Answering medical questions in Chinese using automatically mined knowledge and deep neural networks: an end-to-end solution

• Published in: BMC bioinformatics Vol. 23; no. 1; pp. 136 - 32
• Main Authors: Zhang, Li, Yang, Xiaoran, Li, Shijian, Liao, Tianyi, Pan, Gang
• Format: Journal Article
• Language: English
• Published: England BioMed Central 15.04.2022; BMC
• Subjects: Accuracy; Artificial neural networks; Bootstrapping; China; Chinese languages; Deep learning; Electronic Health Records; Internet; Knowledge; Knowledge bases (artificial intelligence); knowledge graph; Knowledge representation; Language; Medical records; Medical research; Memory neural network; Natural Language Processing; Neural networks; Neural Networks, Computer; Quality assurance; Question-answering system; Questions; Search engines; Segmentation; Semantics; Software; Statistical methods; Taxonomy; Text mining; Usability; China; Bootstrapping; Deep learning; Memory neural network; Text mining; Question-answering system; Natural language processing; knowledge graph
• DOI: 10.1186/s12859-022-04658-2
• ISSN: 1471-2105

Medical information has rapidly increased on the internet and has become one of the main targets of search engine use. However, medical information on the internet is subject to the problems of quality and accessibility, so ordinary users are unable to obtain answers to their medical questions conveniently. As a solution, researchers build medical question answering (QA) systems. However, research on medical QA in the Chinese language lags behind work on English-based systems. This lag is mainly due to the difficulty of constructing a high-quality knowledge base and the underutilization of medical corpora in the Chinese language. This study developed an end-to-end solution to implement a medical QA system for the Chinese language with low cost and time. First, we created a high-quality medical knowledge graph from hospital data (electronic health/medical records) in a nearly automatic manner that trained a supervised model based on data labeled using bootstrapping techniques. Then, we designed a QA system based on a memory-based neural network and attention mechanism. Finally, we trained the system to generate answers from the knowledge base and a QA corpus on the internet. Bootstrapping and deep neural network techniques can construct a knowledge graph from electronic health/medical records with satisfactory precision and coverage. Our proposed context bridge mechanisms perform training with a variety of language features. Our QA system can achieve state-of-the-art quality in answering medical questions with constrained topics. As we evaluated, complex Chinese language processing techniques, such as segmentation and parsing, were not necessary for practice and complex architectures were not necessary to build the QA system. Lastly, we created an application using our method for internet QA usage.