CN114334065A - Medical record processing method, computer readable storage medium and computer device - Google Patents

Abstract

The invention discloses a medical record processing method, a computer readable storage medium and computer equipment. Wherein, the method comprises the following steps: acquiring a target medical record; extracting a target symptom word set from a target medical record; extracting a target symptom characteristic word set from a target medical record based on the target symptom word set; acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; and determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease. The invention solves the technical problems of low efficiency and high error rate when corresponding diseases are determined according to patient medical records in the related technology.

Description

Medical record processing method, computer readable storage medium and computer device

Technical Field

The invention relates to the field of data processing, in particular to a medical record processing method, a computer-readable storage medium and computer equipment.

Background

In the related art, the disease is predicted by calculating a relationship weight between a single symptom and a disease using a co-occurrence frequency of the disease, manually determining a symptom and a disease relationship weight, and predicting the disease according to the weight or manually determining an initial weight and then performing a counter-fact reasoning. However, the above scheme has the disadvantage of requiring manual determination of weights or inaccurate disease prediction results.

Therefore, in the related art, there are problems of low efficiency and high error rate when identifying a corresponding disease from a patient medical record.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a medical record processing method, a computer readable storage medium and computer equipment, which are used for at least solving the technical problems of low efficiency and high error rate when corresponding diseases are determined according to medical records of patients in the related technology.

According to an aspect of an embodiment of the present invention, there is provided a medical record processing method, including: acquiring a target medical record; extracting a target symptom word set from a target medical record; extracting a target symptom characteristic word set from a target medical record based on the target symptom word set; acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; and determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease.

Optionally, the extracting the target symptom word set from the target medical record includes: dividing the target medical record into a plurality of short sentences; extracting candidate symptom words from the short sentences; and in the case that the candidate symptom words can be matched into a preset symptom word list, determining the candidate symptom words as target symptom words and collecting the target symptom words into a target symptom word set.

Optionally, extracting the target symptom feature word set from the target medical record based on the target symptom word set includes: deleting the target symptom words included in the target symptom word set from the target medical record to obtain residual short sentences; performing word segmentation on the remaining short sentences to obtain a plurality of word segments; and combining the multiple word segments respectively to obtain target symptom characteristic words, and collecting the target symptom characteristic words into a target symptom characteristic word set.

Optionally, the obtaining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: acquiring a sample medical record set, wherein the sample medical record set comprises sample medical record description information and a sample medical record result; acquiring a sample symptom word set and a sample characteristic word set of a sample medical record of the sample medical record set from the sample medical record description information; and determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease based on the sample symptom word set and the sample feature word set.

Optionally, based on the sample symptom word set and the sample feature word set, determining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: aiming at a sample disease corresponding to a sample medical record result in a sample medical record set, acquiring the times of the sample symptomatic words in the sample symptomatic word set appearing in the sample medical record set and the times of the sample characteristic words in the sample characteristic word set appearing in the sample medical record set; acquiring a first weight of a sample symptom word in the sample symptom word set in a sample disease based on the frequency of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the frequency of the feature word in the sample feature word set appearing in the sample medical record set; when the target symptom words are sample symptom words and the predetermined disease is a sample disease, determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease as a first weight of the sample symptom words in the sample disease, and determining a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease as a second weight of the sample feature words in the sample disease.

Optionally, obtaining a first weight of a sample symptom word in the sample symptom word set in the sample disease based on the number of times of occurrence of the sample symptom word in the sample medical record set, and obtaining a second weight of a sample feature word in the sample feature word set in the sample disease based on the number of times of occurrence of the feature word in the sample feature word set in the sample medical record set includes: determining the quality score of the sample medical record based on the sample symptom word set and the sample characteristic word set of the sample medical record in the sample symptom word set; determining a third weight of the sample medical record based on the quality score of the sample medical record; the method comprises the steps of obtaining a first weight of a sample symptom word in a sample symptom word set in a sample disease based on the number of times and a third weight of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and obtaining a second weight of a sample feature word in a sample feature word set in the sample disease based on the number of times and the third weight of the feature word in the sample feature word set appearing in the sample medical record set.

Optionally, determining the target disease corresponding to the target medical record based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: determining similarity between a disease corresponding to the target medical record and a plurality of candidate diseases based on a first weight of a target symptom word in a predetermined disease and a second weight of a target symptom feature word in a predetermined disease, wherein the first weight of the target symptom word is included in the target symptom word set; and determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the candidate diseases.

Optionally, determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the plurality of candidate diseases includes: sequencing the similarity of the disease corresponding to the target medical record and a plurality of candidate diseases, and determining the first N candidate diseases with the highest similarity as the target diseases corresponding to the target medical record, wherein N is a positive integer; or determining the candidate diseases with the similarity higher than the similarity threshold as the target diseases corresponding to the target medical records.

Optionally, the obtaining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: determining a quality score of the target medical record based on the target symptom word set and the target symptom characteristic word set; and under the condition that the quality score is higher than a quality score threshold value, acquiring a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

Optionally, determining the quality score of the target medical record based on the target symptom word set and the target symptom feature word set comprises: determining the quantity of normal information and the quantity of abnormal information in the target medical record based on the target symptom word set and the target symptom characteristic word set; and determining the quality score of the target medical record based on the quantity of the normal information and the quantity of the abnormal information in the target medical record.

According to another aspect of the embodiments of the present invention, there is also provided a medical record processing method, including: displaying a medical record input control on the interactive interface; receiving a target medical record in response to the operation of the medical record input control; in response to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set; and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

According to another aspect of the embodiments of the present invention, there is also provided a medical record processing method, including: displaying a medical record input control on the interactive interface; responding to the operation of the medical record input control, and displaying the target medical record on the interactive interface; displaying a target symptom word set and a target symptom characteristic word set of the target medical record on an interactive interface; and responding to the operation of the target medical record, and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

According to another aspect of the embodiments of the present invention, there is also provided a medical record processing apparatus, including: the first acquisition module is used for acquiring a target medical record; the first extraction module is used for extracting a target symptom word set from a target medical record; the second extraction module is used for extracting a target symptom characteristic word set from the target medical record based on the target symptom word set; the second acquisition module is used for acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; the first determining module is used for determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease.

