Deep learning method and system for electronic medical record

Abstract

The invention discloses a deep learning method and system for an electronic medical record. The method comprises the following steps: S1, acquiring specialized physical examination results and evaluation results of a plurality of patients in an electronic medical record system to obtain an electronic medical record data set, and performing missing data deletion and data expression unified preprocessing operation on the electronic medical record data set; S2, performing word vector conversion operation on the electronic medical record data set subjected to the preprocessing operation to obtainelectronic medical record word vector representation; S3, constructing a model by adopting a bidirectional GRU network and an attention mechanism, and inputting the electronic medical record word vector representation into the model for training to obtain a prediction model; and S4, performing preprocessing and word vector representation on newly acquired electronic medical record data through thesteps S1 and S2, and inputting the data into the prediction model to obtain a prediction result. With considering that different words and different sentences have different influences on result prediction, feature extraction is carried out by adopting word-level and sentence-level multi-level attention models, so that the prediction accuracy is improved.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to a deep learning method and system for electronic medical records. Background technique [0002] Stroke is an acute cerebrovascular disease. It is a group of diseases caused by the sudden rupture of blood vessels in the brain or the inability of blood to flow into the brain due to blood vessel blockage, which causes brain tissue damage, and can lead to death in severe cases. Hemiplegia, so you can know in time whether you have the possibility of hemiplegia of stroke, so as to seek medical treatment in time. With the application of machine learning, data mining and other technologies in the medical field, it is possible to realize computer-aided diagnosis based on patient conditions, but this type of method mainly uses patient medical information for feature extraction, and then classifies the feature extraction results, and the cost is relatively high And inconvenient. And existing ...

AI Technical Summary

Problems solved by technology

With the application of machine learning, data mining and other technologies in the medical field, it is possible to realize computer-aided diagnosis based on patient conditions, but this type of method mainly uses patient medical information for feature extraction, and then classifies the feature extraction results, and the cost is relatively high and inconvenient

And existing machine learning methods cannot judge the degree of hemiplegia

Images