CN114822807A

CN114822807A - Disease identification method, device, system and storage medium

Info

Publication number: CN114822807A
Application number: CN202110062895.1A
Authority: CN
Inventors: 周益锋
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2021-01-18
Filing date: 2021-01-18
Publication date: 2022-07-29
Also published as: WO2022152280A1

Abstract

The embodiment of the application provides a disease identification method, equipment, a system and a storage medium. In the embodiment of the application, the disease characteristics of the medical record data of the patient to be audited can be extracted, and the disease type of the patient to be audited can be identified according to the disease characteristics of the patient to be audited, so that the disease type of the patient to be audited can be determined, the automatic identification of the disease type of the patient can be realized, and the disease type identification efficiency can be improved.

Description

Disease identification method, device, system and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to a disease identification method, device, system, and storage medium.

Background

Paying according to the disease types is a great direction of medical reform in China in recent years. Pay by disease category means that a quota reimbursement standard of each disease is scientifically made through unified disease diagnosis and classification, and a social security institution pays hospitalization cost to a fixed-point medical institution according to the standard and the number of hospitalized persons so as to standardize the utilization of medical resources.

However, due to the large number of disease categories, it is difficult for a medical facility to determine the patient's disease category grouping during a patient visit. Therefore, how to quickly and accurately determine the disease type of a patient to be examined becomes a technical problem to be urgently solved.

Disclosure of Invention

Various aspects of the present application provide a disease identification method, device, system, and storage medium, which are used to realize automatic identification of disease, and contribute to improving the disease identification efficiency.

The embodiment of the application provides a disease species identification method, which comprises the following steps:

acquiring medical record data of a patient to be examined;

performing disease feature extraction on the medical record data of the patient to be examined to obtain the disease feature of the patient to be examined;

and identifying the disease species according to the disease characteristics of the patient to be examined to determine the disease species of the patient to be examined.

The embodiment of the application further provides a disease species identification method, which comprises the following steps:

responding to the disease identification request, and acquiring medical record data of a patient to be examined of the patient to be examined;

according to the disease characteristics of the patient to be examined, disease species identification is carried out so as to determine the disease species of the patient to be examined;

and providing the disease species of the patient to be audited to a client sending the disease species identification request, so that the client can output the disease species of the patient to be audited.

An embodiment of the present application further provides a data processing system, including: the system comprises terminal equipment and server-side equipment;

the terminal device is used for responding to the audit event and sending a disease identification request to the server device; the disease species identification request comprises: patient identification;

the server device is configured to: responding to the disease identification request, and acquiring medical record data of a patient to be examined of the patient to be examined corresponding to the patient identification; performing disease feature extraction on the medical record data of the patient to be examined to obtain the disease feature of the patient to be examined; according to the disease characteristics of the patient to be audited, disease species identification is carried out to determine the disease species of the patient to be audited; and providing the disease species of the patient to be audited for the terminal equipment so that the terminal equipment can output the disease species of the patient to be audited.

An embodiment of the present application further provides a computer device, including: a memory and a processor; wherein the memory is used for storing a computer program;

the processor is coupled to the memory for executing the computer program for performing the steps of the above-mentioned disease species identification method.

Embodiments of the present application also provide a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the above-mentioned disease species identification method.

In the embodiment of the application, the disease characteristics of the medical record data of the patient to be audited can be extracted, and the disease type of the patient to be audited can be identified according to the disease characteristics of the patient to be audited, so that the disease type of the patient to be audited can be determined, the automatic identification of the disease type of the patient can be realized, and the identification efficiency of the disease type can be improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1a is a block diagram of a data processing system according to an embodiment of the present application;

FIG. 1b is a schematic view of a display interface for a medical resource expiration status provided by an embodiment of the present application;

fig. 2 and fig. 3 are schematic flow charts of a disease species identification method provided in an embodiment of the present application;

fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Due to the large number of disease categories, it is difficult for medical institutions to determine the patient's category grouping during a patient visit. Therefore, how to quickly and accurately determine the disease category of the patient to be examined becomes an urgent technical problem to be solved.

In order to solve the technical problem, in some embodiments of the present application, disease feature extraction may be performed on medical record data of a patient to be examined, and disease species identification may be performed on the extracted disease features to determine the disease species of the patient to be examined, so that automatic identification of the disease species of the patient is achieved, and improvement of disease species identification efficiency is facilitated.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

It should be noted that: like reference numerals refer to like objects in the following figures and embodiments, and thus, once an object is defined in one figure or embodiment, further discussion thereof is not required in subsequent figures and embodiments.

Fig. 1a is a schematic structural diagram of a data processing system according to an embodiment of the present application. As shown in fig. 1a, the system comprises: a terminal device 11 and a server device 12.

The server device 12 and the terminal device 11 may be connected wirelessly or by wire. Optionally, the service-side device 12 may be communicatively connected to the terminal device 11 through a mobile network, and accordingly, the network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), 5G, WiMax, and the like. Alternatively, the server device 12 may also be communicatively connected to the terminal device 11 through bluetooth, WiFi, infrared, or the like.

In this embodiment, the terminal device 11 refers to a computer device used by a user and having functions of computing, accessing internet, communicating and the like required by the user, and may be, for example, a smart phone, a tablet computer, a personal computer, a wearable device and the like. In this embodiment, the user may be a medical staff or a patient.

In this embodiment, the server device 12 refers to a computer device that can perform medical record data management and provide services related to data processing for a user in response to a service request from the terminal device 12, and generally has the capability of undertaking and guaranteeing the services. The server device 12 may be a single server device, a cloud server array, or a Virtual Machine (VM) running in the cloud server array. In addition, the server device may also refer to other computing devices with corresponding service capabilities, such as a terminal device (running a service program) such as a computer.

The server device 12 may be a server of a hospital. Alternatively, the server device 12 may be a server in a private cloud of the hospital. Alternatively, the server device 12 may also be a server in a public cloud, and the like.

In this embodiment, the terminal device 11 may send a disease category identification request to the server device 12 in response to the audit event. In the embodiment of the present application, a specific implementation form of the audit event is not limited. In some embodiments, as shown in fig. 1a, terminal device 11 may provide a disease category query interface K1. Alternatively, the disease category query interface may be implemented as a query control K1. Accordingly, the audit event may be implemented as an audit event generated by a trigger operation for the disease category query interface K1.

In some embodiments, the user may upload medical record data of a patient to be reviewed to the server device 12 through the terminal device 11. Medical record data refers to medical records generated by a patient during a visit to a patient, and can be outpatient medical records and/or inpatient medical records. Medical record data can include, but is not limited to: outpatient diagnosis, admission diagnosis, medical history, operative records, medical advice, nursing records, medical lists, death records, and the like. The list of medications may include: name of medicine, price, quantity, etc. The medicine includes medicine, medical consumables, etc.

Alternatively, as shown in fig. 1a, the terminal device 11 may provide a data uploading interface, such as a medical record providing control K2. The user can upload medical record data through the medical record providing control. The terminal device 11 may respond to the triggering operation for the medical record providing control K2, and acquire data associated with the triggering operation as medical record data of the patient to be audited. Namely, the data uploaded by the user of the terminal device 11 through the medical record providing control is used as medical record data of the patient to be audited. In this embodiment, the terminal device 11 may further provide medical record data of a patient to be audited to the server device 12. Alternatively, the terminal device 11 may provide medical record data of a patient to be audited to the server device 12 before initiating a patient identification request, store the medical record data of the patient by the server device 12, and establish a corresponding relationship between a patient identifier and the medical record data of the patient. Patient identification refers to information that uniquely identifies a patient. Such as, but not limited to, the patient identifier may be the patient's name, identification number, social security number, etc.

Further, the user may trigger the disease inquiry interface K1 when checking the disease of the patient. The terminal device 11 may issue a disease category identification request to the server device 12 in response to the audit event generated for triggering the disease category inquiry interface K1. The patient identification request may include a patient identification. Optionally, the terminal device 11 may provide a patient identification upload interface K3. Optionally, the terminal device 11 may provide a patient identification input control through which the user may input the identification of the patient to be audited. In other embodiments, as shown in FIG. 1a, the patient identification upload interface K3 may also be implemented as a selection control K3 through which a user may select an identification of a patient to be reviewed. Accordingly, the terminal device 11 may respond to the selection operation for the patient identifier, and use the selected patient identifier as the identifier of the patient to be audited.

The server device 12 may respond to the patient identification request to obtain medical record data of the patient to be examined corresponding to the patient identifier. Optionally, the server device 12 may analyze the patient identifier from the disease identification request, and perform matching in the corresponding relationship between the patient identifier and the medical record data of the patient, so as to obtain the medical record data corresponding to the patient identifier in the disease identification request, which is used as the medical record data of the patient to be examined.

In other embodiments, the terminal device 11 may provide the medical record data of the patient to be reviewed and the patient identification request to the server device 12 in response to the review event. In this embodiment, the server device 12 receives the medical record data of the patient to be reviewed and the disease identification request, and in response to the disease identification request, uses the medical record data sent together with the disease identification request as the medical record data of the patient to be reviewed.