According to another aspect of the embodiments of the present invention, there is also provided a medical record processing apparatus, including: the first display module is used for displaying the medical record input control on the interactive interface; the first receiving module is used for responding to the operation of the medical record input control and receiving the target medical record; the third extraction module is used for responding to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set; the second display module is used for displaying the target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on the first weight of the target symptom word included in the target symptom word set in the preset disease and the second weight of the target symptom feature word included in the target symptom feature word set in the preset disease.

According to another aspect of the embodiments of the present invention, there is also provided a medical record processing apparatus, including: the third display module is used for displaying the medical record input control on the interactive interface; the second receiving module is used for responding to the operation of the medical record input control and displaying the target medical record on the interactive interface; the fourth display module is used for responding to the operation on the target medical record and displaying the target symptom word set and the target symptom characteristic word set of the target medical record on the interactive interface; and the fifth display module is used for displaying the target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom word included in the target symptom feature word set in the predetermined disease.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, the apparatus where the computer-readable storage medium is located is controlled to execute any one of the medical record processing methods described above.

According to another aspect of the embodiments of the present invention, there is also provided a computer device, including: a memory and a processor, the memory storing a computer program; and the processor is used for executing the computer program stored in the memory, and the computer program enables the processor to execute any one of the medical record processing methods when running.

In the embodiment of the invention, the target symptom word set and the target symptom characteristic word set are extracted from the target medical record, the weights of the target symptom words and the target symptom characteristic words in the preset diseases are obtained, and finally the target diseases corresponding to the target medical record are determined based on the weights, so that the aims of avoiding manually determining the weights, increasing the symptom table testimonials corresponding to the diseases and considering the relation between the symptom table testimonials are fulfilled, the technical effect of directly, efficiently and accurately determining the diseases suffered by the patient according to the medical record of the patient is realized, and the technical problems of low efficiency and high error rate when the corresponding diseases are determined according to the medical record of the patient in the related technology are solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

fig. 1 shows a hardware configuration block diagram of a computer terminal for implementing a medical record processing method;

FIG. 2 is a flowchart of a first medical record processing method according to embodiment 1 of the invention;

FIG. 3 is a flowchart of a second medical record processing method according to embodiment 1 of the invention;

FIG. 4 is a flowchart of a third medical record processing method according to embodiment 1 of the present invention;

fig. 5 is a block diagram showing a first medical record processing apparatus according to embodiment 2 of the present invention;

fig. 6 is a block diagram showing a second medical record processing apparatus according to embodiment 2 of the present invention;

fig. 7 is a block diagram showing a third medical record processing apparatus according to embodiment 2 of the present invention;

fig. 8 is a block diagram of a computer terminal according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, 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 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 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 apparatus 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.

First, some terms or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:

association rule mining, a rule-based machine learning algorithm that can discover relationships of interest in big data. Its purpose is to use some metrics to resolve strong rules that exist in the database. The corresponding mature algorithms include Aproir, FP-Growth, and the like.

Document similarity, a common method known as TF-IDF, a commonly used weighting technique for information retrieval and text mining, can be used to evaluate the importance of a word to a document in a document set or corpus. The importance of a word increases in direct proportion to the number of times it appears in the corpus, but at the same time decreases in inverse proportion to the frequency with which it appears in the corpus. The more mature algorithms are BIM, BM25, BM25F, PLN, etc.

Complaints, medical and psychological terms. It is the patient (visitor) who self-states his symptoms or (and) signs, nature, and duration.

Natural Language Processing (NLP) is a subject of studying the Language problem of human interaction with computers. According to different technical implementation difficulties, such systems can be divided into three types, namely simple matching type, fuzzy matching type and paragraph understanding type.

The knowledge map is a series of different graphs displaying the relationship between the knowledge development process and the structure, and is used for describing knowledge resources and carriers thereof by using a visualization technology, mining, analyzing, constructing, drawing and displaying knowledge and the mutual relation between the knowledge resources and the carriers. The knowledge graph is a modern theory which achieves the aim of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing a visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects.

Example 1

There is also provided, in accordance with an embodiment of the present invention, a method for medical record processing, an embodiment of which is illustrated in the flowchart of the figure as being executable by a computer system, such as a set of computer-executable instructions, and although a logical order is illustrated in the flowchart, in some cases the steps shown or described may be executed in an order different than that shown.

The method provided by the embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Fig. 1 shows a hardware configuration block diagram of a computer terminal (or mobile device) for implementing a medical record processing method. As shown in fig. 1, the computer terminal 10 (or mobile device) may include one or more processors (shown as 102a, 102b, … …, 102n, which may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial BUS (USB) port (which may be included as one of the ports of the BUS), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.

It should be noted that the one or more processors and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal 10 (or mobile device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).

The memory 104 can be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the medical record processing method in the embodiment of the present invention, and the processor executes various functional applications and data processing by operating the software programs and modules stored in the memory 104, that is, implementing the above-mentioned vulnerability detection method for application programs. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor, which may be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal 10 (or mobile device).

Under the operating environment, the application provides a first medical record processing method as shown in fig. 2. Fig. 2 is a flowchart of a first medical record processing method according to embodiment 1 of the present invention, as shown in fig. 2, the method includes the following steps:

step S202, acquiring a target medical record;

step S204, extracting a target symptom word set from a target medical record;

step S206, extracting a target symptom word set from the target medical record based on the target symptom word set;

step S208, acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease;

step S210, determining a target disease corresponding to the target medical record based on a first weight of the target symptom word included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease.

Through the steps, the target symptom words and the target symptom characteristic words are extracted from the target medical record, symptom basis required by target disease prediction can be rapidly obtained, particularly the target symptom characteristic words are obtained, the corresponding relation between the target disease and symptoms can be further confirmed on the basis of the original symptom words, the accuracy of a subsequent target disease prediction result is improved, the final target disease is determined according to the corresponding weight of the extracted target symptom words and the extracted target symptom characteristic words in the preset disease, the technical effect that the disease of the patient is directly, efficiently and accurately determined according to the medical record of the patient can be achieved, and the technical problems that in the related technology, when the corresponding disease is determined according to the medical record of the patient, efficiency is low and the error rate is high are solved.

