Intelligent auxiliary diagnosis method based on deep learning and ensemble classification

Abstract

The invention discloses an intelligent auxiliary diagnosis method based on deep learning and ensemble classification. Through named entity identification and relation extraction, entities and attributes in the chief complaint and the current medical history are accurately extracted, and invalid information is removed. In the label topic model, the position weight of the feature words is added, andthe proportion of the feature words at the key position is increased. Adjusting parameters are added into a loss function of a multilayer perceptron model, so that the problem caused by uneven sampledistribution is solved. For the same sample, the classification boundaries obtained by different classification methods are different, so that the label topic model and the multi-layer perceptron model are integrated by adopting a stacking integration method, and the disease prediction accuracy is improved.

Description

technical field [0001] The invention relates to the field of medical information technology and the field of artificial intelligence technology, and designs an intelligent auxiliary diagnosis method based on deep learning and integrated classification. Background technique [0002] With the rapid development of information technology and Internet technology, electronic medical records, which play a central role in the construction of hospital informatization and digitization, are constantly being optimized and improved. Electronic medical records contain patient symptom description information, which can assist doctors to quickly make a preliminary diagnosis of the disease when faced with patients with similar symptoms. This is of great guiding significance for the initial diagnosis of difficult and miscellaneous diseases or the rapid investigation of emergency patients, and it is also conducive to improving the diagnostic ability of doctors by sharing their diagnosis and tr...

AI Technical Summary

Problems solved by technology

First of all, it is necessary to be able to accurately extract named entities such as symptoms and signs in medical record texts, and the extraction of information requires the support of named entity extraction technology. At this stage, the named entity extraction technology based on deep learning still has problems such as low recognition efficiency and insufficient performance.

Images