论文信息 - Using Electronic Medical Records and Physician Data to Improve Information Retrieval for Evidence-Based Care

Using Electronic Medical Records and Physician Data to Improve Information Retrieval for Evidence-Based Care

Healthcare practitioners are increasingly using search functionality embedded in Electronic Medical Record (EMR) software to search for relevant evidence summaries at point of care. We introduce a learning to rank approach that exploits information carried in EMR data and UpToDate user accounts to (significantly) improve ranking results, compared to a comparable model that does not exploit such features.

[1] Thorsten Joachims,et al. Optimizing search engines using clickthrough data , 2002, KDD.

[2] Jaime Teevan,et al. Understanding and predicting personal navigation , 2011, WSDM '11.

[3] Wei Chu,et al. Modeling the impact of short- and long-term behavior on search personalization , 2012, SIGIR '12.

[4] Hang Li,et al. A Short Introduction to Learning to Rank , 2011, IEICE Trans. Inf. Syst..

[5] Christian Poellabauer,et al. An architecture for personalized health information retrieval , 2012, SHB '12.

[6] Hang Li. Learning to Rank for Information Retrieval and Natural Language Processing , 2011, Synthesis Lectures on Human Language Technologies.

[7] ChengXiang Zhai,et al. Mining long-term search history to improve search accuracy , 2006, KDD '06.

[8] Keith R. Godfrey,et al. Correlation methods , 1980, Autom..

[9] Gerard Salton,et al. Research and Development in Information Retrieval , 1982, Lecture Notes in Computer Science.

[10] Lei Yang,et al. Query log analysis of an electronic health record search engine. , 2011, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[11] Thore Graepel,et al. Large Margin Rank Boundaries for Ordinal Regression , 2000 .

[12] Daniel M. Stein,et al. An analysis of clinical queries in an electronic health record search utility , 2010, Int. J. Medical Informatics.