Data model establishment method and device, and clinical auxiliary decision method and device

Abstract

The present disclosure relates to a data model establishing method and device, and a clinical auxiliary decision method and device. The data model establishing method comprises: field disassembling historical data according to different disease categories; structured processing is performed according to the fields obtained by disassembling to form a structured output rule; and a disease data model is established according to the structured output rule combined with clinical data. The present disclosure also relates to a data model establishing device, an electronic device and a computer readable medium, and a clinical auxiliary decision method, device, electronic device and computer readable medium based on the data model establishing method. The structured output rule is generated by structured processing of diseases, and the clinical data is saved in a relational structure in a database according to the rule to form a data model, so that the clinical data can be effectively utilized, the interconnection and intercommunication between data can be realized, and the research conversion rate can be improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of cloud storage, and in particular, to a method and device for establishing a data model, and a method and device for clinical auxiliary decision-making. BACKGROUND

[0002] At present, the medical diagnosis idea at home and abroad is to analyze and judge through a group of clinical data (including the results of inquiry, physical examination, laboratory examination, physical examination, etc.) by the self-cognition and clinical experience of doctors, so as to give a diagnosis result. However, this diagnosis process is often easily affected by subjective factors, and its accuracy degree is closely related to the overall quality level of medical personnel, and the population base in China is large, and the medical conditions in some grass-roots or remote areas are relatively backward, and there is a relative shortage of medical practitioners with rich experience, so it is difficult to ensure that all patients can obtain high-quality diagnosis and treatment.

[0003] With the popularity of hospital electronic medical record systems, a huge medical information database can be formed based on one electronic medical record after another, and the stored data also grows exponentially. However, these data are mainly used to record patient treatment information, which contains a large amount of natural language text that machines cannot identify, and the reading speed and quantity of humans are limited, so it is difficult to analyze valuable information in hospital diagnosis and treatment data from a macro perspective. Doctors can only spend a lot of time screening one case after another by eye, which is slow and inefficient, thereby hindering the development of clinical research.

[0004] Therefore, a new method and device for establishing a data model, an electronic device and a computer readable medium are needed.

[0005] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, so it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0006] Therefore, the present disclosure provides a method and device for establishing a data model, an electronic device and a computer readable medium, which can solve the problem of slow speed and low efficiency in manual data analysis and modeling process.

[0007] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0008] According to an aspect of the present disclosure, a method for establishing a data model is provided, which comprises: field disassembling historical data according to different disease categories; performing structured processing according to the disassembled fields to form a structured output rule; and establishing a disease data model according to the structured output rule combined with clinical data.

[0009] In an example embodiment of the present disclosure, the historical data at least includes medical books, medical literatures, disease guidelines and clinical experiments.

[0010] In an example embodiment of the present disclosure, the structured processing according to the fields obtained by the disassembling includes: obtaining a first field for a field in the fields obtained by the disassembling which directly corresponds to a corresponding value range through the same field name; extracting a second field from the natural language text content; performing a logical operation according to the first field and the second field to obtain a third field; and extracting a keyword according to the first field, the second field and the third field to generate a term dictionary.

[0011] In an example embodiment of the present disclosure, the extraction of the second field from the natural language text content includes: constructing a medical term system with a tree structure in combination with the hierarchical relationship of the terms; and extracting the second field from the natural language text content in combination with the medical term system.

[0012] In an example embodiment of the present disclosure, the structured processing according to the fields obtained by the disassembling forms a structured output rule, which includes: performing medical logical relationship analysis according to the term dictionary to obtain the structured output rule.

[0013] In an example embodiment of the present disclosure, the clinical data includes basic information of a patient, disease general data and disease non-general data, and the disease data model is established according to the structured output rule in combination with the clinical data, which includes: extracting and integrating the basic information of the patient to obtain a basic information field set; extracting and integrating the disease general data to obtain a general field set; extracting and integrating the disease non-general data to obtain a non-general field set; and summarizing the basic information field set, the general field set and the non-general field set according to the structured output rule to obtain the disease data model.

[0014] According to an aspect of the present disclosure, a data model establishment device is also provided, which includes: a field disassembling module for disassembling fields according to different disease categories for historical data; a structured module for performing structured processing according to the fields obtained by the disassembling to form a structured output rule; and a model construction module for establishing a disease data model according to the structured output rule in combination with clinical data.

[0015] In an example embodiment of the present disclosure, the structured module comprises: a field hierarchical module, configured to obtain first-level fields by directly corresponding respective value ranges of fields with the same field name in the fields obtained by disassembling, obtain second-level fields by extracting from the natural language text content, and obtain third-level fields by logical operation according to the first-level fields and the second-level fields; and a dictionary generation module, configured to extract keywords to generate a term dictionary according to the first-level fields, the second-level fields and the third-level fields.

[0016] In an example embodiment of the present disclosure, the model construction module comprises: a patient demographic information module, configured to extract and integrate basic information of a patient to obtain a basic information field set; a disease general layer module, configured to extract and integrate disease general data to obtain a general field set; a disease non-general layer module, configured to extract and integrate disease non-general data to obtain a non-general field set; and a summary module, configured to summarize the basic information field set, the general field set and the non-general field set according to the structured output rule to obtain the disease data model.

