A Hybrid Approach to Clinical Question Answering
Sadid A. Hasan, Xianshu Zhu, Dong Yao, Joey Liu, Oladimeji Farri · 2016
In this paper, we describe our clinical ques-tion answering system developed and submit-ted for the Text Retrieval Conference (TREC 2014) Clinical Decision Support (CDS) track. The task for this track was to retrieve relevant biomedical articles to answer generic clini-cal questions about medical case reports. As part of our maiden participation in TREC, we submitted a single run using a hybrid Natural Language Processing (NLP)-driven approach to accomplish the given task. Evaluation re-sults showed that our clinical question answer-ing system achieved the best scores in two of eight dual-judged topics: #5 and 27, and per-formed relatively better compared to the me-