Further, the server-side device 12 may perform disease feature extraction on medical record data of a patient to be examined to obtain disease features of the patient to be examined; and according to the disease characteristics of the patient to be examined, identifying the disease species to determine the disease species of the patient to be examined.

Further, as shown in fig. 1a, the server-side device 12 may also provide the disease type of the patient to be audited to the terminal device 11. Accordingly, the terminal device 11 may receive the disease category of the patient to be audited and output the disease category of the patient to be audited. Optionally, the terminal device 11 may display the disease category of the patient to be examined, i.e. the disease category query result shown in fig. 1a, on the screen; and/or playing the disease category of the patient to be audited through an audio component, and the like.

The data processing system provided by the embodiment can extract disease characteristics of medical record data of a patient to be audited, and identify the disease type of the patient to be audited according to the disease characteristics of the patient to be audited, so that the disease type of the patient to be audited can be determined, the automatic identification of the disease type of the patient can be realized, and the disease type identification efficiency can be improved.

In the embodiment of the present application, a specific implementation manner of performing, by the server device 12, disease feature extraction on medical record data of a patient to be examined is not limited. In some embodiments, the server-side device 12 may obtain a plurality of keywords reflecting the medical condition of the patient to be examined from the medical record data of the patient to be examined. Plural means 2 or more. In the present embodiment, the attribute of the keyword is not limited. Such as keyword, disease name, symptom description, detection index parameter value, etc. The server-side device 12 obtains keywords reflecting the medical conditions of the patient to be examined in different embodiments according to medical record data with different attributes.

In some embodiments, medical record data can be divided into structured medical record data and unstructured medical record data. The structured medical record data specifically refers to medical record data organized in a structured data structure, such as medical record data organized in a data structure form of a table, a list, a graph, and the like. The fields of the medical record data are typically of a fixed format and scope. For example, in the detection of a certain index, there are an actually measured index parameter value and a normal parameter value range of the index.

Unstructured medical record data refers to medical record data without a fixed format and scope. Such as text, pictures, etc. The text can be a text description in the examination report, such as a text description in a color Doppler report, a text description in a CT report, and the like; the pictures can be pictures in the examination report, such as color Doppler pictures, pathological examination pictures, and the like.

For structured medical record data, the data can be organized in a format such as a table. For a table, each entry has a field name. Accordingly, field data can be indexed by field name, and the field name and the field data are used as keywords. Such as blood pressure, blood item data, urine routine data, etc. Wherein, the field name and the field data can form a Key-Value (K-V) pair.

For unstructured medical record data, the server-side device 12 can perform semantic analysis on the unstructured medical record data to obtain keywords from the unstructured medical record data. Optionally, the server device 12 may perform word segmentation processing on the unstructured medical record data to obtain a word set included in the unstructured medical record data; carrying out attribute identification on the word set to determine the attribute of each word in the word set; and then determining keywords reflecting the symptoms of the patient to be audited according to the attributes of all the words in the word set. Optionally, the keywords with the word attributes as the target attributes may be selected according to the attributes of each word in the word set.

In this embodiment, the target attribute may be a description item of the detection item. For example, if color Doppler ultrasound detection is performed on a certain part, the target attributes may be the size of the part, the presence or absence of an abnormality, the abnormal part, and the size of the abnormal part. For example, the target attribute may be, but is not limited to, size of thyroid gland, presence or absence of nodules, nodule location, nodule size, presence or absence of calcification in nodules, etc.

Further, for a plurality of keywords reflecting the symptoms of the patient to be examined, ICD codes of target keywords in the plurality of keywords can be determined according to a dictionary of the keywords and ICD codes of International Classification of Diseases (ICD). ICD codes are an international unified disease classification method established by the WHO, and the ICD codes classify diseases into an ordered combination according to characteristics of disease causes, pathology, clinical manifestations, anatomical positions and the like, and are expressed by a coding method. The ICD code dictionary records names and symptoms of each disease and the like. The ICD coding dictionary comprises: diagnosis ICD coding dictionary and operation ICD coding dictionary. The ICD coding refers to a classification coding system for international diagnosis and clinical operation.

Accordingly, the server device 12 may calculate the similarity between each keyword and the disease category description in the ICD encoding dictionary. That is, the server device 12 may calculate the similarity between the keyword and the disease category description of each disease category in the ICD encoding dictionary. In the embodiments of the present application, for convenience of description, the description of the disease species is simply referred to as the disease species description. In this embodiment, a specific implementation of calculating the similarity between the keyword and the disease category description in the ICD encoding dictionary is not limited.

In some embodiments, the keyword may be character-matched in the ICD encoding dictionary, and the number of character matches between the keyword and the description of the disease category a in the ICD encoding dictionary may be used as the similarity between the keyword and the description of the disease category a in the ICD encoding dictionary.

In other embodiments, vectorization processing may be further performed on the keyword and the disease category description in the ICD encoding dictionary to obtain a vector corresponding to the keyword and a vector corresponding to the disease category description in the ICD encoding dictionary. Optionally, word2vec and other word segmentation models or text classification models such as fasttext can be adopted to perform vectorization processing on the keywords and disease descriptions in the ICD coding dictionary.

Further, the server device 12 may calculate a distance between a vector corresponding to the keyword and a vector corresponding to the disease category description in the ICD encoding dictionary as a similarity between the keyword and the disease category description in the ICD encoding dictionary. The greater the distance between the vector corresponding to the keyword and the vector corresponding to the disease category description in the ICD coding dictionary, the smaller the similarity between the two vectors. The distance between the vectors corresponding to the keywords and the vectors corresponding to the disease type descriptions in the ICD coding dictionary may be a cosine distance, a euclidean distance, a manhattan distance, and the like between the vectors.

Further, the server device 12 may select the target keyword from the multiple keywords according to the similarity between the multiple keywords and the disease category description in the ICD encoding dictionary. For example, a keyword with the similarity greater than or equal to a set similarity threshold value can be selected from the multiple keywords as a target keyword according to the similarity between the multiple keywords and the disease category description in the ICD coding dictionary; alternatively, a set number of keywords may be selected from the plurality of keywords as target keywords in the order of the similarity between the plurality of keywords and the disease category description in the ICD encoding dictionary from large to small, and so on.

Further, the server device 12 may use the ICD code corresponding to the disease category description with the highest similarity to the target keyword as the ICD code of the target keyword.

Aiming at the ICD codes of the target keywords, vectorization processing can be carried out on the ICD codes of the target keywords to obtain vector characteristics of the target keywords, and the vector characteristics are used as at least part of disease characteristics of the patient to be examined.

Alternatively, the target keyword may be 1 or more. Plural means 2 or more. Aiming at the target keywords, connecting the target keywords according to a set sequence to obtain a sentence describing the disease of the patient to be examined; inputting the sentences describing the diseases of the patient to be audited into the word vector model, and vectorizing the sentences describing the diseases of the patient to be audited in the word vector model to obtain vector characteristics corresponding to the sentences describing the diseases of the patient to be audited, namely the vector characteristics of the target keywords. Alternatively, the word vector model may be, but is not limited to, a word2vector model or a fasttext model, etc.

In some embodiments, ICD encoding of the target keyword includes: diagnostic ICD coding and/or surgical ICD coding. ICD encoding for the target keyword includes: in the case of the diagnosis ICD code and the operation ICD code, the diagnosis ICD code and the operation ICD code can be separately vectorized, and the diagnosis ICD code and the operation ICD code can also be fused and vectorized.

When vectorization processing is carried out on the diagnosis ICD codes independently, a plurality of diagnosis ICD codes can be connected together according to a set sequence to form a diagnosis sentence; and inputting the diagnosis sentence into the word vector model to obtain the vector characteristics of the diagnosis ICD code. The set sequence can be a description sequence for diagnosis when a doctor makes medical records. Alternatively, the set order may be a ranking of the diagnoses by primary or secondary or severity of the diagnosis. If the set sequence is as follows: main diagnosis, complications, past medical history, etc.

When the operation ICD codes are separately vectorized, a plurality of operation ICD codes can be connected together according to a set sequence to form an operation sentence; and the operation sentences are input into the word vector model to obtain the vector characteristics of the operation ICD codes. The set order can be the ranking of the diagnoses according to the primary or secondary operation or difficulty.

When the diagnosis ICD codes and the operation ICD codes are subjected to vectorization softly, a plurality of diagnosis ICD codes and a plurality of operation ICD codes can be connected according to a set sequence to form a sentence for describing the disease of a patient to be examined; inputting the sentences describing the diseases of the patient to be audited into the word vector model, and vectorizing the sentences describing the diseases of the patient to be audited in the word vector model to obtain vector characteristics corresponding to the sentences describing the diseases of the patient to be audited, namely the vector characteristics of the target keywords. In this embodiment, the order of setting includes, but is not limited to: diagnosis ICD coding is in front of the diagnosis ICD coding, and operation ICD coding is behind the diagnosis ICD coding; alternatively, surgical ICD coding precedes diagnostic ICD coding follows, and the like.