As an alternative embodiment, extracting the target symptom word set from the target medical record may include: dividing the target medical record into a plurality of short sentences; extracting candidate symptom words from the short sentences; and in the case that the candidate symptom words can be matched into a preset symptom word list, determining the candidate symptom words as target symptom words and collecting the target symptom words into a target symptom word set. By dividing the short sentences and extracting the symptom words, the descriptors capable of representing the symptoms can be quickly found from the medical records to serve as reliable bases for predicting the target diseases subsequently.

As an alternative embodiment, extracting the target symptom feature word set from the target medical record based on the target symptom word set includes: deleting the target symptom words included in the target symptom word set from the target medical record to obtain residual short sentences; performing word segmentation on the remaining short sentences to obtain a plurality of word segments; and combining the multiple word segments respectively to obtain target symptom characteristic words, and collecting the target symptom characteristic words into a target symptom characteristic word set. The target symptom characteristic words are obtained by further segmenting and combining the remaining short sentences from which the target symptom words are deleted, and after the target symptom words are determined, the symptom descriptions corresponding to the preset diseases can be expanded, and meanwhile, the association among symptoms can be considered, so that the finally determined target symptom word set and the target symptom characteristic word set can more comprehensively represent the symptoms of the diseases of the current patient, and the reliability of the target symptom words and the target symptom characteristic words as prediction bases is improved. By adopting the processing, compared with the prior art that the symptom characteristics are determined only according to the preset symptom word set, the medical record characterization method has the advantages that the segmentation words which are divided from the short sentences and include more details are added, so that the medical record characterization can be more accurate and comprehensive.

As an alternative embodiment, the obtaining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: acquiring a sample medical record set, wherein the sample medical record set comprises sample medical record description information and a sample medical record result; acquiring a sample symptom word set and a sample characteristic word set of a sample medical record of the sample medical record set from the sample medical record description information; and determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease based on the sample symptom word set and the sample feature word set. Because the symptom words and the symptom characteristic words corresponding to the predetermined diseases are obtained by extracting and processing a large number of sample medical records, the target diseases corresponding to the medical records of the patient can be determined by determining the corresponding weights of all the obtained target symptom words and target symptom characteristic words in the predetermined diseases.

As an alternative embodiment, based on the sample symptom word set and the sample feature word set, determining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: aiming at a sample disease corresponding to a sample medical record result in a sample medical record set, acquiring the times of the sample symptomatic words in the sample symptomatic word set appearing in the sample medical record set and the times of the sample characteristic words in the sample characteristic word set appearing in the sample medical record set; acquiring a first weight of a sample symptom word in the sample symptom word set in a sample disease based on the frequency of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the frequency of the feature word in the sample feature word set appearing in the sample medical record set; when the target symptom words are sample symptom words and the predetermined disease is a sample disease, determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease as a first weight of the sample symptom words in the sample disease, and determining a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease as a second weight of the sample feature words in the sample disease. According to the sample medical record result, the first weight and the second weight in the sample medical record are respectively counted and calculated based on the corresponding times of the sample symptom words and the sample symptom characteristic words in the sample medical record, so that the sample symptom words and the sample symptom characteristic words corresponding to the sample medical record result can be truly and accurately determined, and the possibility that the sample medical record corresponds to the sample medical record result when the sample symptom words and the sample symptom characteristic words appear in a case can be determined, namely, the possibility that some disease diagnosis results are correspondingly obtained when some symptom descriptions exist in the case can be determined. On the basis, corresponding weights of the obtained target symptom words and the target symptom characteristic words in the predetermined diseases are further determined, so that the range of the predetermined diseases can be greatly and accurately narrowed, and the accuracy of the prediction results of the subsequent target diseases is improved.

As an alternative embodiment, the obtaining a first weight of the sample symptomatic words in the sample symptomatic word set in the sample disease based on the number of times of appearance of the sample symptomatic words in the sample medical record set in the sample symptomatic word set, and the obtaining a second weight of the sample characteristic words in the sample disease based on the number of times of appearance of the characteristic words in the sample characteristic word set in the sample medical record set includes: determining the quality score of the sample medical record based on the sample symptom word set and the sample characteristic word set of the sample medical record in the sample symptom word set; determining a third weight of the sample medical record based on the quality score of the sample medical record; the method comprises the steps of obtaining a first weight of a sample symptom word in a sample symptom word set in a sample disease based on the number of times and a third weight of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and obtaining a second weight of a sample feature word in a sample feature word set in the sample disease based on the number of times and the third weight of the feature word in the sample feature word set appearing in the sample medical record set. Because the descriptive information about disease symptoms in the sample medical records is not necessarily large enough, the referential performance of the sample medical records with small information content in the training process is correspondingly reduced. By scoring the quality of the sample medical records based on the set, the weight of the sample medical records in the subsequent training process can be determined according to the quality scores of the sample medical records, so that the influence of the sample medical records with large information quantity is larger, and the subsequent training process can be finished efficiently and with high quality.

As an alternative embodiment, determining the target disease corresponding to the target medical record based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: determining similarity between a disease corresponding to the target medical record and a plurality of candidate diseases based on a first weight of a target symptom word in a predetermined disease and a second weight of a target symptom feature word in a predetermined disease, wherein the first weight of the target symptom word is included in the target symptom word set; and determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the candidate diseases. And determining the similarity between the disease corresponding to the target medical record and a plurality of candidate diseases based on the first weight and the second weight, and determining the target disease which is most consistent with the symptom words and the symptom characteristic words in the target medical record according to the similarity.

As an alternative embodiment, determining the target medical record corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the plurality of candidate diseases includes: sequencing the similarity of the disease corresponding to the target medical record and a plurality of candidate diseases, and determining the first N candidate diseases with the highest similarity as the target diseases corresponding to the target medical record, wherein N is a positive integer; or determining the candidate diseases with the similarity higher than the similarity threshold as the target diseases corresponding to the target medical records. By recalling all candidate diseases with similarity higher than the similarity threshold as target diseases, the possibility of wrong diagnosis can be further reduced.

As an alternative embodiment, the obtaining a first weight of the target symptom word included in the target symptom word set in the predetermined disease, and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease includes: determining a quality score of the target medical record based on the target symptom word set and the target symptom characteristic word set; and under the condition that the quality score is higher than a quality score threshold value, acquiring a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease. By scoring the quality of the target medical record as well, whether the information quantity of the target medical record is enough for supporting the judgment of the target disease can be judged according to the quality scoring condition of the target medical record, so that the possibility of wrong diagnosis of the disease can be further reduced.

