CN111105852A

CN111105852A - Electronic medical record recommendation method and device, terminal and storage medium

Info

Publication number: CN111105852A
Application number: CN201911214460.3A
Authority: CN
Inventors: 李想; 沈宏
Original assignee: Shanghai United Imaging Intelligent Healthcare Co Ltd
Current assignee: Shanghai United Imaging Intelligent Healthcare Co Ltd
Priority date: 2019-12-02
Filing date: 2019-12-02
Publication date: 2020-05-05
Anticipated expiration: 2039-12-02
Also published as: CN111105852B

Abstract

The invention discloses an electronic medical record recommendation method, an electronic medical record recommendation device, a terminal and a storage medium, wherein the electronic medical record recommendation method comprises the following steps: determining a first disease type and at least one first disease condition corresponding to a target electronic medical record to be processed; matching a second disease type corresponding to the historical electronic medical records in a preset historical electronic medical record library with the first disease type, and determining matched candidate historical electronic medical records to obtain a candidate historical electronic medical record set; determining the similarity of the disease symptoms corresponding to the candidate historical electronic medical records according to the similarity between at least one second disease symptom corresponding to the candidate historical electronic medical records and the at least one first disease symptom; and determining at least one candidate electronic medical history with the similarity of diseases meeting preset conditions in the candidate electronic medical history set as the electronic medical history to be recommended, and displaying the electronic medical history to be recommended. The invention improves the recommendation efficiency of the electronic medical record.

Description

Electronic medical record recommendation method and device, terminal and storage medium

Technical Field

The invention relates to the technical field of medical treatment, in particular to an electronic medical record recommendation method, device, terminal and storage medium.

Background

With the development of the intelligence of medical systems, electronic medical records have been widely used for storing medical data, which may include information on a plurality of aspects, such as chief complaints, medical history, examinations, and diagnoses.

At present, when doctors diagnose diseases, the treatment scheme of the diseases needs to reference the past diagnosis records, and then the filling of the current treatment advice is performed in the electronic medical records, so that the computer system needs to recommend the historical electronic medical records. In the related art, when recommendation of historical electronic medical records is performed, the recommendation process is not only complex, but also time-consuming, and the recommendation efficiency of the electronic medical records is low.

Disclosure of Invention

In order to solve the problems in the prior art, embodiments of the present invention provide an electronic medical record recommendation method, apparatus, terminal, and storage medium. The technical scheme is as follows:

in one aspect, an electronic medical record recommendation method is provided, and the method includes:

determining a first disease type and at least one first disease condition corresponding to a target electronic medical record to be processed;

matching a second disease type corresponding to the historical electronic medical records in a preset historical electronic medical record library with the first disease type, and determining matched candidate historical electronic medical records to obtain a candidate historical electronic medical record set;

determining the similarity of the disease symptoms corresponding to the candidate historical electronic medical records according to the similarity between at least one second disease symptom corresponding to the candidate historical electronic medical records in the candidate historical electronic medical record set and the at least one first disease symptom;

and determining at least one candidate electronic medical record of which the disease similarity meets a preset condition in the candidate electronic medical record sets as the historical electronic medical record to be recommended, and displaying the historical electronic medical record to be recommended.

In another aspect, an electronic medical record recommendation apparatus is provided, the apparatus includes:

the first determining module is used for determining a first disease type and at least one first disease corresponding to a target electronic medical record to be processed;

the second determining module is used for matching a second disease type corresponding to the historical electronic medical records in the preset historical electronic medical record library with the first disease type, and determining matched candidate historical electronic medical records to obtain a candidate historical electronic medical record set;

a third determining module, configured to determine, according to a similarity degree between at least one second medical condition and the at least one first medical condition that correspond to the candidate electronic medical records in the candidate electronic medical record set, a medical condition similarity corresponding to the candidate electronic medical record;

and the recommending module is used for determining at least one candidate historical electronic medical record in the candidate historical electronic medical record set, of which the disease similarity meets a preset condition, as a historical electronic medical record to be recommended and displaying the historical electronic medical record to be recommended.

As an optional implementation manner, the apparatus further includes a building module for building the preset electronic medical history library, where the building module includes:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plurality of historical electronic medical records;

the fourth determining module is used for determining a second disease type and at least one second disease corresponding to each historical electronic medical record in the plurality of historical electronic medical records;

the first relation establishing module is used for taking the second disease type and at least one second disease as index information of a corresponding historical electronic medical record and establishing a mapping relation between the historical electronic medical record and the index information;

and the creating module is used for creating the preset historical electronic medical record library according to the mapping relation.

As an optional implementation, the first determining module includes:

the second acquisition module is used for acquiring the text content of the target electronic medical record to be processed;

the classification processing module is used for classifying the text content based on a disease classification model to obtain a first disease type corresponding to the target electronic medical record;

the named entity recognition module is used for carrying out named entity recognition on the text content based on a named entity recognition model to obtain at least one named entity;

the first display module is used for displaying the at least one named entity;

a fifth determining module, configured to determine, according to a selection instruction for a named entity of the at least one named entity, a target named entity, where the target named entity serves as the at least one first condition.

