A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
This paper describes ETH Zurich's submission to the TREC 2016 Clinical Decision Support (CDS) track. In three successive stages, we apply query expansion based on literal as well as semantic term matches, rank documents in a negation-aware manner and, finally, re-rank them based on clinical intent types as well as semantic and conceptual affinity to the medical case in question. Empirical results show that the proposed method can distill patient representations from raw clinical notes thatdblp:conf/trec/GreuterJKMMRE16 fatcat:utpyi6isvjaejp5gblacyln6ze