In the actual use process, whether the diagnosis ICD code and the operation ICD code are separately vectorized or the diagnosis ICD code and the operation ICD code are fused and vectorized is mainly determined by separately training a word vector model for vectorizing the diagnosis ICD code and a word vector model for vectorizing the operation ICD code in the training stage of the word vector model; and training the word vector model by fusing the diagnosis ICD code and the operation ICD code. In the training stage of the word vector model, the dimensionality of the vector features can be optimized as the hyperparameter of the word vector model.

Aiming at keywords without ICD codes, such as keywords in the structured medical record data, such as the number of days of stay, leaving mode, department of discharge, various expenses and the like, the structured medical record data can be coded to obtain the coding result of the structured medical record data, and the coding result is used as at least part of disease characteristics of the patient to be audited. Optionally, the server device 12 may perform one-hot encoding (one-hot), normalization, null value filling, and the like on the structured medical record data.

Optionally, in some embodiments, the server-side device 12 may further perform feature screening on the disease features of the patient to be examined to obtain the target disease features. The disease screening method for the disease characteristics of the patient to be examined includes but is not limited to the following steps: screening based on statistical methods (such as correlation coefficient method, mutual information method, chi-square test, etc.) or model-based feature screening, etc., but is not limited thereto. Optionally, for the case of excessive feature dimensions, the server device 12 may also perform dimension reduction processing on the disease features. Alternatively, the dimension reduction process can be performed on the disease features by using Principal Component Analysis (PCA) or Linear Discriminant Analysis (LDA), but is not limited thereto.

Further, after acquiring the disease characteristics of the patient to be audited, the server-side device 12 may further perform disease identification according to the disease characteristics of the patient to be audited, so as to determine the disease type of the patient to be audited.

In this embodiment, the medical staff can also update the medical record data of the patient to be audited in time during the visit of the patient to be audited (such as during the hospitalization), so that the disease category of the patient to be audited can be identified in time according to the progress dynamics of the patient to be audited.

The embodiment of the application does not limit the specific implementation mode of identifying the disease type according to the disease characteristics of the patient to be examined. Several embodiments are exemplified below.

Embodiment 1: the disease characteristics of the patient to be examined can be input into the disease identification model for disease identification so as to determine the disease of the patient to be examined. Optionally, the disease characteristics of the patient to be examined can be connected, and the connected disease characteristics can be input into the disease identification model for disease identification, so as to determine the disease of the patient to be examined.

In some embodiments, the disease characteristics of the patient to be reviewed include: diagnostic features and surgical features. In embodiment 1, the diagnostic feature and the surgical feature may be linked as a disease feature of the patient to be examined. For example, assume that the vector dimension of p diagnostic features is n, the vector dimension of q surgical features is m, and the dimension of the concatenated vector is (p × n + q × m). Wherein p and q are positive integers.

In the embodiment 1, the historical medical record data and the classification result of the disease types of the historical patients can be acquired; and extracting disease characteristics of the historical medical record data to obtain the disease characteristics of the historical patient. For a specific implementation of obtaining the disease characteristics of the historical patient, reference may be made to the above-mentioned related contents of obtaining the disease characteristics of the patient to be examined, and details are not described here again.

Furthermore, the disease classification result of the historical patient can be used as supervision, and the disease characteristics of the historical patient are used for model training to obtain a disease identification model, namely, the disease characteristics of the historical patient are used as a training sample for model training to obtain the disease identification model.

Wherein, the disease species identification model is a multi-classification model. The machine learning algorithm for the disease identification model includes, but is not limited to: a logistic regression Model, a Support Vector Machine (SVM) Model, a random forest Model, a Gradient Boosting Decision Tree (GBDT) Model, a lightweight Gradient Boosting Model (LightGBM), a deep neural network Model, etc., or an integrated learning algorithm that integrates the above models.

Embodiment 2: and performing feature fusion on the disease features of the patient to be examined to obtain fused disease features of the patient to be examined. Optionally, the disease features of the patient to be examined may be weighted and summed to obtain the disease features after the patient to be examined is fused. Furthermore, the disease characteristics of the patient to be examined after fusion can be input into the disease identification model for disease identification, so as to determine the disease of the patient to be examined.

In some embodiments, the disease characteristics of the patient to be reviewed include: diagnostic features and surgical features. When the disease characteristics of a patient to be examined are subjected to characteristic fusion, the diagnosis characteristics and the operation characteristics can be separately and respectively fused; diagnostic features and surgical features may also be fused together.

When the diagnostic features and the surgical features are separately and respectively fused, the p diagnostic features can be subjected to weighted summation to obtain fused diagnostic features. Optionally, p diagnostic features may each be assigned a weight value W _i . 1, 2, p; p is a positive integer. The weighted values may be equal or unequal. The formula for weighted summation of p diagnostic features can be expressed as:

wherein, in the formula (1), V _i A vector representing a correspondence of each diagnostic feature;

representing the fused diagnostic features.

Similarly, q surgical features may also be assigned weight values W _i . 1, 2, ·, q; q is a positive integer. The formula for weighted summation of q surgical features can be expressed as:

wherein, in the formula (2), V _i A vector representing each surgical feature;

indicating the post-fusion surgical features.

Further, the fused diagnostic features and the fused surgical features can be connected in a feature manner to obtain fused disease features.

When the diagnostic features and the surgical features are fused together, p diagnostic features and q surgical features may be assigned respective weights Wi, i ═ 1, 2., (p + q); and carrying out weighted summation on the vectors corresponding to the p diagnostic features and the q surgical features to obtain fused disease features. In this embodiment, the vector dimensions of the p diagnostic features and the q surgical features are the same.

In the embodiment 2, the historical medical record data and the classification result of the disease types of the historical patients can be obtained; and extracting disease characteristics of the historical medical record data to obtain the disease characteristics of the historical patient. Furthermore, feature fusion can be carried out on the disease features of the historical patients to obtain the fused disease features of the historical patients. Furthermore, the disease classification result of the historical patient can be used as supervision, and the disease characteristics of the historical patient after fusion are used as training samples to perform model training so as to obtain a disease identification model. For a specific implementation of feature fusion of disease features of historical patients, reference may be made to the above-mentioned related contents of feature fusion of disease features of patients to be examined, which are not described herein again. For the implementation of the disease identification model, reference is made to the related contents in embodiment 1, and details are not repeated here.

Further, the server device 12 may input the disease characteristics of the patient to be audited or the fused disease characteristics into the disease identification model, and perform disease identification by using the disease identification model to obtain the disease of the patient to be audited.

It should be noted that the scheme for identifying the disease type without performing feature fusion on the disease features of the historical patient as shown in embodiment 1, and the scheme for performing feature fusion on the diagnosis feature and the surgical feature individually and performing feature fusion on the diagnosis feature and the surgical feature together as shown in embodiment 2 can be flexibly selected according to the disease grouping criteria supported at the time. In practice, one of the disease category identification schemes may be set by the data processing system developer according to the disease grouping criteria that the hospital currently supports. Of course, the developer of the data processing system also sets the above-mentioned multiple disease identification scheme settings, and the actual user (medical staff or patient) selects one of the multiple disease identification schemes for disease identification according to the disease grouping standard currently supported by the hospital.

In practical application, different disease species have different medical resource standards. Wherein the medical resource comprises at least one medical resource item. The medical resource standard mainly refers to a standard for a medical resource item. The medical resource items may include: one or more of standards such as medical insurance claim payment proportion corresponding to the disease category, average total hospitalization cost of the disease category in a designated area, total hospitalization days, total hospitalization cost, total drug cost, total medical consumable cost, number of operations and the like, wherein the multiple means 2 or more. The designated area may be an area to which a hospital to be examined belongs, such as a provincial city to which the hospital belongs.

Based on this, in the embodiment of the application, medical resource examination can be performed on the patient to be examined based on the disease type of the patient to be examined and the medical resource standard corresponding to the disease type. The specific implementation mode is as follows:

after acquiring the disease category of the patient to be audited, the server device 12 may also acquire the medical resource standard corresponding to the disease category of the patient to be audited; and acquiring the medical resource consumption of the patient to be audited according to the medical record data of the patient to be audited. Correspondingly, the medical resource consumption of the patient to be audited mainly refers to the consumption of the patient to be audited for the medical resource item. The healthcare resource items may include: the number of the hospitalization days, the total cost of hospitalization, the total cost of medicines, the total cost of medical consumables, the number of operations and the like of the patient to be examined.

Further, the server device 12 may calculate the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumed by the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited.

Optionally, for any medical resource item, the consumption of the patient to be audited for the medical resource item may be calculated, the absolute superscalar value and the relative superscalar proportion of the patient to be audited for the medical resource standard corresponding to the medical resource item are calculated, and the absolute superscalar value and the relative superscalar proportion of the patient to be audited for the medical resource item are weighted and summed to obtain the superscalar degree of the patient to be audited for the medical resource item, which is used as the superscalar condition of the patient to be audited for the medical resource item.

For example, if the medical resource item is the number of days of hospitalization, the number of days of hospitalization of the patient to be examined can be calculated, the absolute superscalar value and the relative superscalar proportion of the number of days of hospitalization corresponding to the type of disease of the patient to be examined are calculated, and the absolute superscalar value and the relative superscalar proportion of the patient to be examined with respect to the number of days of hospitalization are weighted and summed to obtain the superscalar program of the patient to be examined with respect to the number of days of hospitalization, which is used as the superscalar condition of the patient to be examined with respect to the number of days of hospitalization.

