Medical Knowledge Extraction Using Truth Discovery Framework

Abstract

With the booming new technology, the traditional health care system is undergoing an evolution. The medical crowd sourced question answering (Q&A) website is one among them. There are a lot of patients and doctors involved in these crowd sourced question and answering websites. The valuable information from these medical crowd sourced Q&A websites can benefit patients, doctors and the society.  Facing the daunting scale of information generated on medical Q&A websites every day, it is unrealistic to full fill this task via supervised method due to the expensive annotation cost. In this concept, we propose a Medical Knowledge Extraction (MKE) system that can automatically provide high quality knowledge triples extracted from the noisy question-answer pairs, and at the same time, estimate expertise for the doctors who give answers on these Q&A websites. The MKE system is built upon a truth discovery framework, where we jointly estimate trustworthiness of answers and doctor expertise from the data without any supervision. We further tackle three unique challenges in the medical knowledge extraction task, namely representation of noisy input, multiple linked truths, and the long-tail phenomenon in the data. The MKE system is applied on real-world datasets crawled from xywy.com, one of the most popular medical crowd sourced Q&A websites. This system can automatically provide high quality knowledge information extracted from the noisy question-answer pairs.