As an optional implementation, the third determining module includes:

the first mapping module is used for mapping the at least one first disease into first word vectors respectively to obtain a first word vector set;

the second mapping module is used for mapping at least one second disease corresponding to the candidate historical electronic medical records into a second word vector respectively aiming at each candidate historical electronic medical record in the candidate historical electronic medical record set to obtain a second word vector set;

the first calculation module is used for calculating the similarity between a first word vector in the first word vector set and a second word vector in the second word vector set to obtain a similarity set corresponding to the candidate historical electronic medical record;

the second calculation module is used for calculating the average value of the similarity in the similarity set to obtain the average similarity; and the average similarity is used as the symptom similarity corresponding to the candidate historical electronic medical record.

As an optional implementation, the recommendation module includes:

the arrangement module is used for sequentially arranging the candidate historical electronic medical records according to the disease similarity;

and the third acquisition module is used for acquiring the candidate historical electronic medical records at the preset arrangement position to obtain the historical electronic medical records to be recommended.

As an optional implementation, the apparatus further comprises:

the fourth acquisition module is used for acquiring target text information in the historical electronic medical record to be recommended;

the word segmentation processing module is used for carrying out word segmentation processing on the target text information to obtain a word set;

a sixth determining module, configured to determine a target word whose word frequency of the word in the word set exceeds a preset word frequency, to obtain a target word set;

and the second relation establishing module is used for establishing the incidence relation between the target word set and the target electronic medical record.

As an optional implementation, the apparatus further comprises:

the first response module is used for responding to the target processing of the target electronic medical record and acquiring the target word set according to the incidence relation;

the second display module is used for displaying the target words in the target word set;

the second response module is used for responding to a selection instruction of the target word and determining an interested word;

and the result generation module is used for generating a processing result of the target processing according to the interested words.

In another aspect, a terminal is provided, which includes a processor and a memory, where at least one instruction, at least one program, a code set, or a set of instructions is stored in the memory, and the at least one instruction, the at least one program, the code set, or the set of instructions is loaded and executed by the processor to implement the above electronic medical record recommendation method.

In another aspect, a computer readable storage medium is provided, in which at least one instruction, at least one program, a set of codes, or a set of instructions is stored, and loaded and executed by a processor to implement the electronic medical record pushing method as described above.

According to the embodiment of the invention, the candidate electronic history medical record sets matched with the target electronic medical record to be processed are determined through matching of disease types, then the disease similarity corresponding to each candidate electronic history medical record is determined based on the similarity between the disease of the candidate electronic history medical record and the disease of the target electronic medical record, and further the to-be-recommended electronic history medical record with the disease similarity meeting the preset condition is screened out from the candidate electronic history medical record sets and displayed.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of an electronic medical record recommendation method according to an embodiment of the present invention;

FIG. 2 is a flow chart illustrating a method for constructing a preset electronic history record database according to an embodiment of the present invention;

FIG. 3 is a flowchart illustrating another method for recommending an electronic medical record according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating another method for recommending an electronic medical record according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic medical record recommendation device according to an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of another electronic medical record recommendation apparatus according to an embodiment of the present invention;

fig. 7 is a block diagram of a hardware structure of a terminal according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Referring to fig. 1, which is a schematic flow chart illustrating an electronic medical record recommendation method according to an embodiment of the present invention, the electronic medical record recommendation method according to the embodiment of the present invention can be applied to an electronic medical record recommendation apparatus according to an embodiment of the present invention, and the electronic medical record recommendation apparatus can be configured in an electronic device such as a terminal or a server. The terminal can be a hardware device with various operating systems, such as a mobile phone, a tablet computer, a personal digital assistant and the like; the server may comprise a server operating independently, or a distributed server, or a server cluster consisting of a plurality of servers.

Further, it should be noted that the present specification provides the method steps as described in the examples or flowcharts, but may include more or less steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In actual system or product execution, sequential execution or parallel execution (e.g., parallel processor or multi-threaded environment) may be possible according to the embodiments or methods shown in the figures.

The following describes in detail an electronic medical record recommendation method with reference to a specific embodiment from the perspective of a terminal, and as shown in fig. 1, the method may include:

s101, determining a first disease type and at least one first disease corresponding to a target electronic medical record to be processed.

The target electronic medical record to be processed is an electronic medical record which needs to be completed by a doctor, and the target electronic medical record can be but is not limited to an electronic medical record which includes a treatment recommendation to be filled.

A condition is an outward manifestation of an abnormal state of the body, which is associated with a particular disease type. In the embodiments of the present disclosure, the first disease condition may be any disease condition corresponding to the associated disease type, and preferably, the first disease condition may be a key disease condition or an important disease condition corresponding to the associated disease type, where the key disease condition or the important disease condition refers to a main appearance characteristic when the body is in an abnormal state, and is a disease condition having a strong relationship with the disease type. For example, the disease type is nephritis, and the corresponding disorders may include, but are not limited to, edema, proteinuria, hypertension, pregnancy, etc., wherein the key or important disorders may be hypertension, pregnancy.

In this embodiment of the present specification, the first disease type of the target electronic medical record may be determined based on a pre-trained disease classification model, and the first disease condition of the target electronic medical record may be determined based on a pre-trained named entity model, and therefore, before step S101, the method further includes a step of training a disease classification model and a step of training a named entity model.