[0017] According to an aspect of the present disclosure, a clinical auxiliary decision method is also provided, which comprises: field disassembling historical data according to different disease categories; structured processing of the fields obtained by disassembling to form a structured output rule; establishing a disease data model in combination with clinical data according to the structured output rule; and obtaining a decision result in combination with a clinical test result and the disease data model.

[0018] According to an aspect of the present disclosure, a clinical auxiliary decision device is also provided, which comprises: a field disassembling module, configured to disassemble fields of historical data according to different disease categories; a structured module, configured to structured process the fields obtained by disassembling to form a structured output rule; a model construction module, configured to establish a disease data model in combination with clinical data according to the structured output rule; and a decision module, configured to obtain a decision result in combination with a clinical test result and the disease data model.

[0019] According to an aspect of the present disclosure, an electronic device is provided, which comprises: one or more processors; a storage device configured to store one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned data model establishment method and clinical auxiliary decision method.

[0020] According to an aspect of the present disclosure, a computer readable medium is provided, which stores a computer program, and the program is executed by a processor to implement the above-mentioned data model establishment method and clinical auxiliary decision method.

[0021] According to the data modeling method, apparatus, electronic device, and computer-readable medium disclosed herein, structured output rules are generated by structuring diseases, and then clinical data is saved in a database in a relational structure according to these rules to form a data model. This can effectively utilize clinical data, realize the interconnection between data, and improve the scientific research translation rate.

[0022] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this disclosure. Attached Figure Description

[0023] The above and other objects, features, and advantages of this disclosure will become more apparent from the detailed description of exemplary embodiments with reference to the accompanying drawings. The drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0024] Figure 1 This is a system block diagram illustrating a method and apparatus for establishing a data model according to an exemplary embodiment.

[0025] Figure 2 This is a flowchart illustrating a method for establishing a data model according to an exemplary embodiment.

[0026] Figure 3 This is a schematic diagram illustrating the proportion of historical data sources in step S202 according to an exemplary embodiment.

[0027] Figure 4 This is a flowchart illustrating the structuring process based on the fields obtained from the decomposition in step S204, according to an exemplary embodiment.

[0028] Figure 5 This is a flowchart illustrating step S206 of establishing a disease data model based on the structured output rules and clinical data, according to an exemplary embodiment.

[0029] Figure 6 This is a block diagram illustrating a data modeling apparatus according to another exemplary embodiment.

[0030] Figure 7 This is illustrated according to an exemplary embodiment. Figure 6 Block diagram of the structured module 602.

[0031] Figure 8 This is illustrated according to an exemplary embodiment. Figure 6 Block diagram of the model building module 603.

[0032] Figure 9 This is a flowchart illustrating another method for building a data model according to an exemplary embodiment.

[0033] Figure 10 is a block diagram of another apparatus for establishing a data model according to another exemplary embodiment.

[0034] Figure 11 is a block diagram of an electronic device according to an exemplary embodiment.

[0035] Figure 12 is a schematic diagram of a computer-readable storage medium according to an exemplary embodiment. DETAILED DESCRIPTION

[0036] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the specification.

[0037] Moreover, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the techniques described herein can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, devices, implementations, and operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.

[0038] The block diagrams in the accompanying drawings are only block diagrams and do not necessarily correspond to physical entities. That is, these functional entities can be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0039] The flow diagrams in the drawings are merely illustrative of example embodiments and do not necessarily correspond to all possible series of operations or steps. For example, some operations / steps can be split into multiple operations / steps, and some operations / steps can be combined or partially combined, so the actual order of execution can be changed according to actual situations.

[0040] It should be understood that although the terms first, second, third, etc. can be used herein to describe various components, these components should not be limited by these terms. These terms are used only to distinguish one component from another. Thus, a first component discussed below could be termed a second component without departing from the teachings of the present disclosure concept. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0041] Those skilled in the art can understand that the modules or flows in the drawings are not necessarily required for implementing the present disclosure, and therefore cannot be used to limit the protection scope of the present disclosure.

[0042] Figure 1 is a system block diagram of a method and apparatus for establishing a data model according to an exemplary embodiment.

[0043] As shown in Figure 1 , the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0044] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, search applications, instant messaging tools, etc.

[0045] The terminal devices 101, 102, 103 can be various electronic devices with display screens and support for web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc.

[0046] The server 105 can be a server that provides various services, such as a background management server that supports the establishment of a data model request submitted by a user using the terminal device 101, 102, 103. The background management server can analyze and process the received data model establishment request, etc., and feed back the processing result to the terminal device.

[0047] The server 105 may, for example, obtain the to-be-processed data transmitted by the user using the terminal device 101, 102, 103; the server 105 may, for example, process the to-be-processed data.

[0048] Server 105 can be a single physical server, or it can be composed of multiple servers. It should be noted that the data model establishment method provided in this embodiment can be executed by server 105, and correspondingly, the data model establishment device can be set in server 105.