As an alternative embodiment, determining the quality score of the target medical record based on the target symptom word set and the target symptom feature word set includes: determining the quantity of normal information and the quantity of abnormal information in the target medical record based on the target symptom word set and the target symptom characteristic word set; and determining the quality score of the target medical record based on the quantity of the normal information and the quantity of the abnormal information in the target medical record. Since only the abnormal information relates to the symptom description of the disease in the target medical record, the normal information does not help to determine the target disease, for example, in the case of "the patient has cough and running nose, and does not have fever", the cough and running nose belong to the abnormal information, and the fever is the normal information. The reliability of diagnosis according to the target medical record can be accurately evaluated in detail by determining the quantity of normal information and abnormal information in the target medical record and calculating the quality score of the target medical record based on the statistical result. Meanwhile, other operations can be performed on the quality score result of the target medical record, for example, when the quality score of the target medical record is lower than a predetermined threshold, diagnosis is not continued, but a result that medical record information is insufficient and cannot be diagnosed is given, so that wrong diagnosis caused by insufficient information of the target medical record is reduced.

Fig. 3 is a flowchart of a second medical record processing method according to embodiment 1 of the present invention, as shown in fig. 3, the method includes the following steps:

step S302, displaying a medical record input control on an interactive interface;

step S304, responding to the operation of the medical record input control, and receiving a target medical record;

step S306, in response to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set;

step S308, displaying the target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom word included in the target symptom feature word set in the predetermined disease.

Through the steps, the target diseases corresponding to the target medical records can be obviously obtained through operating the medical record input control on the interactive interface, the technical effect of directly, efficiently and accurately determining the diseases suffered by the patient according to the patient medical records is achieved, and the technical problems of low efficiency and high error rate in the related technology when the corresponding diseases are determined according to the patient medical records are solved.

Fig. 4 is a flowchart of a third medical record processing method according to embodiment 1 of the present invention, and as shown in fig. 4, the method includes the following steps:

step S402, displaying a medical record input control on an interactive interface;

step S404, responding to the operation of the medical record input control, and displaying and receiving a target medical record on an interactive interface;

step S406, displaying a target symptom word set and a target symptom feature word set of the target medical record on an interactive interface;

step S408, responding to the operation of the target medical record, and displaying the target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease.

Through the steps, the target symptom word set, the target symptom characteristic words and the diseases corresponding to the target medical record can be displayed on the interactive interface when the target medical record is input on the interactive interface, and therefore the technical problems that in the related technology, when the corresponding diseases are determined according to the patient medical record, efficiency is low and error rate is high are solved.

Based on the above embodiments and alternative embodiments, an alternative implementation is provided, which is described in detail below.

An alternative embodiment of the invention is a clinical-aided diagnosis system that primarily diagnoses medical scenarios and requires a list of possible diseases and probability of each disease that a patient may have after a physician has entered a description of the patient's underlying condition. The doctor makes a final diagnosis by means of the recommendation list so as to reduce misdiagnosis, improve diagnosis efficiency and improve the quality of medical record input. The system comprises a patient information extraction module, an inference rule mining module and a disease inference module.

In the related art, there are several general implementations as follows:

(1) a construction method of knowledge graph is applied to clinical auxiliary diagnosis, wherein the relation weight of symptom and disease is calculated according to the frequency of single symptom and the frequency of co-occurrence of the symptom and the disease, and belongs to the traditional Bayesian inference recommendation method;

(2) a disease inference algorithm, wherein the relationship weights of symptoms and disease comprise two parts, the prevalence of symptoms and the impact factors of symptoms and disease, both of which are determined manually;

(3) a counterfactual reasoning method is based on two principles of 'the correct diagnosis always covers the symptom characteristics of a patient as much as possible' and 'the symptom denied by the correct diagnosis is always the least'.

However, the above solutions have disadvantages, each of which is as follows:

(1) the algorithm does not consider the influence of a plurality of symptom combination conditions on the disease to calculate the weight, and the contribution of each symptom to the disease is assumed to be independent, so that the symptoms are related, for example, the two symptoms of cough and phlegm are related; the image relationship between symptoms and diseases is based on frequency, and when some symptoms are more common, such as fever, or some diseases are more common, such as upper respiratory tract infection, the recommended results are biased;

(2) a doctor expert is required to manually determine the weight;

(3) a physician specialist is required to manually determine the initial weights.

The optional implementation mode of the invention comprises a patient information extraction module, an inference rule mining module and a disease inference module.

Wherein the patient information extraction module: the extraction of the patient information not only comprises the characteristics of the symptom dictionary, but also considers the characteristics of the phrase combination, thereby reducing the probability of missing detection of the symptoms to the maximum extent. An inference rule mining module: each disease is regarded as a document, the relation between the symptom characteristic and the disease is regarded as the relation between a keyword and the document, the number of patients is regarded as word frequency, meanwhile, the quality weight coefficient of medical records is considered, and the relation weight between the symptom and the disease is calculated by adopting a document similarity method. A disease reasoning module: and performing feature extraction on the disease description of the patient according to a method in the patient information extraction module, calculating the similarity between the disease of the patient and each disease by adopting a document similarity-based algorithm, and giving disease recommendation sequencing according to the similarity.

In the experiment, compared with the recommendation result of the traditional inference method based on the Bayesian statistical rule, the clinical auxiliary diagnosis system designed according to the above process can improve the Top5 recommendation recall rate from 72% to 83%.

Alternative embodiments of the invention are described in detail below.