For training a disease classification model, in practical applications, before training, a classification training sample set may be determined, where the classification training sample set includes a plurality of classification training samples, each classification training sample includes a historical electronic medical record and a disease type corresponding to the historical electronic medical record, and for example, the training sample set is denoted as X ═ { X ═ X₁,x₂……x_n}，Wherein x is₁Representing a training sample. The historical electronic medical records in the classification training samples can be any electronic medical records with specific disease types in an electronic medical record library.

The disease classification model to be trained can comprise a text processing word vector embedding layer, a bidirectional cyclic neural network layer, a pooling layer and an output layer which are sequentially connected, wherein the text processing word vector embedding layer is used for carrying out word vector coding on the text content of the input historical electronic medical record to obtain a corresponding word vector e (w); the bidirectional cyclic neural network layer is used for acquiring context coding information in the text content of the historical electronic medical record according to the word vectors e (w) to respectively obtain the vectors R_leftSum vector R_rightWherein, the vector R_leftCorresponding to the above coding information, the R vector right corresponds to the below coding information; the pooling layer is used for performing down-sampling operation, that is, returning the maximum value in the sampling window as down-sampling output, and in specific implementation, the word vectors e (w) and the vector R_leftSum vector R_rightAnd splicing to obtain a splicing vector, and then taking the splicing vector as the input of the pooling layer. In the disease classification model, because each layer outputs a linear function of the previous layer, considering that data is not linearly separable in practical application, a non-linear factor can be introduced by adding an activation function, namely adding an activation function layer before a pooling layer, and because the Sigmoid activation function is in the state of [ -1,1 ] at the input]In between, the function value is sensitive to change, and the sensitivity is lost once the interval is approached or exceeded, and the function is in a saturation state, so in this specification, the activation function of the activation function layer may adopt a tanh activation function.

The output layer can identify disease categories of the historical electronic medical records and output corresponding category labels, the output layer can output the category labels by adopting a softmax function, and the softmax function comprises a nonlinear classifier and is used for performing category classification training on the historical electronic medical records.

In the training process of the disease classification model, the training target is that the prediction class label output by the model is as close as possible to the disease type (namely, the labeling class label) of the corresponding historical electronic medical record in the input training sample, based on the training target, the loss value of the disease classification model can be determined according to the output prediction class label and the input disease type (namely, the labeling class label), and the parameter of the disease classification model is adjusted based on the loss value until the training end condition is met. The training end condition may be that the loss value of the disease classification model is in a convergence state, or that the loss value is smaller than a preset value, and may be specifically set according to an actual requirement.

After the disease classification model is trained, when the first disease type corresponding to the target electronic medical record to be processed is determined, the text content of the target electronic medical record to be processed can be obtained, and then the text content is classified based on the trained disease classification model to obtain the first disease type corresponding to the target electronic medical record. The text content of the target electronic medical record can be all record information currently contained in the target electronic medical record.

Named Entity Recognition (NER), also referred to as "proper name Recognition", refers to Recognition of entities having specific meanings in text, and may include, but is not limited to, names of people, places, disease states, organizations, works, network vocabularies having specific meanings, other proper nouns, and the like.

For training a named entity recognition model, in practical application, a named entity recognition training sample set may be determined before training, where the named entity recognition training sample set includes a large number of symptoms in the medical field, and the named entity recognition model to be trained is pre-trained through the large number of symptoms to obtain model parameters during convergence, and the named entity recognition model including the model parameters during convergence is the trained named entity recognition model used in the embodiments of the present specification.

The named entity recognition model to be trained may be, but is not limited to, a BERT (bidirectional encoding reconstruction from transforms) network model, and the BERT model may employ a 12-layer bidirectional transform encoder as a feature extractor.

After the named entity recognition model is trained, when at least one first medical condition corresponding to a target electronic medical record to be processed is determined, text content of the target electronic medical record can be input into the named entity recognition model to perform named entity recognition on the text content to obtain at least one named entity, then the at least one named entity is displayed, the target named entity is determined according to a selection instruction of the named entity in the at least one named entity, and the target named entity serves as the at least one first medical condition corresponding to the target electronic medical record. In practical application, the user can select at least one first disease corresponding to the target electronic medical record of the first disease type from the displayed at least one named entity according to experience.

S103, matching a second disease type corresponding to the historical electronic medical records in the preset historical electronic medical record library with the first disease type, and determining matched candidate historical electronic medical records to obtain a candidate historical electronic medical record set.

In the embodiment of the present specification, the preset electronic history medical record library is an electronic medical record library with index information obtained by processing the electronic history medical record. Based on this, in this embodiment of the present specification, before step S103, the method may further include a step of constructing a preset electronic history record library, and as shown in fig. 2, the constructing of the preset electronic history record library may include the following steps S1031 to S1037:

and S1031, acquiring a plurality of historical electronic medical records.

In view of the subsequent need to obtain the relevant processing results of the target electronic medical records based on the analysis of the plurality of historical electronic medical records, the plurality of historical electronic medical records used for constructing the preset historical electronic medical record library may be electronic medical records including processing results corresponding to operations to be processed, for example, the plurality of historical electronic medical records are electronic medical records including treatment schemes.