For the medical resource item i, the calculation formula of the overproof condition of the patient to be audited for the medical resource item i can be expressed as follows:

R _i ＝W _i A _i +Q _i B _i (3)

in the formula (3), i represents the ith medical resource item; r _i The standard exceeding score, namely the standard exceeding degree, of the patient to be audited aiming at the medical resource item i is represented; a. the _i And B _i Respectively representing the absolute exceeding standard value and the relative exceeding standard proportion of the patient to be audited aiming at the medical resource item i compared with the medical resource standard; w _i And Q _i Respectively representing the absolute superscript value sum of the medical resource standard and the medical resource item i of the patient to be auditedRelative superscalar weight.

In some embodiments, the server-side device 12 may further determine the standard-exceeding medical resource item of the patient to be audited according to the standard-exceeding degree of the patient to be audited for each medical resource item, and use the standard-exceeding medical resource item of the patient to be audited as the standard-exceeding medical resource condition of the patient to be audited. Optionally, for each medical resource item, a threshold of the degree of overproof for that medical resource item may be set. The server-side device 12 may use the medical resource item whose exceeding degree is greater than or equal to the exceeding degree threshold of the medical resource item as the exceeding medical resource item of the patient to be audited. Optionally, the server-side device 12 may further use the absolute superscalar value and/or the relative superscalar proportion of the patient to be audited with respect to the superscalar resource item as the superscalar condition of the medical resource of the patient to be audited.

In other embodiments, the server-side device 12 may perform weighted summation on the consumption of the to-be-audited patient for each medical resource item, with respect to the absolute superscalar value and the relative superscalar proportion of the medical resource standard corresponding to the medical resource item, and the absolute superscalar value and the relative superscalar proportion of the to-be-audited patient for the medical resource item, to obtain the medical resource superscalar degree of the to-be-audited patient, which is used as the medical resource superscalar condition of the to-be-audited patient. Accordingly, the calculation formula can be expressed as:

in equation (4), n is a positive integer and represents the total number of medical resource items.

Further, the server device 12 may also provide the medical resource exceeding condition of the patient to be audited to the terminal device 11. Optionally, the medical resource standard exceeding condition of the patient to be audited may include: the standard exceeding medical resource item of the patient to be audited, the standard exceeding degree of the patient to be audited aiming at the standard exceeding medical resource item, the absolute standard exceeding value and the relative standard exceeding proportion of the patient to be audited aiming at the standard exceeding medical resource item, the standard exceeding degree of the medical resource of the patient to be audited and the like.

Correspondingly, the terminal device 11 receives the medical resource exceeding condition of the patient to be audited, displays the medical resource exceeding condition on the screen, and provides reference for medical staff to check the medical resource exceeding condition in time and adjust the treatment scheme in time. As shown in fig. 1b, the terminal device 11 may display one or more information of the standard-exceeding medical resource item of the patient to be audited, the standard-exceeding degree of the patient to be audited for the standard-exceeding medical resource item, the absolute standard-exceeding value and the relative standard-exceeding proportion of the patient to be audited for the standard-exceeding medical resource item, and the standard-exceeding degree of the medical resource of the patient to be audited, on the screen. The standard exceeding medical resource items of the patient to be audited, the standard exceeding degree of the patient to be audited aiming at the standard exceeding medical resource items, the absolute standard exceeding value and the relative standard exceeding proportion of the patient to be audited aiming at the standard exceeding medical resource items are displayed on the screen, the standard exceeding reasons can be displayed, medical workers can know the standard exceeding reasons in time, and a reference direction for adjusting the treatment scheme is provided.

In some embodiments, in addition to considering the medical resource consumption of the patient to be audited relative to the medical resource standard of the patient's race, the historical medical resource consumption of the office in which the patient to be audited is located may be referenced. Based on this, the server device 12 can also obtain the medical department of the patient to be examined from the medical record data of the patient to be examined; and acquiring the historical per-capita medical resource consumption of the office of treatment. Such as one or more of the average number of hospitalizations of the office in which the patient to be examined is located, the average total cost of hospitalization of the office in which the patient to be examined is located, the average number of operations of the office in which the patient to be examined is located, the average total cost of medicines of the office in which the patient to be examined is located, the average total cost of medical consumables of the office in which the patient to be examined is located, and the like.

Correspondingly, the server-side device 12 can also calculate the absolute superscalar value and the relative superscalar proportion of each medical resource item of the patient to be audited according to the medical resource consumption of the patient to be audited, the historical per-patient medical resource consumption of the clinic and the medical resource consumption of the patient to be audited.

Optionally, for any medical resource item i, the medical resource item for which the patient to be audited can be calculatedi consumption, relative to the absolute superscalar value A of the medical resource standard corresponding to the medical resource item _i And relative over-standard ratio B _i (ii) a And calculating the consumption of the audited patient aiming at the medical resource item i, and calculating an absolute superscript value C relative to the historical per-capita resource consumption of the department where the audited patient is located aiming at the medical resource item i _i And relative over-standard ratio D _i (ii) a Further, the absolute exceeding standard value and the relative exceeding standard proportion of the patient to be audited aiming at the medical resource item i can be subjected to weighted summation to obtain the exceeding standard degree of the patient to be audited aiming at the medical resource item i. The calculation method is as follows:

R _i ＝W _i A _i +Q _i B _i +K _i C _i +G _i D _i (5)

in the formula (5), i represents the ith medical resource item; r _i The standard exceeding score, namely the standard exceeding degree, of the patient to be audited aiming at the medical resource item i is represented; a. the _i And B _i Respectively representing the absolute exceeding standard value and the relative exceeding standard proportion of the patient to be audited aiming at the medical resource item i compared with the medical resource standard; w _i And Q _i And respectively representing the weights of the absolute superscalar value and the relative superscalar proportion of the patient to be audited aiming at the medical resource item i compared with the medical resource standard. C _i And D _i Respectively representing the absolute superscalar value and the relative superscalar proportion of the medical resource consumption of the patient to be audited aiming at the medical resource item i compared with the historical per-capita consumption of the department where the patient to be audited is located; k _i And G _i And respectively representing the absolute superscalar value and the weight of the relative superscalar proportion of the medical resource consumption of the patient to be audited aiming at the medical resource item i compared with the historical per-capita medical resource consumption of the department where the patient to be audited is located.

In some embodiments, the server-side device 12 may further determine the standard-exceeding medical resource item of the patient to be audited according to the standard-exceeding degree of the patient to be audited for each medical resource item, and use the standard-exceeding medical resource item of the patient to be audited as the standard-exceeding medical resource condition of the patient to be audited. Optionally, the server-side device 12 may further use an absolute superscale value and/or a relative superscale proportion of the patient to be audited with respect to the superscale medical resource item as the medical resource superscale condition of the patient to be audited.

In other embodiments, the server-side device 12 may calculate the consumption of the patient to be audited for each medical resource item, as compared with the absolute superscript value and the relative superscript proportion of the medical resource standard corresponding to the medical resource item, and the consumption of the patient to be audited for the medical resource item, as compared with the average consumption of the patient to be audited for the historical people of the medical resource item in the clinic, and perform weighted summation on the absolute superscript value and the relative superscript proportion of the patient to be audited for a plurality of medical resource items, to obtain the medical resource superscript degree of the patient to be audited, which is used as the medical resource superscript condition of the patient to be audited. Accordingly, the calculation formula can be expressed as:

in equation (6), n is a positive integer and represents the total number of medical resource items.

Further, the server device 12 may also provide the medical resource standard exceeding condition of the patient to be audited to the terminal device 11. Optionally, the medical resource standard exceeding condition of the patient to be audited may include: the medical resource monitoring system comprises one or more information of standard exceeding medical resource items of a patient to be examined, standard exceeding degrees of the patient to be examined aiming at the standard exceeding medical resource items, absolute superscript values and relative standard exceeding proportions of the standard exceeding medical resource items of the patient to be examined compared with medical resource standards of the patient, absolute superscript values and relative standard exceeding proportions of the standard exceeding medical resource items of the patient to be examined compared with historical per-capita resource consumption of a department where the patient to be examined is located, the standard exceeding degrees of the medical resources of the patient to be examined and the like.

Correspondingly, the terminal device 11 receives the medical resource exceeding condition of the patient to be audited, displays the medical resource exceeding condition on the screen, and provides reference for medical staff to check the medical resource exceeding condition in time and adjust the treatment scheme in time. For example, one or more information of the exceeding medical resource item of the patient to be audited, the exceeding degree of the exceeding medical resource item of the patient to be audited, the absolute exceeding value and the relative exceeding proportion of the exceeding medical resource item of the patient to be audited to the medical resource standard of the exceeding medical resource item compared with the disease type of the patient, the absolute exceeding value and the relative exceeding proportion of the exceeding medical resource item compared with the historical per-person resource consumption of the department of the patient to be audited, the exceeding degree of the medical resource of the patient to be audited, and the like can be displayed on the screen. The exceeding medical resource items of the patient to be audited, the exceeding degree of the patient to be audited aiming at the exceeding medical resource items, the absolute exceeding value and the relative exceeding proportion of the patient to be audited aiming at the exceeding medical resource items compared with the medical resource standard of the patient in which the exceeding medical resource items are located, and the absolute exceeding value and the relative exceeding proportion of the patient to be audited aiming at the medical resource consumption of the exceeding medical resource items compared with the historical people in the clinic in which the exceeding medical resource items are located are displayed on the screen, the exceeding reasons can be displayed, medical workers can know the exceeding reasons in time, and a reference direction for adjusting a treatment scheme is provided.