(1) Patient information extraction module

1.1 constructing a term vocabulary D _ i (i =1,2.. m) containing diseases, a vocabulary S _ i (i =1,2.. k) containing symptoms, m being the total number of disease species, k being the total number of symptoms;

1.2 dividing texts such as chief complaints, current medical history, physical examination and the like in the electronic medical record P _ i (i =1,2.. n; n is the total number of medical records) into short sentences according to punctuation marks;

1.3 judging whether the described state of illness of the short sentence is a healthy state or an abnormal state according to the NLP algorithm. Performing NLP extraction on the statement short sentence of the abnormal condition and aligning the statement short sentence to a symptom word list S constructed by 1.1;

1.4 in order to better obtain the effect of the optional embodiment of the invention, on the basis of 1.3, the statement short sentence of the abnormal condition is segmented, and after the segmentation, stop words are removed, and then the statement short sentence is combined in pairs to form an expanded symptom characteristic word W _ x;

1.5 extracting doctor diagnosis information in the electronic medical record, and combining the results of 1.3 and 1.4. And obtaining the structured electronic medical record data set. Q _ i (i =1,2.. n) includes, for each medical record, a number of diagnoses, symptom words, feature words;

1.6 in order to better obtain the effect of the optional embodiment of the invention, the connotative quality of the electronic medical record is graded, the electronic medical record is graded according to the quantity of the abnormal information described by the electronic medical record, the value is from 0 to 1, and the larger the information quantity, the higher the value is. If the number of the abnormal information or symptoms extracted by an electronic medical record is Nb = 3, and the number of the normal information or symptoms is Nn = 4, the quality score of the electronic medical record can adopt the following empirical formula:

this empirical formula is intended to guarantee:

when the temperature of the water is higher than the set temperature,

when the temperature of the water is higher than the set temperature,

when the temperature of the water is higher than the set temperature,

other similar empirical formulas may be used, not generally.

(2) Disease inference rule mining

2.1 merging the medical record data according to the extracted disease diagnosis to form a document representation of the disease, and listing D for the disease_i(i =1,2.. m) of the kth disease D_kIt calculates all the symptoms S _, which co-occur with the disease in each case history_xAnd a feature word W_yWhile calculating the symptom S_xAnd feature W_yRespectively, are denoted as TF_kxAnd TF_ky(ii) a The calculation of the word frequency can calculate the frequency for 1 time according to each 1 medical record as optimization, and can also cumulatively increase the content quality score C of the medical record according to the condition that 1 case does not appear_i；

2.2 calculating each disease D separately from the disease document representation of 2.1_kNumber of all features in the document of (1) L_kAnd the average characteristic number L of all diseases_avgFor characterizing the complexity of the disease;

2.3 calculating each symptom S separately from the disease document representation of 2.1_xAnd symptom word W_xInverse document frequency IDF of_xAnd IDF_yAnd is used for representing the prevalence degree of symptoms or characteristic words.

(3) Disease reasoning module

3.1 for a given medical record P 'to be diagnosed, extracting corresponding features according to 1.3 to obtain a symptom set S' { } of the medical record;

3.2, as a supplement, extracting a symptom feature word set W' { } according to 1.4 for a given medical record to be diagnosed;

3.3 according to 1.6, calculating the content quality score of the medical record to be diagnosed, if the score is less than a certain threshold, not performing disease reasoning judgment, and only giving a prompt of insufficient information content of the medical record;

3.4 traversing each feature S in the symptom set S' and the feature word set W_x'And W_y'The result of query 2.3 obtains the inverse document frequency IDF of the corresponding feature_x'And IDF_y'If not, using default value 0;

3.5 the degree of similarity between the disease Dk and the patient can be calculated according to the following formula:

wherein, C₁,C₂Is a constant number, C₁Values between 0 and 1 including 0 and 1, C₂Values between 0 and 10 include 0.

3.6 sort all diseases by similarity and output the highest scoring 3 or 10 diseases to recommend to the user.

Based on an alternative embodiment of the invention, the following data were found in the experiments:

training set medical record data: 40000 parts, each case history comprises the chief complaint, past history, present history, physical examination of the outpatient clinic of a patient, and the initial diagnosis made by the doctor.

Disease species: 0-800 disease names, such as: diabetes, myocarditis, hypertension, upper respiratory tract infections, positional vertigo, etc.

0-1700 symptom word banks, such as: chest tightness, asthma, vomiting, headache, cough, fever, etc.

Test set medical record data: 2800 copies in the same format as the training set, and not overlapped with the training set.

Evaluation: and if the first five diseases are the same as the diagnosis of the doctor, if the diseases are the same, the score is 1, and the score and the quality score of the medical record information are weighted and then counted into a total score.

Test results obtained based on the scheme in the related art: top5 hit rate is 71%.

According to the similarity calculation method in the alternative embodiment of the present invention, the feature extraction is performed without considering the combination of words (i.e., skipping 1.4 steps), and calculation and sorting are performed using the BM25 algorithm. Wherein C1=1.2, C2= 0.25. And (3) testing results: top5 hit rate was 79.9%.

According to the method of the alternative embodiment of the present invention, the combination of words is considered in the feature extraction. And (3) testing results: the Top5 hit rate was 87.8%.

It can be seen that alternative embodiments of the present invention have the following advantages:

(1) the extraction of the patient information not only comprises the characteristics of a symptom dictionary, but also considers the characteristics of short sentence segmentation combination, thereby reducing the probability of missing detection of symptoms to the maximum extent;

(2) each disease is regarded as a document, the relation between the symptom characteristic and the disease is regarded as the relation between a keyword and the document, the number of patients is regarded as word frequency, meanwhile, the quality weight coefficient of medical records is considered, and the relation weight between the symptom and the disease is calculated by adopting a document similarity method. The prejudice of reasoning results caused by unbalanced distribution of disease and disease species data is reduced;

(3) the information content of each disease is scored, and medical records with high scores are given higher weight in training. The influence caused by the uneven quality of the medical records is avoided.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

Through the above description of the embodiments, those skilled in the art can clearly understand that the medical record processing method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

Example 2

According to an embodiment of the present invention, there is further provided an apparatus for implementing the first medical record processing method, and fig. 5 is a block diagram of a first medical record processing apparatus provided in embodiment 2 of the present invention, and as shown in fig. 5, the apparatus includes: a first obtaining module 51, a first extracting module 52, a second extracting module 53, a second obtaining module 54 and a first determining module 55, which will be explained below.

A first obtaining module 51, configured to obtain a target medical record; a first extraction module 52, connected to the first acquisition module 51, for extracting a target symptom word set from a target medical record; a second extraction module 53, connected to the first extraction module 52, for extracting a target symptom feature word set from the target medical record based on the target symptom word set; a second obtaining module 54, connected to the second extracting module 53, configured to obtain a first weight of a target symptom word included in the target symptom word set in a predetermined disease, and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease; the first determining module 55 is connected to the second obtaining module 54, and is configured to determine a target disease corresponding to the target medical record based on a first weight of the target symptom word included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease.

It should be noted here that the first obtaining module 51, the first extracting module 52, the second extracting module 53, the second obtaining module 54 and the first determining module 55 correspond to steps S202 to S210 in embodiment 1, and the five modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the above modules may be operated in the computer terminal 10 provided in embodiment 1 as a part of the apparatus.