S1033, determining a second disease type and at least one second disease condition corresponding to each historical electronic medical record in the plurality of historical electronic medical records.

The second condition can be any condition corresponding to the associated disease type, and preferably, the second condition can be a key condition or important condition corresponding to the associated disease type.

The determination mode of the disease type and the disease symptoms of each historical electronic medical record in the plurality of historical electronic medical records is similar to that of the target electronic medical record to be processed, and the text content of each historical electronic medical record can be obtained; classifying the text content based on the trained disease classification model to obtain a second disease type of each historical electronic medical record; the method comprises the steps of conducting named entity recognition on text contents based on a trained named entity recognition model to obtain at least one named entity corresponding to each historical electronic medical record, displaying the at least one named entity, and determining a target named entity according to a selection instruction of the named entity in the at least one named entity, wherein the target named entity is the second medical condition of the corresponding historical electronic medical record. In order to improve the recommendation efficiency and recommendation accuracy of the electronic medical record, it is preferable to determine at least one second key condition of the historical electronic medical record based on the named entity recognition model, as shown in fig. 2, considering that the key condition or the important condition has a strong correlation with the disease type.

S1035, taking the second disease type and at least one second disease as index information of a corresponding historical electronic medical record, and establishing a mapping relation between the historical electronic medical record and the index information.

S1037, creating the preset historical electronic medical record library according to the mapping relation.

Through the processing, each historical electronic medical record in the preset historical electronic medical record library has the index information which corresponds to the historical electronic medical record one by one, the index information comprises the disease type and at least one second disease of the historical electronic medical record, namely the index information reflects the incidence relation between the disease type and the disease, and the electronic medical record is recommended later only by matching according to the index information, so that the matching efficiency is improved.

Based on the above description, when step S103 is executed, the disease type may be matched based on the index information, the index information to which the second disease type having the same type as the first disease type belongs may be determined, the candidate index information may be obtained, and a plurality of candidate index information may be generally screened outThe history electronic medical records corresponding to the candidate index information constitute a candidate history electronic medical record set, and the candidate history electronic medical record set is expressed as { C'₁,C′₂,……,C′_qQ represents the number of the candidate historical electronic medical records in the candidate historical electronic medical record set. In specific implementation, the first disease type and the second disease type can be converted into type vectors through a word embedding network, and matching is performed in a type vector mode, so that matching efficiency is improved.

S105, determining the similarity of the disease symptoms corresponding to the candidate historical electronic medical records according to the similarity between the at least one second disease symptom corresponding to the candidate historical electronic medical records in the candidate historical electronic medical record set and the at least one first disease symptom.

It is understood that, a plurality of candidate index information are obtained in step S103, and each candidate index information includes a corresponding second disease, so that when the similarity calculation is performed in step S105, the similarity calculation is performed substantially directly based on the plurality of candidate index information, and the obtained disease similarity may also be understood as the disease similarity corresponding to the candidate index information.

In a specific embodiment, step S105 may include the following steps:

(1) and mapping at least one first disease into first word vectors respectively to obtain a first word vector set. In particular, a first disorder may be mapped to a first word vector, e.g. a first set of word vectors denoted as s, respectively, by a word embedding network, e.g. word2vec₁,s₂,……,s_mWhere m denotes the number of first word vectors in the first set of word vectors, i.e. the number of first disorders.

(2) And mapping at least one second disease corresponding to the candidate historical electronic medical records into a second word vector respectively aiming at each candidate historical electronic medical record in the candidate historical electronic medical record set to obtain a second word vector set. Specifically, a second disorder included in each candidate index information may be mapped to a second word vector through the word embedding network word2vec, for example, the candidate historical electronic medical record C'₁Corresponding second word directionVolume set is expressed as { C'₁|s′₁,s′₂,……,s′_nN represents a candidate historical electronic medical record C'₁The number of corresponding second disorders.

(3) And calculating the similarity between the first word vector in the first word vector set and the second word vector in the second word vector set to obtain a similarity set corresponding to the candidate historical electronic medical record.

In a specific embodiment, for a second word vector set of each candidate historical electronic medical record, a second word vector in the second word vector set may be traversed, in the traversing process, a similarity between the second word vector and each first word vector in the first word vector set is calculated, then, a maximum similarity is selected as a similarity corresponding to the current second word vector, and after the traversing is finished, a similarity set corresponding to each candidate historical electronic medical record may be obtained.