In the embodiment of the present application, in addition to calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited, the server-side device 12 may also perform medical resource scheduling on the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited. Optionally, the server-side device 12 may determine, according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited, a medical resource item for which the patient to be audited does not meet the medical resource standard. For any medical resource item, the server-side device 12 may obtain a consumption amount corresponding to the medical resource item from the medical resource consumption amount of the patient to be audited; acquiring medical resource standard quantity corresponding to the medical resource item from the medical resource standard corresponding to the disease species of the patient to be examined; and judging whether the consumption corresponding to the medical resource item reaches the corresponding medical resource standard quantity, and if not, determining that the medical resource item is the medical resource item which does not reach the medical resource standard.

Further, the server-side device 12 may also calculate a difference between the consumption amount corresponding to the medical resource item that does not meet the medical resource standard for the patient to be audited and the medical resource standard; and according to the difference between the consumption amount of the patient to be audited corresponding to the medical resource item which does not reach the medical resource standard and the medical resource standard, scheduling the medical resource corresponding to the medical resource item which does not reach the medical resource standard for the patient to be audited.

In the embodiment of the present application, the server device 12 may recommend a clinical route for a disease category in addition to standardizing medical resource reimbursement. The clinical pathway is a method for establishing a set of standardized treatment modes and treatment procedures for a certain disease, is a comprehensive mode related to clinical treatment, and promotes treatment organization and disease management by taking evidence and guidelines of medical evidence as guidance. The clinical pathway may include: examination protocols (e.g., ultrasound, X-ray, bone scan, pathology, etc.), clinical treatment protocols (e.g., drug treatment protocols, surgical treatment protocols, etc.), rehabilitation protocols, post-operative or post-discharge follow-up protocols, etc., but are not limited thereto.

Correspondingly, the server device 12 may match the disease species of the patient to be audited in the predetermined correspondence between the disease species and the clinical path to determine the clinical path corresponding to the disease species of the patient to be audited; and outputting a clinical path corresponding to the disease category of the patient to be examined. Optionally, the server device 12 may provide the clinical path corresponding to the disease category of the patient to be examined to the terminal device 11. The terminal device 11 can display the clinical path corresponding to the disease category of the patient to be examined, so that the clinical path of the disease category is recommended, and the standardization of a treatment mode and a treatment program is facilitated.

In addition to the above system embodiments, the present application embodiment also provides a disease category identification method, and the disease category identification method provided by the present application embodiment is exemplarily described below.

Fig. 2 is a schematic flow chart of a disease identification method according to an embodiment of the present application. As shown in fig. 2, the method includes:

201. acquiring medical record data of a patient to be examined.

202. And performing disease feature extraction on the medical record data of the patient to be examined to acquire the disease features of the patient to be examined.

203. And identifying the disease species according to the disease characteristics of the patient to be examined to determine the disease species of the patient to be examined.

The disease category identification method provided by the embodiment can be deployed on any computer equipment. For example, the method can be deployed on a terminal device of a user, and can also be deployed on a server device. No matter what kind of device is used as the execution subject of the disease identification method provided in this embodiment, in step 201, medical record data of a patient to be examined can be acquired. For the terminal device, a medical record providing control can be provided. The user can upload medical record data through the medical record providing control. For the terminal device, in response to the triggering operation of the medical record providing control, data associated with the triggering operation can be acquired as medical record data of a patient to be audited. That is, the data uploaded by the user through the medical record providing control is obtained and used as the medical record data of the patient to be audited.

Or, the terminal device can also read the medical record data of the patient to be examined from the storage medium. The storage medium may be a hard disk fixedly installed on the terminal device, a cloud storage, or an external storage medium such as a usb disk. Optionally, the terminal device may provide a patient identification selection control, through which the user may determine the patient to be audited. Correspondingly, the terminal device can respond to the triggering operation of the patient identification selection control, and acquire the selected patient identification as the identification of the patient to be audited. Further, the terminal device can match the identifier of the patient to be audited in the corresponding relation between the stored patient identifier and the medical record data to determine the medical record data of the patient to be audited.

Aiming at the server-side equipment, the identification of the patient to be audited can be analyzed from the received disease identification request; and matching the identifier of the patient to be audited in the corresponding relation between the patient identifier and the medical record data to obtain the medical record data of the patient to be audited.

Further, in step 202, disease feature extraction may be performed on medical record data of a patient to be examined to obtain disease features of the patient to be examined; and in step 203, disease species identification is performed according to the disease characteristics of the patient to be examined to determine the disease species of the patient to be examined.

Further, if the main execution body of the disease identification method is terminal equipment, the disease species of the patient to be examined can be displayed on a screen; and/or, the disease types of the patients are audited through the audio component. If the main execution body of the disease identification method is the server-side equipment, the disease of the patient to be examined can be sent to the client (such as the terminal equipment) which initiates the disease identification request. Correspondingly, the client can receive the disease species of the patient to be audited and output the disease species of the patient to be audited. Optionally, the client may display the disease species of the patient to be audited on the screen; and/or playing the disease category of the patient to be audited through an audio component, and the like.

In this embodiment, the medical record data of the patient to be audited can be subjected to disease feature extraction, and the disease species of the patient to be audited can be identified according to the disease features of the patient to be audited, so that the disease species of the patient to be audited can be determined, the automatic identification of the disease species of the patient can be realized, and the disease species identification efficiency can be improved.

In the embodiment of the present application, a specific implementation manner of performing disease feature extraction on medical record data of a patient to be examined is not limited. In some embodiments, a plurality of keywords reflecting the disease condition of the patient to be examined can be obtained from medical record data of the patient to be examined. Plural means 2 or more.

In some embodiments, medical record data can be divided into structured medical record data and unstructured medical record data. For structured medical record data, the data can be organized in a format such as a table. For a table, each entry has a field name. Accordingly, field data can be indexed by field name, and the field name and the field data are used as keywords. Such as blood pressure, blood item data, urine routine data, etc. Wherein, the field name and the field data can form a Key-Value (K-V) pair.

For unstructured medical record data, semantic analysis can be performed on the unstructured medical record data to obtain keywords from the unstructured medical record data.

Further, for a plurality of keywords reflecting the symptoms of the patient to be examined, the ICD code of the target keyword in the plurality of keywords can be determined according to the keywords and the ICD code dictionary.

Optionally, the similarity between each keyword and the disease category description in the ICD encoding dictionary may be calculated. Namely, the similarity between the keyword and the disease category description of each disease category in the ICD coding dictionary is calculated. In the embodiments of the present application, for convenience of description, the description of the disease species is simply referred to as the disease species description. In this embodiment, a specific implementation of calculating the similarity between the keyword and the disease category description in the ICD encoding dictionary is not limited.

In other embodiments, vectorization processing may be further performed on the keyword and the disease category description in the ICD encoding dictionary to obtain a vector corresponding to the keyword and a vector corresponding to the disease category description in the ICD encoding dictionary. Further, the distance between the vector corresponding to the keyword and the vector corresponding to the disease category description in the ICD encoding dictionary may be calculated as the similarity between the calculated keyword and the disease category description in the ICD encoding dictionary. The greater the distance between the vector corresponding to the keyword and the vector corresponding to the disease category description in the ICD coding dictionary, the smaller the similarity between the two vectors. The distance between the vectors corresponding to the keywords and the vectors corresponding to the disease type descriptions in the ICD coding dictionary may be a cosine distance, a euclidean distance, a manhattan distance, and the like between the vectors.

Further, a target keyword may be selected from the plurality of keywords according to the similarity between the plurality of keywords and the disease category description in the ICD encoding dictionary, and an ICD encoding corresponding to the disease category description having the highest similarity with the target keyword may be used as the ICD encoding for the target keyword.

Aiming at keywords without ICD codes, such as keywords in the structured medical record data, such as the number of days of stay, leaving mode, department of discharge, various expenses and the like, the structured medical record data can be coded to obtain the coding result of the structured medical record data, and the coding result is used as at least part of disease characteristics of the patient to be audited. Optionally, the structured medical record data can be processed by one-hot encoding (one-hot), normalization, null filling, and the like.

Furthermore, after the disease characteristics of the patient to be audited are obtained, the disease type can be identified according to the disease characteristics of the patient to be audited, so that the disease type of the patient to be audited can be determined.

In some embodiments, the disease characteristics of the patient to be reviewed include: diagnostic features and surgical features. When the disease characteristics of a patient to be examined are subjected to characteristic fusion, the diagnosis characteristics and the operation characteristics can be independently and respectively fused; diagnostic features and surgical features may also be fused together. For a specific implementation of feature fusion for the disease features of the patient to be examined, reference may be made to the related contents of the above system embodiment, which are not described herein again.