According to an embodiment of the present invention, there is further provided an apparatus for implementing the second medical record processing method, and fig. 6 is a block diagram of a second medical record processing apparatus provided in embodiment 2 of the present invention, and as shown in fig. 6, the apparatus includes: a first display module 61, a first receiving module 62, a third extracting module 63 and a second display module 64, which will be described below.

The first display module 61 is used for displaying a medical record input control on the interactive interface; a first receiving module 62, connected to the first display module 61, for receiving a target medical record in response to an operation on the medical record input control; a third extracting module 63, connected to the first receiving module 62, configured to, in response to an operation of a processing control for processing a target medical record, extract a target symptom feature word set from the target medical record, and extract a target symptom feature word set from the target medical record based on the target symptom word set; and a second display module 64, connected to the third extraction module 63, configured to display a target disease corresponding to the target medical record on the interactive interface, where the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

It should be noted here that the first display module 61, the first receiving module 62, the third extracting module 63, and the second display module 64 correspond to steps S302 to S308 in embodiment 1, and the four modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the above modules may be operated in the computer terminal 10 provided in embodiment 1 as a part of the apparatus.

According to an embodiment of the present invention, there is further provided an apparatus for implementing the third medical record processing method, and fig. 7 is a block diagram of a third medical record processing apparatus provided in embodiment 2 of the present invention, and as shown in fig. 7, the apparatus includes: a third display module 71, a second receiving module 72, a fourth display module 73 and a fifth display module 74, which will be described below.

The third display module 71 is configured to display a medical record input control on the interactive interface; the second receiving module 72 is configured to respond to the operation of the medical record input control, and display the target medical record on the interactive interface; the fourth display module 73 is configured to display a target symptom word set and a target symptom feature word set of the target medical record on the interactive interface; and a fifth display module 74, configured to display, in response to an operation on the target medical record, a target disease corresponding to the target medical record on the interactive interface, where the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

It should be noted here that the third display module 71, the second receiving module 72, the fourth display module 73, and the fifth display module 74 correspond to steps S402 to S408 in embodiment 1, and the four modules and the corresponding steps implement the same example and application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the above modules may be operated in the computer terminal 10 provided in embodiment 1 as a part of the apparatus.

Example 3

The embodiment of the invention can provide a computer terminal which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced with a terminal device such as a mobile terminal.

Optionally, in this embodiment, the computer terminal may be located in at least one network device of a plurality of network devices of a computer network.

In this embodiment, the computer terminal may execute the program code of the following steps in the medical record processing method of the application program: acquiring a target medical record; extracting a target symptom word set from a target medical record; extracting a target symptom characteristic word set from a target medical record based on the target symptom word set; acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; and determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease.

Alternatively, fig. 8 is a block diagram of a computer terminal according to an embodiment of the present invention. As shown in fig. 8, the computer terminal may include: one or more processors 802 (only one shown), memory 804, and the like.

The memory can be used for storing software programs and modules, such as program instructions/modules corresponding to the medical record processing method and device in the embodiments of the present invention, and the processor executes various functional applications and data processing by operating the software programs and modules stored in the memory, that is, the medical record processing method is implemented. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: acquiring a target medical record; extracting a target symptom word set from a target medical record; extracting a target symptom characteristic word set from a target medical record based on the target symptom word set; acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; and determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease.

Optionally, the processor may further execute the program code of the following steps: dividing the target medical record into a plurality of short sentences; extracting candidate symptom words from the short sentences; and in the case that the candidate symptom words can be matched into a preset symptom word list, determining the candidate symptom words as target symptom words and collecting the target symptom words into a target symptom word set.

Optionally, the processor may further execute the program code of the following steps: deleting the target symptom words included in the target symptom word set from the target medical record to obtain residual short sentences; performing word segmentation on the remaining short sentences to obtain a plurality of word segments; and combining the multiple word segments respectively to obtain target symptom characteristic words, and collecting the target symptom characteristic words into a target symptom characteristic word set.

Optionally, the processor may further execute the program code of the following steps: acquiring a sample medical record set, wherein the sample medical record set comprises sample medical record description information and a sample medical record result; acquiring a sample symptom word set and a sample characteristic word set of a sample medical record of the sample medical record set from the sample medical record description information; and determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease based on the sample symptom word set and the sample feature word set.

Optionally, the processor may further execute the program code of the following steps: aiming at a sample disease corresponding to a sample medical record result in a sample medical record set, acquiring the times of the sample symptomatic words in the sample symptomatic word set appearing in the sample medical record set and the times of the sample characteristic words in the sample characteristic word set appearing in the sample medical record set; acquiring a first weight of a sample symptom word in the sample symptom word set in a sample disease based on the frequency of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the frequency of the feature word in the sample feature word set appearing in the sample medical record set; when the target symptom words are sample symptom words and the predetermined disease is a sample disease, determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease as a first weight of the sample symptom words in the sample disease, and determining a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease as a second weight of the sample feature words in the sample disease.

Optionally, the processor may further execute the program code of the following steps: determining the quality score of the sample medical record based on the sample symptom word set and the sample characteristic word set of the sample medical record in the sample symptom word set; determining a third weight of the sample medical record based on the quality score of the sample medical record; the method comprises the steps of obtaining a first weight of a sample symptom word in a sample symptom word set in a sample disease based on the number of times and a third weight of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and obtaining a second weight of a sample feature word in a sample feature word set in the sample disease based on the number of times and the third weight of the feature word in the sample feature word set appearing in the sample medical record set.

Optionally, the processor may further execute the program code of the following steps: determining similarity between a disease corresponding to the target medical record and a plurality of candidate diseases based on a first weight of a target symptom word in a predetermined disease and a second weight of a target symptom feature word in a predetermined disease, wherein the first weight of the target symptom word is included in the target symptom word set; and determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the candidate diseases.

Optionally, the processor may further execute the program code of the following steps: sequencing the similarity of the disease corresponding to the target medical record and a plurality of candidate diseases, and determining the first N candidate diseases with the highest similarity as the target diseases corresponding to the target medical record, wherein N is a positive integer; or determining the candidate diseases with the similarity higher than the similarity threshold as the target diseases corresponding to the target medical records.