For example, the second set of word vectors is { C'₁|s′₁,s′₂,……,s′_nThe first word vector set is s₁,s₂,……,s_mIs traversed to { C'₁|s′₁,s′₂,……,s′_nEvery second word vector in (j), e.g. for second word vector s'₁S 'is calculated'₁And { s₁,s₂,……,s_mSimilarity of each first word vector in (i.e. sim (s'₁,s_i) I-1 … … m, and then selecting the maximum similarity as s'₁Corresponding similarity is

i-1 … … m, and so on for s'₂……s′_nCarry out s 'similarly as above respectively'₁The similarity of the electronic medical record C is calculated, so that a candidate historical electronic medical record C 'is obtained'₁Is expressed, for example, as

It should be noted that, in the embodiment of the present specification, the similarity between two word vectors may be characterized by, but not limited to, a cosine angle, a euclidean distance, and a manhattan distance, and in practical applications, other quantization values capable of characterizing the similarity between two word vectors may also be included. For example, the cosine included angle is used to represent the similarity between two word vectors, and the calculation formula is as follows:

(4) calculating the average value of the similarity in the similarity set to obtain the average similarity; and the average similarity is used as the symptom similarity corresponding to the candidate historical electronic medical record. For example, for similarity set

Average degree of similarity thereof

The average similarity

Namely the candidate historical electronic medical record C'₁Similarity of disease states of (a).

It can be understood that the above is only one example of calculating the similarity of the medical conditions of the candidate historical electronic medical records, and other methods may be used for calculation in practical applications as needed.

S107, determining at least one candidate electronic medical record in the candidate electronic medical record set, of which the similarity of the diseases meets preset conditions, as a to-be-recommended historical electronic medical record, and displaying the to-be-recommended historical electronic medical record.

It can be understood that, in the actual implementation process of step S107, at least one candidate index information whose medical condition similarity satisfies the preset condition is obtained first, and then at least one candidate historical electronic medical record whose medical condition similarity satisfies the preset condition is obtained based on the mapping relationship between the index information and the historical electronic medical records.

The preset conditions can be set according to actual needs, and the preset conditions can be set to be that the disease similarity is greater than the preset disease similarity; the preset condition can also be set as a candidate electronic medical record corresponding to a preset arrangement position in the candidate electronic medical records arranged according to the similarity degree sequence of the disease symptoms, and the sequential arrangement can include descending order or ascending order.

Based on the above description, determining at least one candidate electronic medical record in the candidate electronic medical record set, in which the similarity of the disease state satisfies a preset condition, as the historical electronic medical record to be recommended may include: sequentially arranging the candidate historical electronic medical records according to the disease similarity; and acquiring candidate historical electronic medical records corresponding to the preset arrangement position to obtain the historical electronic medical records to be recommended.

In a specific embodiment, the candidate electronic history medical records can be arranged in a descending order according to the similarity of the disease symptoms from large to small, and then a preset number of candidate electronic history medical records arranged in the past are obtained, wherein the preset number of candidate electronic history medical records arranged in the past are the electronic history medical records to be recommended.

In another specific implementation manner, the candidate electronic history medical records may be arranged in an ascending order according to the similarity of the disease conditions from small to large, and then the candidate electronic history medical records in the preset number after arrangement are obtained, where the candidate electronic history medical records in the preset number after arrangement are the electronic history medical records to be recommended.

The preset number may be set according to actual needs, and may be set to a numerical value such as 3 or 5, for example.

When the historical electronic medical records to be recommended are displayed, the historical electronic medical records to be recommended can be displayed in a descending order according to the similarity of the medical conditions, specifically, only the index information of the historical electronic medical records to be recommended can be displayed, and when a user clicks certain index information, the corresponding historical electronic medical records can be displayed based on the mapping relation in the preset historical electronic medical record library.

According to the technical scheme of the embodiment of the invention, the incidence relation between the disease type and the disease symptoms is utilized, and the specific disease type and disease symptoms are combined for retrieval and similar matching, so that the directed characteristic comparison is realized, the matching time is shortened, and the recommendation efficiency of the electronic medical record is greatly improved.

In order to improve the processing efficiency of a user on a target electronic medical record in practical application, an embodiment of the present invention further provides another electronic medical record recommendation method, as shown in fig. 3, the method may further include:

and S109, acquiring target text information in the historical electronic medical record to be recommended.

Wherein the target text information is associated with an operation type of the pending operation, which may include, but is not limited to, filling out a treatment recommendation, a patient response, and the like. When the pending operation is to fill out a treatment suggestion, the target text information may include treatment scheme related contents in the historical electronic medical record to be recommended.

And S111, performing word segmentation processing on the target text information to obtain a word set.

Specifically, a word segmentation algorithm may be adopted to perform word segmentation processing on the target text information to obtain a word set. The word segmentation algorithm may include a dictionary-based word segmentation algorithm and a statistical-based word segmentation algorithm, among others.

When the word segmentation processing is carried out on the target text information by adopting a word segmentation algorithm based on a dictionary, the target text information can be matched with the entries stored in the dictionary, if the matching with a certain entry is successful, the word corresponding to the entry can be determined to be one word in the word set, and therefore each word in the word set corresponding to the target text information can be determined.

When the word segmentation processing is carried out by adopting the word segmentation algorithm based on statistics, the times of simultaneous occurrence of adjacent words in the input target text information can be counted, and it can be understood that the more the times of simultaneous occurrence of adjacent words are, the higher the probability that the adjacent words can form words is, so that each word in the word set corresponding to the target text information can be determined through the counted probability that the words and the words are adjacent to each other.

It should be noted that, in practical application, other word segmentation processing algorithms may also be used to perform word segmentation processing on the target text information to obtain a corresponding word set, which is not specifically limited in the present invention.

