Knowledge discovery of diseases symptoms and rehabilitation measures in Q&A communities

Abstract

Rehabilitation-related diseases have long recovery times, making frequent hospital visits impractical for patients. There is a high demand for online rehabilitation advice, but valuable Q&A information in online health communities remains largely untapped, leading to wasted medical resources. This study developed a BERT-BiGRU-attention model to extract three types of entity relationships: disease symptoms, appropriate rehabilitation measures, and inappropriate rehabilitation measures. This model achieved optimal knowledge extraction results. We then used a clustering analysis model to group disease-related knowledge, helping to uncover useful information for rehabilitation patients, assist in medical diagnosis, and enhance health education.