Further, the disease characteristics of the patient to be examined or the fused disease characteristics can be input into the disease identification model, and the disease identification model is used for identifying the disease to obtain the disease of the patient to be examined.

The disease identification method provided by the embodiment of the application can be suitable for identifying the disease of a single patient and can also be used for identifying the disease of a plurality of patients in batches. The disease identification method for each of the plurality of patients can refer to the related contents of the above embodiments.

Based on the medical resource auditing method, the medical resource auditing can be performed on the patient to be audited based on the disease type of the patient to be audited and the medical resource standard corresponding to the disease type. The specific implementation mode is as follows:

after acquiring the disease species of the patient to be audited, acquiring the medical resource standard corresponding to the disease species of the patient to be audited; and acquiring the medical resource consumption of the patient to be audited according to the medical record data of the patient to be audited. Correspondingly, the medical resource consumption of the patient to be audited mainly refers to the consumption of the patient to be audited for the medical resource item. The medical resource items may include: the number of the hospitalization days, the total cost of hospitalization, the total cost of medicines, the total cost of medical consumables, the number of operations and the like of the patient to be examined.

Furthermore, the medical resource standard exceeding condition of the patient to be audited can be calculated according to the medical resource consumed by the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited.

In some embodiments, the exceeding medical resource item of the patient to be audited can be determined according to the exceeding degree of the patient to be audited for each medical resource item, and the exceeding medical resource item of the patient to be audited is used as the exceeding medical resource condition of the patient to be audited. Optionally, for each medical resource item, a threshold of the degree of overproof for that medical resource item may be set. The medical resource items with the exceeding degree greater than or equal to the exceeding degree threshold value of the medical resource items can be used as the exceeding medical resource items of the patient to be audited. Optionally, the absolute superscalar value and/or the relative superscalar proportion of the patient to be audited for the superscalar resource item can be used as the medical resource superscalar condition of the patient to be audited.

In other embodiments, the consumption of the patient to be audited for each medical resource item can be calculated, the absolute superscalar value and the relative superscalar proportion of the medical resource standard corresponding to the medical resource item can be calculated, the absolute superscalar value and the relative superscalar proportion of the patient to be audited for the medical resource item can be weighted and summed, and the medical resource superscalar degree of the patient to be audited can be obtained and used as the medical resource superscalar condition of the patient to be audited.

Furthermore, the medical resource standard exceeding condition of the patient to be audited can be output. Optionally, for the server device, the medical resource standard exceeding condition of the patient to be audited can be provided to the client. Optionally, the medical resource standard exceeding condition of the patient to be audited may include: the standard exceeding medical resource item of the patient to be audited, the standard exceeding degree of the patient to be audited aiming at the standard exceeding medical resource item, the absolute standard exceeding value and the relative standard exceeding proportion of the patient to be audited aiming at the standard exceeding medical resource item, the standard exceeding degree of the medical resource of the patient to be audited and the like.

Correspondingly, the client receives the medical resource standard exceeding condition of the patient to be audited, displays the medical resource standard exceeding condition on the screen, and provides reference for medical staff to check the medical resource standard exceeding condition in time and adjust the treatment scheme in time.

If the disease identification method is executed by the client, the condition that medical resources exceed standards can be directly displayed on a screen.

In some embodiments, in addition to considering the medical resource consumption of the patient to be audited relative to the medical resource standard of the patient's race, the historical medical resource consumption of the office in which the patient to be audited is located may be referenced. Based on the above, the medical department of the patient to be examined can be obtained from the medical record data of the patient to be examined; and acquiring the historical per-capita medical resource consumption of the office of treatment. Correspondingly, the absolute superscalar value and the relative superscalar proportion of each medical resource item of the patient to be audited can be calculated according to the medical resource consumption of the patient to be audited, the historical per-patient medical resource consumption of the clinic and the medical resource consumption of the patient to be audited.

In some embodiments, the exceeding medical resource item of the patient to be audited can be determined according to the exceeding degree of the patient to be audited for each medical resource item, and the exceeding medical resource item of the patient to be audited is used as the exceeding medical resource condition of the patient to be audited. Optionally, the absolute superscalar value and/or the relative superscalar proportion of the patient to be audited for the superscalar medical resource item can be used as the superscalar medical resource condition of the patient to be audited.

In other embodiments, the consumption of the patient to be audited for each medical resource item can be calculated, compared with the absolute superscalar value and the relative superscalar proportion of the medical resource standard corresponding to the medical resource item, and the consumption of the patient to be audited for the medical resource item, compared with the average consumption of the patient to be audited for the historical people of the medical resource item in the clinic where the patient to be audited is located, the absolute superscalar values and the relative superscalar proportions of the plurality of medical resource items of the patient to be audited are weighted and summed to obtain the standard-exceeding degree of the medical resource of the patient to be audited, and the standard-exceeding degree of the medical resource of the patient to be audited is used as the standard-exceeding condition of the medical resource of the patient to be audited.

Furthermore, the medical resource standard exceeding condition of the patient to be audited can be output. For a specific implementation of outputting the medical resource standard exceeding condition of the patient to be audited, reference may be made to the relevant contents of the above embodiments, and details are not described herein again.

In the embodiment of the application, in addition to calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited, the medical resource scheduling can be performed on the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited. Optionally, the medical resource item for which the patient to be audited does not meet the medical resource standard can be determined according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited. Aiming at any medical resource item, acquiring the consumption corresponding to the medical resource item from the medical resource consumption of a patient to be examined; acquiring medical resource standard quantity corresponding to the medical resource item from the medical resource standard corresponding to the disease species of the patient to be examined; and judging whether the consumption corresponding to the medical resource item reaches the corresponding medical resource standard quantity, and if not, determining that the medical resource item is the medical resource item which does not reach the medical resource standard.

Further, the difference between the consumption corresponding to the medical resource item which does not meet the medical resource standard of the patient to be audited and the medical resource standard can be calculated; and according to the difference between the consumption amount of the patient to be audited corresponding to the medical resource item which does not reach the medical resource standard and the medical resource standard, scheduling the medical resource corresponding to the medical resource item which does not reach the medical resource standard for the patient to be audited.

In the embodiment of the application, besides the standardization of medical resource reimbursement, clinical paths can be recommended for disease types. Correspondingly, the disease species of the patient to be audited can be matched in the corresponding relation between the predetermined disease species and the clinical path so as to determine the clinical path corresponding to the disease species of the patient to be audited; and outputting a clinical path corresponding to the disease type of the patient to be examined. For a specific embodiment of outputting the clinical path corresponding to the disease category of the patient to be audited, reference may be made to the above-mentioned related content of outputting the disease category of the patient to be audited, and details are not described here.

The disease identification method provided by the embodiment of the application can be deployed on any computer equipment. Optionally, the disease identification method provided by the embodiment of the application can be deployed in a cloud to serve as a SaaS service. For the server device with the SaaS service deployed, the steps in the above disease identification method may be executed in response to a service request of other client devices. As shown in fig. 3, the method mainly includes:

301. and responding to the disease identification request, and acquiring medical record data of the patient to be examined.

302. And performing disease feature extraction on the medical record data of the patient to be examined to acquire the disease features of the patient to be examined.

303. And identifying the disease species according to the disease characteristics of the patient to be examined to determine the disease species of the patient to be examined.

304. And providing the disease species of the patient to be audited to the client sending the disease species identification request, so that the client can output the disease species of the patient to be audited.

The disease identification method provided by the embodiment can be deployed in a cloud end and provides disease identification service for a user. The cloud end can be a private cloud of a hospital. The server-side equipment which is deployed with the disease identification method can respond to the disease identification request and acquire medical record data of a patient to be examined of the patient to be examined. Alternatively, the server device may provide an Application Program Interface (API) to the user, and the service requester may call the API to invoke the image processing service. Accordingly, the disease identification request is implemented as a call event generated by calling the API. The service requester and the server device may be communicatively connected, and the communication connection manner may refer to the related contents of the above embodiments, which is not described herein again. Alternatively, the service requester may also Call the disease identification service through a Remote Procedure Call (RPC) or a Remote Direct data Access (RDMA) technique.

For the description of

steps

301 and 303, reference may be made to fig. 2 and its related contents in the alternative embodiment. Further, after the disease category of the patient to be audited is determined, the disease category of the patient to be audited can be provided to the client side sending the disease category identification request. And for the client, receiving the disease species of the patient to be audited, outputting the disease species of the patient to be audited, and the like. For a specific implementation of the client outputting the disease category of the patient to be audited, reference may be made to the relevant contents of the above embodiments, and details are not described here.

Optionally, in some embodiments, a medical resource standard corresponding to the disease type of the patient to be audited may also be obtained; acquiring medical resource consumption of a patient to be audited according to medical record data of the patient to be audited; calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumed by the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited; and providing the medical resource exceeding condition of the patient to be audited to the client side, so that the client side can output the medical resource exceeding condition of the patient to be audited. For a specific implementation of calculating the medical resource standard exceeding condition of the patient to be audited, reference may be made to the relevant contents of the above embodiments, and details are not described herein again.

