proportion value, after the input data in the process sequence, the target process node is re-screened, and the diagnostic logic based on the target process node and the sub-diagnosis result of the process node are returned to be executed, and the reverse input data step of the process node is identified through the diagnostic logic reverse strategy, until the proportion value is not lower than the preset proportion value, the diagnostic logic of the target process node, the sub-diagnosis result of the target process node, the diagnostic logic of all process nodes after the target process node, and the sub-diagnosis results of all process nodes after the target process node are used as the abnormal diagnosis content of the case information;

[0119] Obtain the historical diagnosis logic of the target process node, the historical diagnosis logic of all process nodes after the target process node, and the actual input data of the target process node, generate the historical diagnosis result of the last process node in the process sequence, and use the diagnosis type corresponding to the historical diagnosis result as the target diagnosis type corresponding to the case information.

[0120] Optionally, the identification module 220 is specifically configured to:

[0121] Based on the diagnostic logic of the target process node, identify the logical order of each logic strategy of the target process node, and query the reverse strategy corresponding to each logic strategy in the logic database;

[0122] The reverse strategies corresponding to each logical strategy are sorted in the reverse order of the logical order to obtain the reverse logical strategy of the target process node, and the reverse logical strategy is executed based on the sub-diagnosis result of the target process node to generate the reverse input data of the target process node.

[0123] Optionally, the guidance module 230 is specifically used to:

[0124] Classify each of the case information according to each of the target diagnosis types to obtain case groups of each of the target diagnosis types, and for each case group, based on the abnormal diagnosis process of each of the case information in the case group and the abnormal diagnosis content of each of the case information in the case group, count the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group;

[0125] In each of the abnormal diagnosis strategies, the target abnormal diagnosis strategies corresponding to each first abnormal frequency greater than the abnormal frequency threshold and the target abnormal diagnosis logic corresponding to each second abnormal frequency greater than the abnormal frequency threshold are screened, and based on each target abnormal diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormal diagnosis strategy, a target diagnosis strategy corresponding to each target abnormal diagnosis strategy is generated through a strategy optimization algorithm;

[0126] For each target abnormality diagnosis logic, based on each sub-diagnosis result corresponding to the target abnormality diagnosis logic, identify the abnormality cause of the target abnormality diagnosis logic, and based on the abnormality cause of the target abnormality diagnosis logic, generate the target diagnosis logic corresponding to each target abnormality diagnosis logic through a logic optimization algorithm;

[0127] All target diagnosis strategies of the case group are used as target diagnosis process guidance strategies for the target diagnosis type corresponding to the case group, and all target diagnosis logics of the case group are used as target diagnosis logic guidance strategies corresponding to the target diagnosis type corresponding to the case group.

[0128] Each module in the above-mentioned misdiagnosis and missed diagnosis guidance system for emergency patients can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0129] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a misdiagnosis guidance method for emergency patients is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0130] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0131] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0133] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0134] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0136] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0137] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for guiding misdiagnosis and missed diagnosis of patients admitted to an emergency department, characterized in that: The method comprises: Obtaining case information of each patient who has been admitted to the emergency department in history, and for each case information, identifying the diagnosis process of the case information and the diagnosis information of the case information; Based on the diagnostic process corresponding to the case information, identify the abnormal diagnostic process of the case information, and based on the diagnostic information corresponding to the case information, identify the abnormal diagnostic content of the case information and the target diagnostic type corresponding to the case information through a diagnostic logic reverse inference strategy; Based on the abnormal diagnosis process of each of the case information, the abnormal diagnosis content of each of the case information, and the target diagnosis type corresponding to each of the case information, a target diagnosis process guidance strategy corresponding to each of the target diagnosis types and a target diagnosis logic guidance strategy corresponding to each of the target diagnosis types are generated, and the target diagnosis process guidance strategy corresponding to each of the target diagnosis types and the target diagnosis logic guidance strategy corresponding to each of the target diagnosis types are used as the target diagnosis guidance strategy for each of the target diagnosis types.

2. The method according to claim 1, characterized in that The diagnostic process for identifying the case information and the diagnostic information of the case information include: Splitting the case information into diagnosis process record information and diagnosis content record information; Identify the actual process content corresponding to each process node of the case diagnosis process record information and the diagnosis strategy corresponding to each process node, and use the actual process content corresponding to all process nodes and the diagnosis strategy corresponding to all process nodes as the diagnosis process of the case information; Based on the diagnosis content record information, the sub-diagnosis results of the patient at each process node and the diagnosis logic of each process node are identified, and the sub-diagnosis results of all process nodes and the diagnosis logic of each process node are used as the diagnosis information of the case information.

3. The method according to claim 2, characterized in that The step of identifying an abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information includes: Based on the actual process content corresponding to each process node, query the sample diagnosis strategy corresponding to each process node in the diagnosis database, and extract each strategy feature of each diagnosis strategy and each sample strategy feature of the sample diagnosis strategy corresponding to each diagnosis strategy; For each diagnostic strategy, based on each diagnostic feature of the diagnostic strategy and each sample strategy feature of the sample diagnostic strategy corresponding to the diagnostic strategy, the similarity between the diagnostic strategy and the sample diagnostic strategy corresponding to the diagnostic strategy is calculated through a similarity recognition algorithm, and the diagnostic strategy corresponding to the similarity below the similarity threshold is used as an abnormal diagnostic strategy; The process nodes corresponding to all abnormal diagnosis strategies are used as the abnormal diagnosis process of the case information.