[0049] Figure 2 This is a flowchart illustrating a method for building a data model according to an exemplary embodiment. The method for building a data model includes at least steps S202 to S206, which is used to construct a disease data model using historical data combined with clinical data.

[0050] like Figure 2 As shown, in step S202, the historical data is decomposed into fields according to different disease categories.

[0051] like Figure 2 As shown, in step S204, the fields obtained from the decomposition are processed into a structured output rule.

[0052] like Figure 2 As shown, in step S206, a disease data model is established based on the structured output rules and clinical data.

[0053] The following combination Figure 2 The flowchart shown below provides a detailed introduction to the data model establishment method provided in this disclosure, as follows:

[0054] In step S202, the historical data is decomposed into fields according to different disease categories.

[0055] In one exemplary embodiment of this disclosure, the historical data includes at least: medical books, medical literature, disease guidelines, and clinical trials. Figure 3 A diagram illustrating the proportion of historical data sources in this step is shown, such as... Figure 3 As shown, at the current stage, medical books and medical literature still account for a large proportion. Fields can be decomposed based on these existing medical data. However, in this embodiment, fields will be decomposed according to the classification of different diseases.

[0056] Based on the extracted field attributes, the fields can be divided into: general disease fields, general tumor fields, special disease-specific fields, and customized layer fields. The fields are decomposed according to medical literature, books, and disease guidelines, and divided according to attributes. Based on the preset structured information extraction model, the extracted medical information is stored in a relational structure.

[0057] The classification of field attributes is described below:

[0058] Disease general field: all fields have no disease direction (non-directional does not mean to point to any disease), any disease can have this field, and the definition of the field does not change, such as the patient's basic information, such as birth date, hometown, ABO blood type, etc. Positive symptom name, negative symptom name, etc. in the history of the disease. However, for example, "disease onset age", although all diseases have an onset age, but it is not the same for different diseases. For "colorectal cancer", the corresponding onset age is the onset age of colorectal cancer. For "gastric cancer", the corresponding onset age is the onset age of gastric cancer, so the definition / meaning / condition of the "onset age" field changes with different diseases, and is not suitable as a disease general field.

[0059] Tumor general field: refers to all fields related to the term tumor, but has no direction to any tumor. For example, the location of the tumor in the diagnosis, clinical stage, TNM stage, etc. Metastatic site, whether it is recurrent, etc. Special disease field: refers to a field that is only for this disease and does not face other diseases in the same layer. For example, for gastric cancer, Lauren typing and Gleason score, CML staging for leukemia, NYHA classification for heart failure, etc. are its unique fields, which belong to disease-specific fields.

[0060] Custom layer field: refers to adding a custom layer when the above field classification cannot meet certain customized needs, which needs to be set according to specific needs.

[0061] In an exemplary embodiment of the present disclosure, about 20 diseases are initially analyzed and processed, the logic is selected as the disease incidence and drug research needs, and it involves tumor, infectious disease, metabolic disease and other fields.

[0062] During the field disassembly process, medical information analysis needs to be performed according to historical data. The medical information analysis uses qualitative and quantitative research methods as means, and through a series of processing processes such as collection, arrangement, identification, evaluation, analysis, and synthesis of literature information and non-literature information, the fields are classified, the form of related information combination is formed, the core disease model that can adapt to the disease is constructed, and the form, field, value range, value range attribute, data source and the like are included. The paper takes part of the data of CNKI and CMCI (China biomedical journal citation database) as the research object, takes the quantitative method in the medical information analysis method as the means, takes bibliometrics as the basic theoretical support, starts from the aspects of literature growth, literature regional distribution, literature journal distribution, keyword analysis, discipline field distribution and the like, macroscopically grasps the application status of the medical information analysis method at present, grasps the development trend, and thus the information most related to the disease is disassembled. The medical books are based on more than thirty medical authoritative books such as internal medicine, practical surgery, and clinical oncology, and the key information is excavated in etiology, diagnosis, treatment, and examination according to the thought of the diagnosis and treatment process of the disease. In order to enable the disease data model finally obtained in the embodiment to support drug research and scientific research, part of the fields can also be derived from the clinical experiment of the drug and the disease diagnosis and treatment guideline.

[0063] In step S204, the fields disassembled are subjected to structured processing to form a structured output rule.

[0064] This step is mainly to perform structured processing on the natural language in the medical data (in the form of fields) and to establish a related medical terminology system. First, the included patient data is sorted according to the diagnosis name, and is distinguished according to the code of different diseases; second, the disassembled fields are graded, and are divided into three levels. In the process of establishing the related field dictionary, the attributes of the words are classified, the universality and reusability of the vocabulary are increased, and the corresponding terminology system is established.

[0065] Figure 4 A flowchart of the structured processing of the fields disassembled in step S204 is shown, including the following steps:

[0066] As shown in Figure 4 In step S402, the fields disassembled are subjected to structured processing to form a structured output rule.

[0067] As shown in Figure 4As shown, in step S404, secondary fields are extracted from the natural language text content. This step can be performed as follows: a hierarchical medical terminology system with a tree structure is constructed by combining the hierarchical relationships of the terms; secondary fields, i.e., L2 fields, are extracted from the natural language text content based on the medical terminology system. L2 fields can be extracted from information such as examination findings, pathological findings, and conclusions, for example, blood type B.

