Electronic medical record quality inspection method and device, storage medium and equipment

Abstract

The invention discloses an electronic medical record quality inspection method and device, a storage medium and equipment, and the method comprises the steps: firstly obtaining a to-be-inspected target electronic medical record, inputting the to-be-inspected target electronic medical record into a pre-constructed comparison learning model, and carrying out the recognition to obtain a feature vector corresponding to each clause in the target electronic medical record; wherein the comparative learning model is obtained by utilizing a comparative learning framework to train according to the related sentence pairs and the non-related sentence pairs; and then, inputting the feature vector corresponding to each clause into a pre-constructed diagnosis result prediction model, performing prediction to obtain a target diagnosis result meeting a preset primary selection condition, matching the target diagnosis result with a real diagnosis result, and performing quality inspection on the target electronic medical record according to a matching result. Therefore, the feature vectors which correspond to each clause in the target electronic medical record and are obtained through recognition of the pre-constructed comparative learning model and have better comparability and discriminability can be utilized to obtain a prediction diagnosis result with higher accuracy and a quality inspection result of the electronic medical record.

Description

technical field [0001] The present application relates to the field of intelligent medical technology, and in particular to a quality inspection method, device, storage medium and equipment for electronic medical records. Background technique [0002] With the rapid development of information technology, electronic medical record systems have gradually become popular in hospitals at all levels. Compared with traditional paper medical records, electronic medical records are more convenient to write and more flexible to access, which helps to improve the work efficiency of medical staff. But electronic medical records can also be of poor quality. For example, the diagnosis may be unreasonable due to the doctor's operation error and other circumstances, resulting in a decline in the quality of the electronic medical record, which cannot accurately reflect the actual condition of the patient, and brings great risks in diagnosis and treatment. Based on this, in order to improve ...

AI Technical Summary

Problems solved by technology

[0003] At present, there are usually two quality inspection methods for electronic medical records: one is based on the idea of ​​classification, automatic diagnosis and prediction based on classification framework or automatic diagnosis and prediction of diagnosis results based on pre-training framework, and conduct quality inspection on electronic medical records according to the diagnosis results , but this method has disadvantages such as poor scalability, low precision of subdivided diseases, and slow calculation speed; another commonly used quality inspection method is based on automatic diagnosis and prediction of similarity calculations, and according to the diagnostic results of electronic medical records Although this method overcomes the three main problems in the aforementioned classification methods, this method has brought new problems: low performance, that is, poor predictive performance for disease diagnosis results, and cannot be timely and accurately Reflect the quality of electronic medical records, which leads to inaccurate quality inspection results of electronic medical records

Images