Knowledge extraction for clinical question answering: preliminary results

The combination of recent developments in question an-swering research and the unparalleled resources devel-oped specifically for automatic semantic processing of text in the medical domain provides a unique opportu-nity to explore complex question answering in the clin-ical domain. In this paper, we attempt to operationalize major aspects of evidence-based medicine in the form of knowledge extractors that serve as the fundamental building blocks of a clinical question answering sys-tem. Our evaluations demonstrate that domain-specific knowledge can be effectively leveraged to extract PICO frame elements from MEDLINE abstracts. Clinical in-formation systems in support of physicians ’ decision-making process have the potential to improve the qual-ity of patient care in real-world settings