[0068] like Figure 4 As shown, in step S406, a third-level field, namely the L3 field, is obtained by performing logical operations on the first-level field and the second-level field. This field is a logically complex field type, requiring implementation based on the information from the L1 and L2 fields. For example, BMI can be an L3 field, and the calculation of BMI depends on information related to weight and height. For instance, based on a weight of 75KG and a height of 180CM, a BMI of ≈23.15 is calculated.

[0069] The L1 field does not require structured processing, while the L2 and L3 fields do require structured processing.

[0070] like Figure 4 As shown, in step S408, keywords are extracted based on the first-level field, the second-level field, and the third-level field to generate a terminology dictionary.

[0071] Specifically, this step can be as follows: Perform medical logical relationship analysis based on the terminology dictionary to obtain the structured output rules. Since field structuring first requires analyzing the sampled data, extracting keywords to build a terminology dictionary supporting the field, analyzing the medical logical relationships in the data, and finally forming the corresponding structured output rules.

[0072] In an exemplary embodiment of the present disclosure, the hierarchical relationship of the medical terminology system is referenced to SNOMED CT, and the system is constructed by referring to MESH, ICD-9, ICD-10 and other terminology standards. Nineteen concepts such as body structure, event and clinical finding are taken as top-level nodes, including: explicit background, body structure, clinical finding, environment or geographical location, event, observable entity, organism, drug / biologic product, physical force, physical object, operation, limit value, record (artificial), YDY-CT model component, social context, special concept, specimen, staging and scale, and substance. Each top-level axis is further classified and refined to form a tree structure of a multi-level subsystem. The tree structure is usually a structure of at least two levels. Taking the body structure as the top-level node, the corresponding tree structure can include three-level nodes. First, the top-level node is the body structure. Second, the top-level node includes nine second-level nodes of respiratory system, digestive system, locomotor system, urinary system, reproductive system, endocrine system, immune system, nervous system and circulatory system. Finally, taking the respiratory system as an example, the respiratory system includes five third-level nodes of nose, pharynx, larynx, trachea and various levels of bronchus. Other top-level nodes also have similar tree structures, which are not listed one by one here.

[0073] The tree structure can be combed according to the needs of clinical practice and guided by the actual diagnosis and treatment process. The principle is to maximize the convenience of medical data application. The two main concepts are finding / disease and operation, and most medical vocabulary is included. The clinical data word mining is mainly used for accumulation. Different concepts can be associated through the tree structure of the upper and lower levels. The parallel attributes such as the same word and the synonym are supported to associate the two concepts in different ways to form a large number of semantic descriptions, so that the clinical information and application have great flexibility.

[0074] In step S206, a disease data model is established according to the structured output rule combined with the clinical data.

[0075] This step starts from the dimension of each disease. For each disease, all medical information involved in the clinical diagnosis and treatment of the disease is summarized from the latest diagnosis and treatment guidelines published by authoritative medical organizations at home and abroad, medical professional textbooks and high-impact research papers at home and abroad. The standard field name corresponding to each information is set. On the basis of the field set, it is divided into three parts of patient demographic information, disease general layer and disease non-general layer. Finally, a complete disease data model is summarized.

[0076] In an exemplary embodiment of the present disclosure, the clinical data includes basic information of the patient, disease general data and disease non-general data.

[0077] Figure 5 A flow chart showing the process of establishing a disease data model according to the structured output rules combined with clinical data in step S206 includes the following steps:

[0078] As shown in the step S502, the basic information of the patient is extracted and integrated to obtain a basic information field set. This step mainly simulates the hospital medical record system to summarize the basic information of the patients who come to the hospital for treatment, such as patient name, gender, age, etc. Figure 5

[0079] As shown in the step S504, the disease general data is extracted and integrated to obtain a general field set. This step is from the disease dimension, and the field information set suitable for all diseases is summarized. It includes chief complaint, history of present illness, family history, past history, marital history, personal history, physical examination, and special examination. According to each part of the content, the corresponding extraction information field set is summarized, such as the positive test examination name, positive symptoms and signs, and duration extracted from the chief complaint. Figure 5

[0080] As shown in the step S506, the fields of the disease non-general data are extracted and integrated to obtain a non-general field set. Figure 5 Due to the great difference in diagnosis and treatment of different diseases, this step summarizes the field set of information extraction according to the diagnosis and treatment characteristics of each disease.

[0081] This step involves the diagnosis information, test information, examination information, pathological analysis information, surgical information, and non-surgical treatment information of the disease. The diagnosis information is mainly the medical information extracted from the diagnosis information of the disease, such as diagnosis name, clinical type, and disease severity. The test information is the test item required for the clinical diagnosis and treatment of the disease, and the field name includes the names of various test sub-items. The examination information is the examination item required for the clinical diagnosis and treatment of the disease, such as X-ray, B-ultrasound, CT, etc. According to different examination items and examination findings and conclusion texts, the field set strongly related to the disease is summarized and extracted. The pathological analysis information refers to the pathological information related to the disease extracted from the pathological report content, mainly including pathological information, immunohistochemical information, and gene detection information. The surgical information refers to the information related to the surgical process of the disease extracted from the surgical related content, such as surgical site, surgical approach, and surgical procedure. The non-surgical treatment information refers to the extraction of all non-surgical treatment information of the disease, including drug treatment of ordinary diseases, chemotherapy, radiotherapy, and interventional therapy of tumors, etc. According to different treatments, the corresponding information extraction fields are set.