It should be noted that the execution subjects of the steps of the methods provided in the above embodiments may be the same device, or different devices may be used as the execution subjects of the methods. For example, the execution subjects of

steps

201 and 202 may be device a; for another example, the execution subject of step 201 may be device a, and the execution subject of step 202 may be device B; and so on.

In addition, in some of the flows described in the above embodiments and the drawings, a plurality of operations are included in a specific order, but it should be clearly understood that the operations may be executed out of the order presented herein or in parallel, and the sequence numbers of the operations, such as 201, 202, etc., are merely used for distinguishing different operations, and the sequence numbers do not represent any execution order per se. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel.

Accordingly, embodiments of the present application also provide a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the above-mentioned disease species identification method.

Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application. As shown in fig. 4, the computer apparatus includes: a memory 40a and a processor 40 b; the memory 40a is used for storing computer programs.

The processor 40b is coupled to the memory 40a for executing a computer program for: acquiring medical record data of a patient to be examined; performing disease feature extraction on medical record data of a patient to be audited to obtain disease features of the patient to be audited; and according to the disease characteristics of the patient to be examined, identifying the disease species to determine the disease species of the patient to be examined.

In some embodiments, the processor 40b, when acquiring medical record data of a patient to be reviewed, is specifically configured to: and responding to the triggering operation of the medical record providing control, and acquiring data associated with the triggering operation as medical record data of the patient to be audited.

Optionally, the processor 40b is further configured to: the disease type of the patient to be examined is displayed on the screen 40 c.

In other embodiments, the processor 40b, when acquiring medical record data of a patient to be reviewed, is specifically configured to: analyzing the identification of the patient to be audited from the received identification request of the disease type; and matching the identifier of the patient to be audited in the corresponding relation between the patient identifier and the medical record data to obtain the medical record data of the patient to be audited.

Optionally, the processor 40b is further configured to: the disease category of the patient to be audited is sent to the client terminal which provides the identification request of the disease category through the communication component 40d, so that the client terminal can output the disease category of the patient to be audited.

In still other embodiments, the processor 40b, when performing disease feature extraction on medical record data of a patient to be examined, is specifically configured to: acquiring a plurality of keywords reflecting the symptoms of a patient to be audited from medical record data of the patient to be audited; determining ICD codes of target keywords in the plurality of keywords according to the keywords and the international disease classification ICD code dictionary; and vectorizing the ICD codes of the target keywords to obtain vector characteristics of the target keywords, wherein the vector characteristics are used as at least part of disease characteristics of the patient to be examined.

Optionally, the processor 40b, when obtaining the keyword reflecting the condition of the patient to be audited, is specifically configured to: dividing unstructured medical record data from medical record data of a patient to be examined; and performing semantic analysis on the unstructured medical record data to obtain a plurality of keywords from the unstructured medical record data.

Optionally, the processor 40b, when determining the ICD code of the target keyword in the keywords, is specifically configured to: calculating the similarity between each keyword and disease type description in the ICD coding dictionary; selecting a target keyword from the multiple keywords according to the similarity between the multiple keywords and disease type description in the ICD coding dictionary; and using the ICD code corresponding to the disease category description with the highest similarity with the target keyword as the ICD code of the target keyword.

Optionally, the processor 40b, when performing disease feature extraction on medical record data of a patient to be examined, is further configured to: dividing structured medical record data from medical record data of a patient to be examined; and coding the structured medical record data to obtain a coding result of the structured medical record data, wherein the coding result is used as at least one part of disease characteristics of the patient to be examined.

In some embodiments, the processor 40b, when performing the disease identification based on the disease characteristics of the patient to be examined, is specifically configured to: performing feature fusion on the disease features of the patient to be examined to obtain fused disease features of the patient to be examined; and inputting the disease characteristics of the patient to be examined after fusion into a disease identification model for disease identification so as to determine the disease of the patient to be examined.

Optionally, the processor 40b, when performing feature fusion on the disease features of the patient to be audited, is specifically configured to: and performing weighted summation on the disease characteristics of the patient to be audited to obtain the fused and post-disease characteristics of the patient to be audited.

Optionally, the processor 40b is further configured to: acquiring historical medical record data and disease classification results of historical patients before inputting the disease characteristics of the patients to be examined after fusion into a disease identification model for disease identification; extracting disease characteristics of historical medical record data to obtain the disease characteristics of historical patients; and the disease classification result of the historical patient is used as supervision, and model training is carried out by using the disease characteristics of the historical patient to obtain a disease identification model.

In some embodiments of the present application, the processor 40b is further configured to: acquiring medical resource standards corresponding to the disease species of a patient to be examined; acquiring medical resource consumption of a patient to be audited according to medical record data of the patient to be audited; and calculating the medical resource standard exceeding condition of the patient to be examined according to the medical resource consumption of the patient to be examined and the medical resource standard corresponding to the disease category of the patient to be examined.

Optionally, the processor 40b is further configured to: acquiring a medical treatment department of a patient to be examined from medical record data of the patient to be examined; and acquiring the historical per-person medical resource consumption of the office of the doctor.

Correspondingly, when the processor 40b calculates that the medical resource of the patient to be audited exceeds the standard, it is specifically configured to: calculating an absolute superscalar value and a relative superscalar proportion of the patient to be audited aiming at each medical resource item according to the medical resource consumption of the patient to be audited, the medical resource standard corresponding to the disease type of the patient to be audited and the historical per-person medical resource consumption of the consulting department; and weighting and summing the absolute superscalar values and the relative superscalar proportions of the patient to be audited aiming at the plurality of medical resource items to obtain the medical resource superscalar degree of the patient to be audited, wherein the medical resource superscalar degree is used as the medical resource superscalar condition of the patient to be audited.

Optionally, the processor 40b is further configured to: carrying out weighted summation on the absolute exceeding standard value and the relative exceeding standard proportion of the patient to be audited aiming at any medical resource item to obtain the exceeding standard degree of the patient to be audited aiming at the medical resource item; and determining the overproof medical resource items of the patient to be audited according to the overproof degree of the patient to be audited aiming at each medical resource item, and taking the overproof medical resource items as the overproof condition of the medical resource of the patient to be audited.

Optionally, the processor 40b, when obtaining the medical resource consumption of the patient to be audited, is further configured to: acquiring consumption of a patient to be audited corresponding to at least one medical resource item from medical record data of the patient to be audited, and taking the consumption as the medical resource consumption of the patient to be audited; wherein the at least one medical resource item includes: at least one of the number of hospitalization days, total cost of hospitalization, total cost of medicine, total cost of medical consumables and the number of operations of the patient to be examined.

Optionally, the processor 40b is further configured to: and outputting the medical resource standard exceeding condition of the patient to be audited.

In some embodiments of the present application, the processor 40b is further configured to: responding to the disease identification request, and acquiring medical record data of a patient to be examined of the patient to be examined; performing disease feature extraction on medical record data of a patient to be examined to obtain disease features of the patient to be examined; according to the disease characteristics of the patient to be examined, identifying the disease species to determine the disease species of the patient to be examined; the disease category of the patient to be examined is provided to the client sending the disease category identification request through the communication component 40d, so that the client can output the disease category of the patient to be examined.

Optionally, the processor 40b is further configured to: acquiring medical resource standards corresponding to the disease species of a patient to be examined; acquiring medical resource consumption of a patient to be audited according to medical record data of the patient to be audited; calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumed by the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited; and the medical resource standard exceeding condition of the patient to be audited is provided to the client through the communication component 40d, so that the client can output the medical resource standard exceeding condition of the patient to be audited.

In some embodiments, the processor 40b is further configured to: and performing medical resource scheduling on the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited.

Optionally, when the processor 40b performs medical resource scheduling on the patient to be audited, the processor is specifically configured to: determining medical resource items of which the medical resource standards are not met by the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standards corresponding to the disease species of the patient to be audited; calculating the difference between the consumption corresponding to the medical resource item which does not reach the medical resource standard of the patient to be audited and the medical resource standard; and according to the difference between the consumption amount of the patient to be audited corresponding to the medical resource item which does not reach the medical resource standard and the medical resource standard, scheduling the medical resource corresponding to the medical resource item which does not reach the medical resource standard for the patient to be audited.

In other embodiments, processor 40b is further configured to: matching the disease species of the patient to be examined in the corresponding relation between the predetermined disease species and the clinical path to determine the clinical path corresponding to the disease species of the patient to be examined; and outputting a clinical path corresponding to the disease category of the patient to be examined.

In some optional embodiments, as shown in fig. 4, the computer device may further include: power component 40e, audio component 40f, and the like. Only some of the components shown in fig. 4 are schematically shown, and it is not meant that the computer device must include all of the components shown in fig. 4, nor that the computer device only includes the components shown in fig. 4.