S113, determining target words of which the word frequency of the words in the word set exceeds a preset word frequency to obtain a target word set.

The word frequency refers to the frequency of a certain word appearing in a word set, and can be determined by the ratio of the total number of times of the certain word appearing in the word set to the total number of words contained in the word set. The preset word frequency can be set according to actual needs, and the value range of the preset word frequency is 0-1, preferably, in order to enable the target words in the target word set to be high-frequency words in the word set, the value range of the preset word frequency can be set to 0.5-1.0, for example, 0.8, and the like.

And S115, establishing the association relationship between the target word set and the target electronic medical record.

It is understood that steps S109 to S115 may be performed before the historical electronic medical records to be recommended are presented, or may be performed after the historical electronic medical records to be recommended are presented.

High-frequency words appearing in the existing treatment scheme can be associated with the target electronic medical record to be processed by establishing the association relation between the target word set and the target electronic medical record, and the high-frequency words are most likely to be adopted in the processing process of the target electronic medical record. When the processing of the high-frequency words is needed, the target word set can be displayed based on the association relation, and the user can select the interested target words according to the requirement, so that the processing efficiency of the user on the target electronic medical record is improved, and the normalization of the processing of the electronic medical record is facilitated.

Based on the above description, in another specific embodiment, as shown in fig. 4, after step S107, the method may further include:

and S117, responding to the target processing of the target electronic medical record, and acquiring the target word set according to the association relation.

Wherein the target treatment may include, but is not limited to, filling out a treatment recommendation.

And S119, displaying the target words in the target word set.

And S121, responding to a selection instruction of the target word, and determining the interested word.

When a user is interested in one or more displayed target words, the user can click the target words, and the terminal receives a selection instruction of the corresponding target words and determines the clicked target words as the interested words.

And S123, generating a processing result of the target processing according to the interested word.

In one specific example, the goal process is to fill out a treatment suggestion, and the corresponding process result is a suggested text containing the word of interest.

According to the embodiment of the invention, the incidence relation between the high-frequency words in the target text information and the target electronic medical record to be processed is established through the processing of the target text information in the historical electronic medical record to be recommended, the automatic generation of the target processing result is realized based on the incidence relation, when a user needs to fill the treatment suggestion in the target electronic medical record, the simple phrases in the similar historical electronic medical record can be automatically supplemented, the manual input time of the user is saved, meanwhile, the subjectivity of the character expression is avoided, and the filling of the electronic medical record is standardized.

Corresponding to the electronic medical record recommendation methods provided in the foregoing embodiments, embodiments of the present invention further provide an electronic medical record recommendation apparatus, and since the electronic medical record recommendation apparatus provided in the embodiments of the present invention corresponds to the electronic medical record recommendation methods provided in the foregoing embodiments, the implementation manner of the electronic medical record recommendation method is also applicable to the electronic medical record recommendation apparatus provided in this embodiment, and is not described in detail in this embodiment.

Referring to fig. 5, a schematic structural diagram of an electronic medical record recommendation apparatus according to an embodiment of the present invention is shown, where the apparatus has a function of implementing the electronic medical record recommendation method in the foregoing method embodiment, and the function may be implemented by hardware or by hardware executing corresponding software. As shown in fig. 5, the apparatus may include:

the first determining module 510 is configured to determine a first disease type and at least one first disease condition corresponding to a target electronic medical record to be processed;

the second determining module 520 is configured to match a second disease type corresponding to a historical electronic medical record in a preset historical electronic medical record library with the first disease type, and determine a matched candidate historical electronic medical record to obtain a candidate historical electronic medical record set;

a third determining module 530, configured to determine, according to a similarity degree between at least one second medical condition and the at least one first medical condition that correspond to the candidate electronic medical records in the candidate electronic medical record set, a medical condition similarity degree that corresponds to the candidate electronic medical record;

and the recommending module 540 is configured to determine at least one candidate electronic medical record in the candidate electronic medical record sets, of which the disease similarity satisfies a preset condition, as the historical electronic medical record to be recommended, and display the historical electronic medical record to be recommended.

As an optional implementation manner, the apparatus further includes a building module for building the preset electronic medical record history library, and the building module may include:

As an optional implementation, the first determining module 510 may include:

the first display module is used for displaying the at least one named entity;

As an optional implementation, the third determining module 530 may include:

As an optional implementation, the recommending module 540 may include:

As an optional implementation manner, as another electronic medical record recommendation apparatus provided in fig. 6, the apparatus may further include:

a fourth obtaining module 550, configured to obtain target text information in the historical electronic medical record to be recommended;

a word segmentation processing module 560, configured to perform word segmentation processing on the target text information to obtain a word set;

a sixth determining module 570, configured to determine a target word whose word frequency of the word in the word set exceeds a preset word frequency, to obtain a target word set;

a second relationship establishing module 580, configured to establish an association relationship between the target word set and the target electronic medical record.

As an alternative embodiment, with continued reference to fig. 6, the apparatus may further comprise:

a first response module 610, configured to respond to target processing on the target electronic medical record, and obtain the target word set according to the association relationship;

a second display module 620, configured to display the target words in the target word set;

a second response module 630, configured to determine a term of interest in response to a selection instruction for the target term;

a result generating module 640, configured to generate a processing result of the target processing according to the word of interest.