Optionally, the processor may further execute the program code of the following steps: determining a quality score of the target medical record based on the target symptom word set and the target symptom characteristic word set; and under the condition that the quality score is higher than a quality score threshold value, acquiring a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

Optionally, the processor may further execute the program code of the following steps: determining the quantity of normal information and the quantity of abnormal information in the target medical record based on the target symptom word set and the target symptom characteristic word set; and determining the quality score of the target medical record based on the quantity of the normal information and the quantity of the abnormal information in the target medical record.

The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: displaying a medical record input control on the interactive interface; receiving a target medical record in response to the operation of the medical record input control; in response to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set; and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: displaying a medical record input control on the interactive interface; responding to the operation of the medical record input control, and displaying the target medical record on the interactive interface; responding to the operation of the target medical record, and displaying a target symptom word set and a target symptom characteristic word set of the target medical record on an interactive interface; and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

The embodiment of the invention provides a medical record processing scheme. The target symptom word set and the target symptom characteristic word set are extracted from the target medical record, the weights of the target symptom words and the target symptom characteristic words in the preset diseases are obtained, and finally the target diseases corresponding to the target medical record are determined based on the weights, so that the aims of avoiding manually determining the weights, increasing the symptom table notations corresponding to the diseases and considering the relation among the symptom table notations are fulfilled, the technical effect of directly, efficiently and accurately determining the diseases suffered by the patient according to the medical record of the patient is achieved, and the technical problems of low efficiency and high error rate when the corresponding diseases are determined according to the medical record of the patient in the related technology are solved.

It can be understood by those skilled in the art that the structure shown in fig. 8 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 8 is a diagram illustrating a structure of the electronic device. For example, it may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 8, or have a different configuration than shown in FIG. 8.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the computer-readable storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

Example 4

Embodiments of the present invention also provide a computer-readable storage medium. Optionally, in this embodiment, the computer-readable storage medium may be configured to store the program code executed by the medical record processing method provided in embodiment 1.

Optionally, in this embodiment, the computer-readable storage medium may be located in any one of a group of computer terminals in a computer network, or in any one of a group of mobile terminals.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: acquiring a target medical record; extracting a target symptom word set from a target medical record; extracting a target symptom characteristic word set from a target medical record based on the target symptom word set; acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease; and determining the target disease corresponding to the target medical record based on the first weight of the target symptom words included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: dividing the target medical record into a plurality of short sentences; extracting candidate symptom words from the short sentences; and in the case that the candidate symptom words can be matched into a preset symptom word list, determining the candidate symptom words as target symptom words and collecting the target symptom words into a target symptom word set.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: deleting the target symptom words included in the target symptom word set from the target medical record to obtain residual short sentences; performing word segmentation on the remaining short sentences to obtain a plurality of word segments; and combining the multiple word segments respectively to obtain target symptom characteristic words, and collecting the target symptom characteristic words into a target symptom characteristic word set.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: acquiring a sample medical record set, wherein the sample medical record set comprises sample medical record description information and a sample medical record result; acquiring a sample symptom word set and a sample characteristic word set of a sample medical record of the sample medical record set from the sample medical record description information; and determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease and a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease based on the sample symptom word set and the sample feature word set.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: aiming at a sample disease corresponding to a sample medical record result in a sample medical record set, acquiring the times of the sample symptomatic words in the sample symptomatic word set appearing in the sample medical record set and the times of the sample characteristic words in the sample characteristic word set appearing in the sample medical record set; acquiring a first weight of a sample symptom word in the sample symptom word set in a sample disease based on the frequency of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the frequency of the feature word in the sample feature word set appearing in the sample medical record set; when the target symptom words are sample symptom words and the predetermined disease is a sample disease, determining a first weight of the target symptom words included in the target symptom word set in the predetermined disease as a first weight of the sample symptom words in the sample disease, and determining a second weight of the target symptom feature words included in the target symptom feature word set in the predetermined disease as a second weight of the sample feature words in the sample disease.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining the quality score of the sample medical record based on the sample symptom word set and the sample characteristic word set of the sample medical record in the sample symptom word set; determining a third weight of the sample medical record based on the quality score of the sample medical record; the method comprises the steps of obtaining a first weight of a sample symptom word in a sample symptom word set in a sample disease based on the number of times and a third weight of the sample symptom word in the sample symptom word set appearing in the sample medical record set, and obtaining a second weight of a sample feature word in a sample feature word set in the sample disease based on the number of times and the third weight of the feature word in the sample feature word set appearing in the sample medical record set.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining similarity between a disease corresponding to the target medical record and a plurality of candidate diseases based on a first weight of a target symptom word in a predetermined disease and a second weight of a target symptom feature word in a predetermined disease, wherein the first weight of the target symptom word is included in the target symptom word set; and determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and the candidate diseases.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: sequencing the similarity of the disease corresponding to the target medical record and a plurality of candidate diseases, and determining the first N candidate diseases with the highest similarity as the target diseases corresponding to the target medical record, wherein N is a positive integer; or determining the candidate diseases with the similarity higher than the similarity threshold as the target diseases corresponding to the target medical records.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining a quality score of the target medical record based on the target symptom word set and the target symptom characteristic word set; and under the condition that the quality score is higher than a quality score threshold value, acquiring a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: determining the quantity of normal information and the quantity of abnormal information in the target medical record based on the target symptom word set and the target symptom characteristic word set; and determining the quality score of the target medical record based on the quantity of the normal information and the quantity of the abnormal information in the target medical record.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: displaying a medical record input control on the interactive interface; receiving a target medical record in response to the operation of the medical record input control; in response to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set; and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

Optionally, in this embodiment, the computer readable storage medium is configured to store program code for performing the following steps: displaying a medical record input control on the interactive interface; responding to the operation of the medical record input control, and displaying the target medical record on the interactive interface; displaying a target symptom word set and a target symptom characteristic word set of the target medical record on an interactive interface; and responding to the operation of the target medical record, and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in the predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a computer-readable storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned computer-readable storage media comprise: 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.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (14)

1. A medical record processing method is characterized by comprising the following steps:

acquiring a target medical record;

extracting a target symptom word set from the target medical record;

extracting a target symptom characteristic word set from the target medical record based on the target symptom word set;

acquiring a first weight of a target symptom word included in the target symptom word set in a preset disease and a second weight of a target symptom feature word included in the target symptom feature word set in the preset disease;

and determining the target disease corresponding to the target medical record based on the first weight of the target symptom word included in the target symptom word set in the predetermined disease and the second weight of the target symptom feature word included in the target symptom feature word set in the predetermined disease.