4. The method according to claim 2, characterized in that: The method of identifying the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information based on the diagnosis information corresponding to the case information through a diagnostic logic reverse inference strategy includes: According to the order from front to back in the process sequence of each process node, the target process node is screened, and based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node, the reverse input data of the target process node is identified through the diagnostic logic reverse strategy; Based on the actual input data of the target process node and the reverse input data of the target process node, the difference input data of the target process node is identified through a data difference information identification strategy, and the proportion of the data volume of the difference input data to the data volume of the actual input data is calculated; In the case where the proportion value is lower than the preset proportion value, after the input data in the process sequence, the target process node is re-screened, and the diagnostic logic based on the target process node and the sub-diagnosis result of the process node are returned to be executed, and the reverse input data step of the process node is identified through the diagnostic logic reverse strategy, until the proportion value is not lower than the preset proportion value, the diagnostic logic of the target process node, the sub-diagnosis result of the target process node, the diagnostic logic of all process nodes after the target process node, and the sub-diagnosis results of all process nodes after the target process node are used as the abnormal diagnosis content of the case information; Obtain the historical diagnosis logic of the target process node, the historical diagnosis logic of all process nodes after the target process node, and the actual input data of the target process node, generate the historical diagnosis result of the last process node in the process sequence, and use the diagnosis type corresponding to the historical diagnosis result as the target diagnosis type corresponding to the case information.

5. The method according to claim 4, characterized in that The step of identifying the reverse input data of the process node based on the diagnostic logic of the target process node and the sub-diagnosis result of the target process node through the diagnostic logic reverse strategy includes: Based on the diagnostic logic of the target process node, identify the logical order of each logic strategy of the target process node, and query the reverse strategy corresponding to each logic strategy in the logic database; The reverse strategies corresponding to each logical strategy are sorted in the reverse order of the logical order to obtain the reverse logical strategy of the target process node, and the reverse logical strategy is executed based on the sub-diagnosis result of the target process node to generate the reverse input data of the target process node.

6. The method according to claim 4, characterized in that The abnormal diagnosis process based on each of the case information, the abnormal diagnosis content of each of the case information, and the target diagnosis type corresponding to each of the case information, generates a target diagnosis process guidance strategy corresponding to each of the target diagnosis types, and a target diagnosis logic guidance strategy corresponding to each of the target diagnosis types, including: Classify each of the case information according to each of the target diagnosis types to obtain case groups of each of the target diagnosis types, and for each case group, based on the abnormal diagnosis process of each of the case information in the case group and the abnormal diagnosis content of each of the case information in the case group, count the first abnormal frequency of each abnormal diagnosis strategy in the case group and the second abnormal frequency of each abnormal diagnosis logic in the case group; In each of the abnormal diagnosis strategies, the target abnormal diagnosis strategies corresponding to each first abnormal frequency greater than the abnormal frequency threshold and the target abnormal diagnosis logic corresponding to each second abnormal frequency greater than the abnormal frequency threshold are screened, and based on each target abnormal diagnosis strategy and the target sample diagnosis strategy corresponding to each target abnormal diagnosis strategy, a target diagnosis strategy corresponding to each target abnormal diagnosis strategy is generated through a strategy optimization algorithm; For each target abnormality diagnosis logic, based on each sub-diagnosis result corresponding to the target abnormality diagnosis logic, identify the abnormality cause of the target abnormality diagnosis logic, and based on the abnormality cause of the target abnormality diagnosis logic, generate the target diagnosis logic corresponding to each target abnormality diagnosis logic through a logic optimization algorithm; All target diagnosis strategies of the case group are used as target diagnosis process guidance strategies for the target diagnosis type corresponding to the case group, and all target diagnosis logics of the case group are used as target diagnosis logic guidance strategies corresponding to the target diagnosis type corresponding to the case group.

7. A misdiagnosis and missed diagnosis guidance system for emergency hospitalized patients, characterized in that: The system comprises: An acquisition module is used to acquire the case information of each patient who has been admitted to the emergency department in history, and for each case information, identify the diagnosis process of the case information and the diagnosis information of the case information; an identification module, for identifying an abnormal diagnosis process of the case information based on the diagnosis process corresponding to the case information, and identifying the abnormal diagnosis content of the case information and the target diagnosis type corresponding to the case information through a diagnostic logic reverse inference strategy based on the diagnosis information corresponding to the case information; A guidance module is used to generate a target diagnosis process guidance strategy corresponding to each target diagnosis type and a target diagnosis logic guidance strategy corresponding to each target diagnosis type based on the abnormal diagnosis process of each case information, the abnormal diagnosis content of each case information, and the target diagnosis type corresponding to each case information, and use the target diagnosis process guidance strategy corresponding to each target diagnosis type and the target diagnosis logic guidance strategy corresponding to each target diagnosis type as the target diagnosis guidance strategy for each target diagnosis type.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images