It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.

The electronic medical record recommendation device provided by the embodiment of the invention utilizes the incidence relation between the disease types and the diseases, and combines the specific disease types and the diseases to carry out retrieval and similar matching, thereby realizing the directional characteristic comparison, shortening the matching time and greatly improving the recommendation efficiency of the electronic medical record.

In addition, the embodiment of the invention establishes the incidence relation between high-frequency words in the target text information and the target electronic medical record to be processed through the processing of the target text information in the historical electronic medical record to be recommended, and realizes the automatic generation of the target processing result based on the incidence relation.

The embodiment of the invention provides a terminal, which comprises a processor and a memory, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor to realize the electronic medical record recommendation method provided by the above method embodiment.

The memory can be used for storing software programs and modules, and the processor executes various functional applications and electronic medical record recommendation by operating the software programs and modules stored in the memory. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs needed by functions and the like; the storage data area may store data created according to use of the apparatus, and the like. Further, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory may also include a memory controller to provide the processor access to the memory.

The method provided by the embodiment of the invention can be executed in a computer terminal, a server or a similar operation device. Taking the operation on the terminal as an example, fig. 7 is a hardware structure block diagram of the terminal for operating the electronic medical record recommendation method according to the embodiment of the present invention, specifically:

the terminal may include RF (Radio Frequency) circuitry 710, memory 720 including one or more computer-readable storage media, input unit 730, display unit 740, sensor 750, audio circuitry 760, WiFi (wireless fidelity) module 770, processor 780 including one or more processing cores, and power supply 790. Those skilled in the art will appreciate that the terminal structure shown in fig. 7 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

RF circuit 710 may be used for receiving and transmitting signals during a message transmission or call, and in particular, for receiving downlink information from a base station and processing the received downlink information by one or more processors 780; in addition, data relating to uplink is transmitted to the base station. In general, RF circuit 710 includes, but is not limited to, an antenna, at least one Amplifier, a tuner, one or more oscillators, a Subscriber Identity Module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, and the like. In addition, the RF circuit 710 may also communicate with a network and other terminals through wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communications), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), e-mail, SMS (short messaging Service), etc.

The memory 720 may be used to store software programs and modules, and the processor 780 performs various functional applications and data processing by operating the software programs and modules stored in the memory 720. The memory 720 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, and the like; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 720 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 720 may also include a memory controller to provide access to memory 720 by processor 780 and input unit 730.

The input unit 730 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control. In particular, the input unit 730 may include a touch-sensitive surface 731 as well as other input devices 732. Touch-sensitive surface 731, also referred to as a touch display screen or touch pad, can collect touch operations by a user on or near touch-sensitive surface 731 (e.g., operations by a user on or near touch-sensitive surface 731 using a finger, stylus, or any other suitable object or attachment) and drive the corresponding connection device according to a predetermined program. Alternatively, the touch sensitive surface 731 may comprise two parts, a touch detection means and a touch controller. The touch detection device detects the touch direction of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch sensing device, converts it to touch point coordinates, and sends the touch point coordinates to the processor 780, and can receive and execute commands from the processor 780. In addition, the touch-sensitive surface 731 can be implemented in a variety of types, including resistive, capacitive, infrared, and surface acoustic wave. The input unit 730 may also include other input devices 732 in addition to the touch-sensitive surface 731. In particular, other input devices 732 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

The display unit 740 may be used to display information input by or provided to the user and various graphic user interfaces of the terminal, which may be configured by graphics, text, icons, video, and any combination thereof. The Display unit 740 may include a Display panel 741, and optionally, the Display panel 741 may be configured in the form of an LCD (Liquid Crystal Display), an OLED (Organic Light-Emitting Diode), or the like. Further, touch-sensitive surface 731 can overlay display panel 741, such that when touch-sensitive surface 731 detects a touch event thereon or nearby, processor 780 can determine the type of touch event, and processor 780 can then provide a corresponding visual output on display panel 741 based on the type of touch event. Where the touch-sensitive surface 731 and the display panel 741 may be implemented as two separate components, input and output functions, but in some embodiments the touch-sensitive surface 731 and the display panel 741 may be integrated to implement input and output functions.

The terminal may also include at least one sensor 750, such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display panel 741 according to the brightness of ambient light, and a proximity sensor that may turn off the display panel 741 and/or a backlight when the terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the terminal is stationary, and can be used for applications of recognizing terminal gestures (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured in the terminal, detailed description is omitted here.

Audio circuitry 760, speaker 761, and microphone 762 may provide an audio interface between a user and the terminal. The audio circuit 760 can transmit the electrical signal converted from the received audio data to the speaker 761, and the electrical signal is converted into a sound signal by the speaker 761 and output; on the other hand, the microphone 762 converts the collected sound signal into an electric signal, converts the electric signal into audio data after being received by the audio circuit 760, processes the audio data by the audio data output processor 780, and transmits the processed audio data to, for example, another terminal via the RF circuit 710, or outputs the audio data to the memory 720 for further processing. The audio circuitry 760 may also include an earbud jack to provide communication of peripheral headphones with the terminal.