2. The method of claim 1, wherein extracting the set of target symptomatic words from the target medical record comprises:

dividing the target medical record into a plurality of short sentences;

extracting candidate symptom words from the short sentences;

and in the case that the candidate symptom words can be matched into a preset symptom word list, determining the candidate symptom words as target symptom words and collecting the target symptom words into the target symptom word set.

3. The method of claim 1, wherein extracting a set of target symptom feature words from the target medical record based on the set of target symptom words comprises:

deleting the target symptom words included in the target symptom word set from the target medical record to obtain residual short sentences;

performing word segmentation on the remaining short sentences to obtain a plurality of word segments;

and combining the multiple word segments respectively to obtain the target symptom characteristic words, and collecting the target symptom characteristic words into the target symptom characteristic word set.

4. The method according to claim 1, wherein the obtaining a first weight of a target symptom word included in the target symptom word set in a predetermined disease, and a second weight of a target symptom word included in the target symptom word set in the predetermined disease comprises:

acquiring a sample medical record set, wherein the sample medical record set comprises sample medical record description information and a sample medical record result;

acquiring a sample symptom word set and a sample characteristic word set of a sample medical record of the sample medical record set from the sample medical record description information;

based on the sample symptom word set and the sample characteristic word set, determining a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom characteristic word included in the target symptom characteristic word set in the predetermined disease.

5. The method according to claim 4, wherein the determining a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom feature word included in the target symptom word set in the predetermined disease based on the sample symptom word set and the sample feature word set comprises:

aiming at a sample disease corresponding to a sample medical record result in the sample medical record set, acquiring the times of appearance of sample symptomatic words in the sample symptomatic word set in the sample medical record set and the times of appearance of sample characteristic words in the sample characteristic word set in the sample medical record set;

acquiring a first weight of a sample symptom word in the sample symptom word set in the sample disease based on the number of times of appearance of the sample symptom word in the sample medical record set, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the number of times of appearance of a feature word in the sample feature word set in the sample medical record set;

when the target symptom word is the sample symptom word and the predetermined disease is the sample disease, determining a first weight of the target symptom word included in the target symptom word set in the predetermined disease as a first weight of the sample symptom word in the sample disease, and determining a second weight of the target symptom word included in the target symptom feature word set in the predetermined disease as a second weight of the sample feature word in the sample disease.

6. The method of claim 5, wherein obtaining a first weight of a sample symptom word in the sample symptom word set in the sample disease based on a number of times the sample symptom word in the sample symptom word set appears in the sample medical record set, and obtaining a second weight of a sample feature word in the sample feature word set in the sample disease based on a number of times the feature word in the sample feature word set appears in the sample medical record set comprises:

determining a quality score of the sample medical record based on a sample symptom word set and a sample characteristic word set of the sample medical record in the sample symptom word set;

determining a third weight of the sample medical record based on the quality score of the sample medical record;

acquiring a first weight of a sample symptom word in the sample symptom word set in the sample disease based on the number of times of appearance of the sample symptom word in the sample medical record set and the third weight, and acquiring a second weight of a sample feature word in the sample feature word set in the sample disease based on the number of times of appearance of the feature word in the sample feature word set in the sample medical record set and the third weight.

7. The method according to claim 1, wherein the determining the target medical record corresponding to the target medical record based on a first weight of the target symptom word included in the target symptom word set in a predetermined disease and a second weight of the target symptom word included in the target symptom word set in the predetermined disease comprises:

determining similarity between a disease corresponding to the target medical record and a plurality of candidate diseases based on a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease;

and determining the target disease corresponding to the target medical record based on the similarity between the disease corresponding to the target medical record and a plurality of candidate diseases.

8. The method of claim 7, wherein determining the target medical record corresponding to the target medical record based on the similarity of the target medical record corresponding to the disease to a plurality of candidate diseases comprises:

sequencing the similarity between the disease corresponding to the target medical record and a plurality of candidate diseases, and determining the first N candidate diseases with the highest similarity as the target diseases corresponding to the target medical record, wherein N is a positive integer;

or determining the candidate diseases with the similarity higher than the similarity threshold as the target diseases corresponding to the target medical record.

9. The method according to any one of claims 1 to 8, wherein the obtaining a first weight of a target symptom word included in the target symptom word set in a predetermined disease, and a second weight of a target symptom word included in the target symptom word set in the predetermined disease comprises:

determining a quality score of the target medical record based on the target symptom word set and the target symptom feature word set;

and under the condition that the quality score is higher than a quality score threshold value, acquiring a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

10. The method of claim 9, wherein determining the quality score for the target medical record based on the set of target symptom words and the set of target symptom feature words comprises:

determining the quantity of normal information and the quantity of abnormal information in the target medical record based on the target symptom word set and the target symptom characteristic word set;

and determining the quality score of the target medical record based on the quantity of the normal information and the quantity of the abnormal information in the target medical record.

11. A medical record processing method is characterized by comprising the following steps:

displaying a medical record input control on the interactive interface;

receiving a target medical record in response to the operation of the medical record input control;

in response to the operation of a processing control for processing the target medical record, extracting a target symptom word set from the target medical record, and extracting a target symptom feature word set from the target medical record based on the target symptom word set;

and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

12. A medical record processing method is characterized by comprising the following steps:

displaying a medical record input control on the interactive interface;

responding to the operation of the medical record input control, and displaying a target medical record on the interactive interface;

displaying a target symptom word set and a target symptom feature word set of the target medical record on the interactive interface;

and responding to the operation of the target medical record, and displaying a target disease corresponding to the target medical record on the interactive interface, wherein the target disease is determined based on a first weight of a target symptom word included in the target symptom word set in a predetermined disease and a second weight of a target symptom feature word included in the target symptom feature word set in the predetermined disease.

13. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the medical record processing method according to any one of claims 1 to 12.

14. A computer device, comprising: a memory and a processor, wherein the processor is capable of,

the memory stores a computer program;

the processor is configured to execute the computer program stored in the memory, and the computer program causes the processor to execute the medical record processing method according to any one of claims 1 to 12.

Images