Fever disease deep-learning auxiliary diagnosis system based on text medical history for children

Abstract

The invention relates to a fever disease deep-learning auxiliary diagnosis system based on text medical history for children. The system includes a medical history input module, a text structuralizingmodule, a characteristic extraction module and a result output module, wherein the medical input module is used for receiving the medical history in a free text form; the text structuralizing moduleis linked with the medical history input module and adopts a natural language processing method for processing the medical history in the free text form to obtain structuralized data; the characteristic extraction module is linked with the text structuralizing module and used for extracting diagnosis characteristics from the structuralized data; the result output module is linked with the characteristic extraction module and used for utilizing a neural network to carry out prediction of disease classification on the current medical history records according to the extracted diagnosis characteristics and a diagnosis model learned from the past medical history records, and then outputting diagnosis results. Compared with the prior art, on the basis of a natural language processing and diagnosis model of deep learning, the diagnosis accuracy of the system can exceed a grassroots doctor level, the system can function stably, and therefore a real help can be offered to grassroots medical workers.

Description

technical field [0001] The invention relates to an auxiliary diagnosis system, in particular to a text-based medical record-based deep learning auxiliary diagnosis system for febrile diseases in children. Background technique [0002] Fever diseases are a very important category of pediatric diseases, with a high proportion and high risk. Because of the confounding symptoms of different febrile illnesses, physicians have difficulty making a diagnosis, requiring decision-making aids and reference to similar medical records. [0003] Existing auxiliary diagnostic systems are mainly divided into two categories: [0004] 1. Based on structured information. All medical history, symptoms, examination results and other information are represented in a structured way, and on this basis, through statistical learning inference or knowledge base-based reasoning, decision-making assistance is provided, and similar medical records are searched according to the matching degree of struct...

AI Technical Summary

Problems solved by technology

Its main disadvantages are: input is not flexible, and patient information is difficult to express in a purely structured way; a large amount of historical non-institutional medical record information cannot be used, which not only limits the amount of training data for statistical learning, but also reduces available data. Similar medical record pool for reference; strong dependence on unified structured representation, information cannot be used across systems

Its main disadvantages are: the decision-making auxiliary information is not accurate enough, and doctors need to further read the indexed literature; it is difficult to learn diagnostic models from historical cases

Images