WiFi belongs to short distance wireless transmission technology, the terminal can help user send and receive e-mail, browse web page and access stream media etc. through WiFi module 770, it provides wireless broadband internet access for user. Although fig. 7 shows the WiFi module 770, it is understood that it does not belong to the essential constitution of the terminal, and can be omitted entirely as needed within the scope not changing the essence of the invention.

The processor 780 is a control center of the terminal, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the terminal and processes data by operating or executing software programs and/or modules stored in the memory 720 and calling data stored in the memory 720, thereby integrally monitoring the terminal. Optionally, processor 780 may include one or more processing cores; preferably, the processor 780 may integrate an application processor, which primarily handles operating systems, user interfaces, applications, etc., and a modem processor, which primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 780.

The terminal also includes a power supply 790 (e.g., a battery) for powering the various components, which may preferably be logically coupled to the processor 780 via a power management system to manage charging, discharging, and power consumption management functions via the power management system. The power supply 790 may also include any component including one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.

Although not shown, the terminal may further include a camera, a bluetooth module, and the like, which are not described herein again. In this embodiment, the terminal further includes a memory and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the one or more processors. The one or more programs include instructions for performing the electronic medical record recommendations provided by the method embodiments described above.

The embodiment of the present invention further provides a computer-readable storage medium, where the storage medium may be configured in a terminal to store at least one instruction, at least one program, a code set, or a set of instructions related to implementing an electronic medical record recommendation method, and the at least one instruction, the at least one program, the code set, or the set of instructions are loaded and executed by the processor to implement the electronic medical record recommendation method provided by the foregoing method embodiment.

Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims

1. An electronic medical record recommendation method is characterized by comprising the following steps:

2. The method for recommending electronic medical records according to claim 1, further comprising constructing said pre-set electronic medical record history repository; the constructing of the preset historical electronic medical record library comprises the following steps:

acquiring a plurality of historical electronic medical records;

determining a second disease type and at least one second disease condition corresponding to each historical electronic medical record in the plurality of historical electronic medical records;

taking the second disease type and at least one second disease as index information of a corresponding historical electronic medical record, and establishing a mapping relation between the historical electronic medical record and the index information;

and creating the preset historical electronic medical record library according to the mapping relation.

3. The method for recommending electronic medical records according to claim 1, wherein the determining the first disease type and the at least one first disease condition corresponding to the target electronic medical record to be processed comprises:

acquiring text content of a target electronic medical record to be processed;

classifying the text content based on a disease classification model to obtain a first disease type corresponding to the target electronic medical record;

carrying out named entity recognition on the text content based on a named entity recognition model to obtain at least one named entity;

exposing the at least one named entity;

determining a target named entity according to a selection instruction of a named entity in the at least one named entity, wherein the target named entity serves as the at least one first disease state.

4. The method for recommending electronic medical records according to claim 1, wherein the determining the similarity of the at least one second medical condition to the at least one first medical condition according to the similarity between the at least one second medical condition and the at least one first medical condition corresponding to the candidate electronic medical records in the candidate electronic medical record set comprises:

mapping the at least one first disease into first word vectors respectively to obtain a first word vector set;

for each candidate historical electronic medical record in the candidate historical electronic medical record set, mapping at least one second disease corresponding to the candidate historical electronic medical record into a second word vector respectively to obtain a second word vector set;

calculating the similarity between a first word vector in the first word vector set and a second word vector in the second word vector set to obtain a similarity set corresponding to the candidate historical electronic medical record;

calculating the average value of the similarity in the similarity set to obtain the average similarity; and the average similarity is used as the symptom similarity corresponding to the candidate historical electronic medical record.

5. The method for recommending electronic medical records according to claim 1, wherein the determining at least one candidate electronic medical record in the candidate electronic medical record set, of which the degree of similarity to the medical condition satisfies a preset condition, as the historical electronic medical record to be recommended includes:

sequentially arranging the candidate historical electronic medical records according to the disease similarity;

and acquiring candidate historical electronic medical records corresponding to the preset arrangement position to obtain the historical electronic medical records to be recommended.

6. The method for recommending electronic medical records according to claim 1, further comprising:

acquiring target text information in the historical electronic medical record to be recommended;

performing word segmentation processing on the target text information to obtain a word set;

determining target words of which the word frequency of the words in the word set exceeds a preset word frequency to obtain a target word set;

and establishing the incidence relation between the target word set and the target electronic medical record.

7. The method for recommending electronic medical records according to claim 6, wherein after said presenting said historical electronic medical record to be recommended, said method further comprises:

responding to the target processing of the target electronic medical record, and acquiring the target word set according to the incidence relation;

displaying target words in the target word set;

in response to a selection instruction of the target word, determining a word of interest;

and generating a processing result of the target processing according to the interested word.

8. An electronic medical record recommendation device, characterized in that the device comprises:

9. A terminal comprising a processor and a memory, wherein the memory has stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by the processor to implement the electronic medical record recommendation method according to any one of claims 1 to 7.

10. A computer readable storage medium having stored therein at least one instruction, at least one program, a set of codes, or a set of instructions, which is loaded and executed by a processor to implement the electronic medical record recommendation method of any of claims 1-7.