[0082]

[0083] Figure 5 ​​​​As shown, in step S508, the basic information field set, the general field set and the non-general field set are summarized according to the structured output rule to obtain the disease data model.

[0084] According to the data model establishment method of the present disclosure, the structured output rule is generated by structuring the disease, and the clinical data is saved in the database in a relational structure according to the rule, forming the disease data model, which can effectively utilize the clinical data, realize the interconnection and intercommunication between data, and improve the research conversion rate. On the other hand, the method effectively stores different disease data and extracts key fields for structured processing, realizing the structured associated storage of data; the present disclosure can further make full use of medical data and maximize the value of medical data.

[0085] It should be clearly understood that the present disclosure describes how to form and use specific examples, but the principles of the present disclosure are not limited to any details of these examples. On the contrary, based on the teachings of the disclosure disclosed in the present disclosure, these principles can be applied to many other embodiments.

[0086] Figure 6 is a block diagram of a data model establishment device according to an exemplary embodiment. The data model establishment device 600 comprises a field disintegration module 601, a structured module 602 and a model construction module 603.

[0087] The field disintegration module 601 is configured to disintegrate the historical data according to the classification of different diseases; the structured module 602 is configured to perform structured processing according to the disintegrated fields to form a structured output rule; and the model construction module 603 is configured to establish a disease data model according to the structured output rule in combination with clinical data.

[0088] In an exemplary embodiment of the present disclosure, Figure 7 The block diagram of the structured module 602 is shown as follows: Figure 7 As shown, the structured module 602 comprises a field classification module 6021, which is configured to obtain a first-level field from the disintegrated fields that directly correspond to a corresponding value range through the same field name, extract a second-level field from natural language text content, and perform logical operation according to the first-level field and the second-level field to obtain a third-level field; and a dictionary generation module 6022, which is configured to extract keywords to generate a term dictionary according to the first-level field, the second-level field and the third-level field.

[0089] In an exemplary embodiment of the present disclosure, Figure 8 The block diagram of the model construction module 603 is shown as follows: Figure 8As shown, including: patient demographic information module 6031 for extracting and integrating the basic information of the patient to obtain a basic information field set; disease general layer module 6032 for extracting and integrating disease general data to obtain a general field set; disease non-general layer module 6033 for extracting and integrating disease non-general data fields to obtain a non-general field set; summary module 6034 for summarizing the basic information field set, the general field set and the non-general field set according to the structured output rule to obtain the disease data model.

[0090] In an exemplary embodiment of the present disclosure, the disease non-general layer module 6033 further includes a diagnosis module, a test module, an examination module, a pathology information module, a surgery information module, and a treatment module.

[0091] Diagnosis module: mainly extracts medical information from the diagnosis information of the disease, such as diagnosis name, clinical classification, and disease severity.

[0092] Test module: is a test item required for the disease in clinical diagnosis and treatment, and the field name includes various test sub-item names.

[0093] Examination module: is an examination item required for the disease in clinical diagnosis and treatment, such as X-ray, B-ultrasound, CT, etc. According to different examination items and examination findings and conclusion texts, the field set strongly related to the disease is summarized and extracted.

[0094] Pathology module: extracts the pathology information related to the disease according to the pathology report content, mainly including pathology information, immunohistochemical information and gene detection information.

[0095] Surgery module: extracts information related to the surgery process of the disease according to the surgery related content, such as surgical site, surgical approach, surgical procedure, etc.

[0096] Non-surgical treatment module: summarizes all non-surgical treatment information extraction fields of the disease, including drug treatment of common diseases, chemotherapy, radiotherapy, interventional therapy of tumors, etc., and sets corresponding information extraction fields according to different treatments.

[0097] Each of the above-mentioned diagnosis module, test module, examination module, pathological information module, surgery information module, and treatment module is composed of a main module, a sub-module, a data element, a data type, a value range, and a data source, and is displayed in a tree structure. Each main module can be classified by a filtering condition, thereby containing multiple sub-modules. For example, the main module is "examination" (i.e., an examination main module), and the corresponding sub-modules are "X-ray examination" and "ultrasound examination" by different filtering conditions "X-ray examination" and "ultrasound examination", i.e., an X-ray examination (X) sub-module and an ultrasound examination (US) sub-module. The data element corresponds to a disassembled medical field. The field set can be divided into three levels, i.e., L1, L2, and L3 fields, which are specifically introduced as follows:

[0098] L1 field: is a field type directly corresponding to a corresponding value range by the same field name. It is mainly directly mapped by a standard vocabulary, such as the values and units corresponding to each specific sub-item name in the test. For diversified value ranges and unit types, subsequent normalization processing can be performed. L2 field: is a field type extracted from complex natural language text content by structured processing technology, such as information extraction in each examination, pathological findings, and conclusions. It is mainly realized by relying on a rule base established by a large amount of data annotation and analysis of a medical terminology system. L3 field: belongs to a logically complex field type. It is a field type realized on the basis of L1 and L2 field information, such as the calculation of BMI depending on the related information of weight and height.

