Aggregating Evidence from Hospital Departments to Improve Medical Records Search

Searching medical records is challenging due to their inherent implicit knowledge – such knowledge may be known by medical practitioners, but it is hidden from an information retrieval (IR) system. For example, it is intuitive for a medical practitioner to assert that patients with heart disease are likely to have records from the hospital’s cardiology department. In this paper, we propose to capture such implicit knowledge, by grouping aggregates of medical records from individual hospital departments, which we refer to as department-level evidence, to enhance a medical records search engine. Specifically, we propose two approaches to build the department-level evidence based on a federated search and a voting paradigm, respectively. In addition, we introduce an extended voting technique that can leverage this department-level evidence while ranking. We evaluate the retrieval effectiveness of our approaches using the TREC 2011 Medical Records track. Our results show that modelling department-level evidence in medical records search improves retrieval effectiveness. In particular, our proposed voting-based technique obtains results comparable to the best submitted TREC 2011 systems without requiring any of the external resources that are exploited in those systems.