A Novel Temporal Similarity Measure for Patients Based on Irregularly Measured Data in Electronic Health Records

• Authors: Ying Sha, Georgia Institute of Technology; Janani Venugopalan, Georgia Institute of Technology; Dongmei Wang, Emory University
• Journal Title: BCB '16: Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
• Volume: Volume 2016
• Publisher: ACM Digital Library | 2016-01-01, Pages 337-344
• Type of Work: Article | Post-print: After Peer Review
• Publisher DOI: http://doi.org/10.1145/2975167.2975202
• Subjects: Engineering, Biomedical; Health Sciences, Public Health; Health Sciences, Health Care Management
• Keywords: Science & Technology; Technology; Life Sciences & Biomedicine; Computer Science, Interdisciplinary Applications; Mathematical & Computational Biology; Medical Informatics; Computer Science; Patient similarity; temporal similarity measure; laboratory tests; acute kidney injury; sepsis; Children

Abstract

Patient similarity measurement is an important tool for cohort identification in clinical decision support applications. A reliable similarity metric can be used for deriving diagnostic or prognostic information about a target patient using other patients with similar trajectories of health-care events. However, the measure of similar care trajectories is challenged by the irregularity of measurements, inherent in health care. To address this challenge, we propose a novel temporal similarity measure for patients based on irregularly measured laboratory test data from the Multiparameter Intelligent Monitoring in Intensive Care database and the pediatric Intensive Care Unit (ICU) database of Children's Healthcare of Atlanta. This similarity measure, which is modified from the Smith Waterman algorithm, identifies patients that share sequentially similar laboratory results separated by time intervals of similar length. We demonstrate the predictive power of our method; that is, patients with higher similarity in their previous histories will most likely have higher similarity in their later histories. In addition, compared with other non-temporal measures, our method is stronger at predicting mortality in ICU patients diagnosed with acute kidney injury and sepsis.