[0099] According to the data model establishment device of the present disclosure, a structured output rule is generated by structuring the disease, and the clinical data is saved in a relational structure in the database according to the rule, forming a disease data model, which can effectively utilize the clinical data, realize the interconnection and intercommunication of the data, and improve the research conversion rate. On the other hand, the method effectively stores different disease data and extracts key fields for structured processing, realizing the structured association storage of the data.

[0100] Figure 9 is a flowchart of a clinical auxiliary decision-making method according to another exemplary embodiment. The data model establishment method at least includes steps S902 to S908, which are further applied to the model on the basis of the construction of the disease data model.

[0101] As shown in Figure 9 , in step S902, the historical data is classified according to different disease types for field disassembly.

[0102] As shown in Figure 9 , in step S904, the fields obtained by disassembly are structured to form a structured output rule.

[0103] like Figure 9 As shown, in step S906, a disease data model is established based on the structured output rules and clinical data.

[0104] like Figure 9 As shown, in step S908, a decision result is obtained by combining the clinical test results and the disease data model.

[0105] The specific descriptions of steps S902 to S906 are the same as those for steps S202 to S206 in the above embodiments, and will not be repeated here.

[0106] In one exemplary embodiment of this disclosure, in step S908, the clinical test results for patients can be input into a disease data model with structured output rules, thereby generating a decision result corresponding to the test results.

[0107] For example, this method is of great significance for disease diagnosis and treatment, treatment plan determination, epidemic prediction, medical research, and drug side effect analysis. Specifically, it promotes the monitoring of clinical diagnosis and treatment standards, establishes a clinical auxiliary decision-making system, and transforms the results of big data research into valuable medical knowledge. For instance, when a patient's test result shows high potassium levels, the machine provides a decision recommendation after receiving the test result, such as recommending 10ml of 10% calcium gluconate. The doctor can confirm with one click and notify the nursing station to prepare the medication. This not only improves the automation process of medical care but also reduces the incidence of unexpected risks. It is of great significance for the research and exploration of medical diseases and also plays a certain role in promoting the formation of unified industry standards.

[0108] The clinical decision support method disclosed herein can improve the conversion rate of historical data in medical diagnosis, which can not only improve the process of medical automation, but also reduce the incidence of unexpected risks. It is of great significance for the research and exploration of medical diseases, and also plays a certain role in promoting the formation of unified industry standards.

[0109] It should be clearly understood that this disclosure describes how specific examples are formed and used, but the principles of this disclosure are not limited to any details of these examples. Rather, based on the teachings of this disclosure, these principles can be applied to many other embodiments.

[0110] Correspondingly, Figure 10 This is a block diagram illustrating a clinical decision support device according to an exemplary embodiment. The clinical decision support device 1000 includes: a field decomposition module 1001, a structuring module 1002, a model building module 1003, and a decision module 1004.

[0111] The field disassembling module 1001 is configured to disassemble fields of historical data according to different disease categories; the structured module 1002 is configured to perform structured processing according to the disassembled fields to form a structured output rule; the model construction module 1003 is configured to establish a disease data model according to the structured output rule and clinical data; and the decision module 1004 is configured to combine the clinical test results and the disease data model.

[0112] The field disassembling module 1001, the structured module 1002, and the model construction module 1003 are described above with reference to the field disassembling module 601, the structured module 602, and the model construction module 603, and thus will not be described herein.

[0113] The clinical auxiliary decision device according to the present disclosure can improve the application conversion rate of historical data in medical diagnosis, improve the medical automation process, reduce the incidence of unexpected risks, and is of great significance to the research and exploration of medical diseases, and can also promote the formation of unified industry standards.

[0114] Those skilled in the art can understand that all or part of the steps of the above embodiments are implemented as a computer program executed by a CPU. When the computer program is executed by the CPU, the above functions defined by the above method provided by the present disclosure are executed. The program can be stored in a computer readable storage medium, which can be a read-only memory, a magnetic disk, an optical disk, or the like.

[0115] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not for limiting purposes. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of the processes. In addition, it is also easy to understand that the processes can be executed synchronously or asynchronously in multiple modules, for example.

[0116] Figure 11 is a block diagram of an electronic device according to an exemplary embodiment.

[0117] The electronic device 200 according to this embodiment of the present disclosure will be described below with reference to Figure 11 Figure 11 The electronic device 200 shown is merely an example, and should not limit the functions and use range of the embodiments of the present disclosure.

[0118] As shown in Figure 11 , the electronic device 200 is in the form of a general computing device. The components of the electronic device 200 can include, but are not limited to, at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components including the storage unit 220 and the processing unit 210, a display unit 240, and the like.​

[0119] The storage unit stores program codes which can be executed by the processing unit 210, so that the processing unit 210 performs the steps described in the above electronic prescription flow processing method part of the present specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 210 can perform the steps as shown in Figure 2 、 Figure 4 、 Figure 5 and Figure 9 .