In embodiments of the present application, the memory is used to store computer programs and may be configured to store other various data to support operations on the device on which it is located. Wherein the processor may execute a computer program stored in the memory to implement the corresponding control logic. The memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

In the embodiments of the present application, the processor may be any hardware processing device that can execute the above described method logic. Alternatively, the processor may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or a Micro Controller Unit (MCU); programmable devices such as Field-Programmable Gate arrays (FPGAs), Programmable Array Logic devices (PALs), General Array Logic devices (GAL), Complex Programmable Logic Devices (CPLDs), etc. may also be used; or Advanced Reduced Instruction Set (RISC) processors (ARM), or System On Chips (SOC), etc., but is not limited thereto.

In embodiments of the present application, the communication component is configured to facilitate wired or wireless communication between the device in which it is located and other devices. The device in which the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, 4G, 5G or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component may also be implemented based on Near Field Communication (NFC) technology, Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, or other technologies.

In the embodiment of the present application, the display assembly may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display assembly includes a touch panel, the display assembly may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

In embodiments of the present application, a power supply component is configured to provide power to various components of the device in which it is located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.

In embodiments of the present application, the audio component may be configured to output and/or input audio signals. For example, the audio component includes a Microphone (MIC) configured to receive an external audio signal when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals. For example, for devices with language interaction functionality, voice interaction with a user may be enabled through an audio component, and so forth.

The computer equipment provided by the embodiment can extract disease characteristics of medical record data of a patient to be audited, and identify the disease type of the patient to be audited according to the disease characteristics of the patient to be audited, so that the disease type of the patient to be audited is determined, the automatic identification of the disease type of the patient is realized, and the identification efficiency of the disease type is improved.

It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A disease species identification method is characterized by comprising the following steps:

acquiring medical record data of a patient to be examined;

2. The method of claim 1, wherein the obtaining medical record data of the patient to be reviewed comprises:

responding to the triggering operation of the medical record providing control, and acquiring data associated with the triggering operation as medical record data of the patient to be audited;

alternatively, the first and second electrodes may be,

analyzing the identification of the patient to be audited from the received identification request of the disease type; and matching the identifier of the patient to be audited in the corresponding relation between the patient identifier and the medical record data to obtain the medical record data of the patient to be audited.

3. The method of claim 2, further comprising:

displaying the disease species of the patient to be examined on a screen;

alternatively, the first and second electrodes may be,

and sending the disease species of the patient to be audited to the client initiating the disease species identification request, so that the client can output the disease species of the patient to be audited.

4. The method according to claim 1, wherein the performing disease feature extraction on the medical record data of the patient to be examined to obtain the disease feature of the patient to be examined comprises:

acquiring a plurality of keywords reflecting the symptoms of the patient to be audited from the medical record data of the patient to be audited;

determining ICD codes of target keywords in the plurality of keywords according to the keywords and an ICD code dictionary for international disease classification;

vectorizing the ICD codes of the target keywords to obtain vector characteristics of the target keywords, wherein the vector characteristics are used as at least one part of disease characteristics of the patient to be examined.

5. The method according to claim 4, wherein the obtaining of the keyword reflecting the condition of the patient to be examined from the medical record data of the patient to be examined comprises:

dividing unstructured medical record data from the medical record data of the patient to be examined;

performing semantic analysis on the unstructured medical record data to obtain the plurality of keywords from the unstructured medical record data.

6. The method according to claim 4, wherein determining the ICD code of the target keyword among the keywords according to the keywords and the ICD code dictionary for international disease classification comprises:

calculating the similarity between each keyword and the disease species description in the ICD coding dictionary;

selecting a target keyword from the keywords according to the similarity between the keywords and disease species description in the ICD coding dictionary;

and taking the ICD code corresponding to the disease category description with the highest similarity with the target keyword as the ICD code of the target keyword.

7. The method according to claim 5, wherein the performing disease feature extraction on the medical record data of the patient to be examined to obtain the disease feature of the patient to be examined further comprises:

dividing structured medical record data from the medical record data of the patient to be examined;

and coding the structured medical record data to obtain a coding result of the structured medical record data, wherein the coding result is used as at least one part of disease characteristics of the patient to be examined.

8. The method according to claim 1, wherein the identification of the disease type based on the disease characteristics of the patient to be examined comprises:

performing feature fusion on the disease features of the patient to be examined to obtain fused disease features of the patient to be examined;

and inputting the disease characteristics of the patient to be examined after fusion into a disease identification model for disease identification so as to determine the disease of the patient to be examined.

9. The method according to claim 8, wherein the feature fusion of the disease features of the patient to be examined comprises:

and carrying out weighted summation on the disease characteristics of the patient to be audited to obtain the fused and post-audited disease characteristics of the patient.

10. The method according to claim 8, before inputting the merged disease features of the patient to be examined into a disease recognition model for disease recognition, further comprising:

acquiring historical medical record data and disease classification results of historical patients;

extracting disease characteristics of the historical medical record data to obtain the disease characteristics of the historical patient;

and taking the disease classification result of the historical patient as supervision, and performing model training by using the disease characteristics of the historical patient to obtain the disease identification model.

11. The method of any one of claims 1-10, further comprising:

acquiring medical resource standards corresponding to the disease species of the patient to be audited;

acquiring medical resource consumption of a patient to be audited according to medical record data of the patient to be audited;

and calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited.

12. The method of claim 11, further comprising:

acquiring the medical record data of the patient to be examined and the visiting department of the patient to be examined;

acquiring the historical per-person medical resource consumption of the office of treatment;

the calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited comprises the following steps:

calculating an absolute over-standard value and a relative over-standard proportion of the patient to be audited aiming at each medical resource item according to the medical resource consumption of the patient to be audited, the medical resource standard corresponding to the disease type of the patient to be audited and the historical per-person medical resource consumption of the consulting department;

and carrying out weighted summation on the absolute superscalar values and the relative superscalar proportions of the patient to be audited aiming at the plurality of medical resource items to obtain the superscalar degree of the medical resources of the patient to be audited, wherein the superscalar degree of the medical resources of the patient to be audited is used as the superscalar condition of the medical resources of the patient to be audited.

13. The method of claim 12, further comprising:

carrying out weighted summation on the absolute superscalar value and the relative superscalar proportion of the patient to be audited aiming at any medical resource item to obtain the superscalar degree of the patient to be audited aiming at the medical resource item;

and determining the overproof medical resource items of the patient to be audited according to the overproof degree of the patient to be audited aiming at each medical resource item, and taking the overproof medical resource items as the overproof medical resource conditions of the patient to be audited.

14. The method according to claim 11, wherein the obtaining the medical resource consumption of the patient to be reviewed based on the medical record data of the patient to be reviewed comprises:

acquiring consumption of the patient to be audited corresponding to at least one medical resource item from the medical record data of the patient to be audited, and taking the consumption as the medical resource consumption of the patient to be audited;

the at least one medical resource item includes: and at least one of the number of hospitalization days, total cost of hospitalization, total cost of medicine, total cost of medical consumables and the number of operations of the patient to be audited.

15. The method of claim 11, further comprising:

and outputting the medical resource standard exceeding condition of the patient to be audited.

16. The method of claim 11, further comprising:

and scheduling the medical resources of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited.

17. The method according to claim 16, wherein the scheduling the medical resource of the patient to be audited according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease category of the patient to be audited comprises:

determining medical resource items of the patient to be audited, which do not meet the medical resource standard, according to the medical resource consumption of the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited;

calculating the difference between the consumption of the patient to be audited corresponding to the medical resource item which does not reach the medical resource standard and the medical resource standard;

and scheduling the medical resource corresponding to the medical resource item which does not reach the medical resource standard for the patient to be audited according to the difference between the consumption corresponding to the medical resource item which does not reach the medical resource standard and the medical resource standard of the patient to be audited.

18. The method of any one of claims 1-10, further comprising:

matching the disease species of the patient to be examined in a corresponding relation between a predetermined disease species and a clinical path to determine the clinical path corresponding to the disease species of the patient to be examined; and outputting the clinical path corresponding to the disease category of the patient to be examined.

19. A disease species identification method is characterized by comprising the following steps:

responding to the disease identification request, and acquiring medical record data of a patient to be audited;

20. The method of claim 19, further comprising:

calculating the medical resource standard exceeding condition of the patient to be audited according to the medical resource consumed by the patient to be audited and the medical resource standard corresponding to the disease type of the patient to be audited;

and providing the medical resource standard exceeding condition of the patient to be audited to the client, so that the client can output the medical resource standard exceeding condition of the patient to be audited.

21. A data processing system, comprising: the system comprises terminal equipment and server-side equipment;

the server device is configured to: responding to the disease identification request, and acquiring medical record data corresponding to the patient identification as medical record data of the patient to be examined; performing disease feature extraction on the medical record data of the patient to be examined to obtain the disease feature of the patient to be examined; according to the disease characteristics of the patient to be examined, identifying the disease species to determine the disease species of the patient to be examined; and providing the disease species of the patient to be audited for the terminal equipment so that the terminal equipment can output the disease species of the patient to be audited.

22. A computer device, comprising: a memory and a processor; wherein the memory is used for storing a computer program;

the processor is coupled to the memory for executing the computer program for performing the steps of the method of any of claims 1-20.

23. A computer-readable storage medium having stored thereon computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of any one of claims 1-20.