Care episode retrieval: distributional semantic models for information retrieval in the clinical domain. Issue 2 (December 2015)

• Record Type: Journal Article
• Authors: Moen, Hans; Ginter, Filip; Marsi, Erwin; Peltonen, Laura-Maria; Salakoski, Tapio; Salanterä, Sanna
• Is Part Of: BMC medical informatics and decision making. Volume 15:Issue 2(2015)
• Page Start: 1
• Page End: 19
• Publication Date: 2015-12
• Subjects: Medical informatics -- Periodicals; Clinical medicine -- Decision making -- Periodicals; 610.285
• DOI: 10.1186/1472-6947-15-S2-S2
• Languages: English
• ISSNs: 1472-6947

Abstract

Abstract Patients' health related information is stored inelectronic health records (EHRs) by health service providers. These records include sequential documentation of care episodes in the form of clinical notes. EHRs are used throughout the health care sector by professionals, administrators and patients, primarily for clinical purposes, but also for secondary purposes such as decision support and research. The vast amounts of information in EHR systems complicate information management and increase the risk of information overload. Therefore, clinicians and researchers need new tools to manage the information stored in the EHRs. A common use case is, given a - possibly unfinished - care episode, to retrieve the most similar care episodes among the records. This paper presents several methods for information retrieval, focusing on care episode retrieval, based on textual similarity, where similarity is measured through domain-specific modelling of the distributional semantics of words. Models include variants ofrandom indexing and the semantic neural network modelword2vec . Two novel methods are introduced that utilize the ICD-10 codes attached to care episodes to better induce domain-specificity in the semantic model. We report on experimental evaluation of care episode retrieval that circumvents the lack of human judgements regarding episode relevance. Results suggest that several of the methods proposed outperform a state-of-the art search engine (Lucene) on the retrieval task.