[0120] The storage unit 220 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 2201 and / or a cache memory 2202, and can further include a read-only memory (ROM) 2203.

[0121] The storage unit 220 can also include a program / utility 2204 having a set of program modules 2205, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each or a combination thereof, which may

[0122] The bus 230 can be representative of one or more of several types of bus structures, including a storage unit bus or bus controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0123] The electronic device 200 can also communicate with one or more external devices 300 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with the electronic device 200; and / or one or more devices that enable the electronic device 200 to communicate with one or more other computing devices. Such communication can be via the input / output (I / O) interface 250. Further, the electronic device 200 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the public network, such as the Internet, via the network adapter 260. The network adapter 260 can communicate with the other modules of the electronic device 200 through the bus 230. It should be appreciated that although not shown, other hardware and / or software modules could be used in conjunction with the electronic device 200. Such hardware would include, but is not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.

[0124] Those skilled in the art can easily understand from the above description of the embodiments that the example embodiments described herein can be implemented by software or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to perform the above-mentioned method according to the embodiments of the present disclosure.

[0125] Figure 12 A schematic diagram of a computer-readable storage medium in an exemplary embodiment of the present disclosure is schematically shown.

[0126] Reference Figure 12 As shown, a program product 400 for implementing the above-mentioned method according to the embodiments of the present disclosure is described, which can take the form of a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, the readable storage medium can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, device or apparatus.

[0127] The program product can take any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0128] The computer-readable storage medium can include a data signal propagating in a baseband or as a carrier wave in a propagated signal, where the readable program code is carried. Such a propagated signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate or transmit a program for use by or in connection with an instruction execution system, device or apparatus. The program code contained on the readable storage medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0129] The program code can be executed by one or more programmable processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, microcontrollers, or other types of processing circuitry. To execute the program code, the processing circuitry can be programmed to perform specific operations by one or more electronic circuits that include electronic components disposed thereon or therein. The electronic components can include resistors, capacitors, inductors, valves, transistors, or other elements, and can be microengineered on an integrated circuit. The programming can be implemented by one or more software programs executed by the programmable processor(s) to perform tasks. The software routines can be stored in any form of a computer program product.

[0130] The computer readable medium described above carries one or more programs, when the one or more programs are executed by a device, the computer readable medium enables the following functions: obtaining new data through a private cloud; performing operation according to a policy original word stored in the public cloud and the new data, and obtaining a version of a dictionary each time the policy is generated; sending the obtained multiple versions of the dictionary to the private cloud, so that the private cloud completes policy taking effect according to the multiple versions of the dictionary; and starting a data aggregation task, so that the private cloud aggregates data for policy taking effect.

[0131] Those skilled in the art can understand that the above modules can be distributed in the device according to the description of the embodiments, and can also be changed in one or more devices different from the embodiments. The modules of the above embodiments can be combined into one module, or can be further split into multiple modules.

[0132] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a plurality of instructions to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the method according to the embodiments of the disclosure.

[0133] The example embodiments of the disclosure are specifically shown and described above. It should be understood that the disclosure is not limited to the detailed structure, arrangement or implementation method described herein; on the contrary, the disclosure is intended to cover various modifications and equivalent arrangements within the spirit and scope of the appended claims.

[0134] Furthermore, the structures, proportions, sizes, etc. shown in the drawings of the present specification are merely used to cooperate with the disclosed content, to be understood and read by those skilled in the art, and do not have technical substantial meaning, and any modification of the structure, change of the proportional relationship, or adjustment of the size, without affecting the technical effects and purposes that can be achieved by the present disclosure, should still fall within the scope of the disclosed technology. Meanwhile, the terms such as "upper", "first", "second", and "one" in the present specification are merely for the convenience of clear description, and are not used to limit the scope of the present disclosure, and the change or adjustment of the relative relationship without substantially changing the technical content is also considered as the scope of the present disclosure.

Claims

1. A method for establishing a data model, characterized in that, include: Historical data is decomposed into fields according to different disease categories. The historical data includes at least: medical books, medical literature, disease guidelines, and clinical trials. The decomposed fields include: general disease fields, general tumor fields, special disease-specific fields, and customized layer fields. The decomposed fields are processed into structured rules to form structured output rules. This process includes: The process involves: first-level fields obtained by directly mapping the corresponding value ranges to the fields obtained through decomposition; second-level fields extracted from natural language text content; third-level fields obtained by performing logical operations on the first-level and second-level fields; keyword extraction to generate a terminology dictionary based on the first-level, second-level, and third-level fields; and structured output rules obtained by performing medical logical relationship analysis on the terminology dictionary. The first-level fields are not structured, while the second-level and third-level fields are. Extracting second-level fields from natural language text content includes: constructing a tree-structured medical terminology system based on the hierarchical relationship of the terms; and extracting second-level fields from natural language text content based on the medical terminology system. A disease data model is established based on the structured output rules and clinical data. The clinical data includes basic patient information, general disease data, and non-general disease data. The establishment of the disease data model based on the structured output rules and clinical data includes: extracting and integrating the patient's basic information to obtain a set of basic information fields; extracting and integrating the general disease data to obtain a set of general fields; extracting and integrating the fields from the non-general disease data to obtain a set of non-general fields; and summarizing the set of basic information fields, the set of general fields, and the set of non-general fields according to the structured output rules to obtain the disease data model.

2. A data modeling apparatus, characterized in that, include: The field decomposition module is used to decompose historical data into fields according to different disease categories. The historical data includes at least: medical books, medical literature, disease guidelines, and clinical trials. The decomposed fields include: general disease fields, general tumor fields, special disease-specific fields, and customized layer fields. The structuring module is used to perform structuring processing on the decomposed fields to form structured output rules. This structuring process includes: directly mapping the value ranges of the same field names in the decomposed fields to obtain first-level fields; extracting second-level fields from the natural language text content; performing logical operations on the first-level and second-level fields to obtain third-level fields; extracting keywords from the first-level, second-level, and third-level fields to generate a terminology dictionary; and performing medical logical relationship analysis on the terminology dictionary to obtain the structured output rules. The first-level fields are not structuring processed, while the second-level and third-level fields are. Extracting second-level fields from the natural language text content includes: constructing a tree-structured medical terminology system based on the hierarchical relationships of the terms; and extracting second-level fields from the natural language text content based on the medical terminology system. The model building module is used to establish a disease data model based on the structured output rules and clinical data. The clinical data includes basic patient information, general disease data, and non-general disease data. Establishing the disease data model based on the structured output rules and clinical data includes: extracting and integrating the patient's basic information to obtain a set of basic information fields; extracting and integrating the general disease data to obtain a set of general fields; extracting and integrating the fields from the non-general disease data to obtain a set of non-general fields; and summarizing the set of basic information fields, the set of general fields, and the set of non-general fields according to the structured output rules to obtain the disease data model.

3. A clinical decision support method, characterized in that, include: Historical data is decomposed into fields according to different disease categories. The historical data includes at least: medical books, medical literature, disease guidelines, and clinical trials. The decomposed fields include: general disease fields, general tumor fields, special disease-specific fields, and customized layer fields. The decomposed fields are structured to form structured output rules. This process includes: directly mapping the value ranges of identical field names to obtain first-level fields; extracting second-level fields from natural language text content; performing logical operations on the first-level and second-level fields to obtain third-level fields; extracting keywords from the first-level, second-level, and third-level fields to generate a terminology dictionary; and performing medical logical relationship analysis on the terminology dictionary to obtain the structured output rules. The first-level fields are not structured, while the second-level and third-level fields are. Extracting second-level fields from natural language text content includes: constructing a tree-structured medical terminology system based on the hierarchical relationships of the terms; and extracting second-level fields from the natural language text content based on the medical terminology system. A disease data model is established based on the structured output rules and clinical data. The clinical data includes basic patient information, general disease data, and non-general disease data. The establishment of the disease data model based on the structured output rules and clinical data includes: extracting and integrating the patient's basic information to obtain a set of basic information fields; extracting and integrating the general disease data to obtain a set of general fields; extracting and integrating the fields from the non-general disease data to obtain a set of non-general fields; and summarizing the basic information field set, the general field set, and the non-general field set according to the structured output rules to obtain the disease data model. The decision-making result is obtained by combining the clinical test results and the disease data model.

4. A clinical decision support device, characterized in that, include: The field decomposition module is used to decompose historical data into fields according to different disease categories. The historical data includes at least: medical books, medical literature, disease guidelines, and clinical trials. The decomposed fields include: general disease fields, general tumor fields, special disease-specific fields, and customized layer fields. The structuring module is used to perform structuring processing on the decomposed fields to form structured output rules. This structuring process includes: directly mapping the value ranges of the same field names in the decomposed fields to obtain first-level fields; extracting second-level fields from the natural language text content; performing logical operations on the first-level and second-level fields to obtain third-level fields; extracting keywords from the first-level, second-level, and third-level fields to generate a terminology dictionary; and performing medical logical relationship analysis on the terminology dictionary to obtain the structured output rules. The first-level fields are not structuring processed, while the second-level and third-level fields are. Extracting second-level fields from the natural language text content includes: constructing a tree-structured medical terminology system based on the hierarchical relationships of the terms; and extracting second-level fields from the natural language text content based on the medical terminology system. A model building module is used to establish a disease data model based on the structured output rules and clinical data. The clinical data includes basic patient information, general disease data, and non-general disease data. Establishing the disease data model based on the structured output rules and clinical data includes: extracting and integrating the patient's basic information to obtain a set of basic information fields; extracting and integrating the general disease data to obtain a set of general fields; extracting and integrating the fields from the non-general disease data to obtain a set of non-general fields; and summarizing the set of basic information fields, the set of general fields, and the set of non-general fields according to the structured output rules to obtain the disease data model. The decision-making module is used to combine clinical test results and the disease data model to obtain a decision result.

5. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the method as described in claim 1 or the method as described in claim 3.

6. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in claim 1 or the method as described in claim 3.

Images