Layout 1 ISDS Annual Conference Proceedings 2012. This is an Open Access article distributed under the terms of the Creative Commons Attribution- Noncommercial 3.0 Unported License (http://creativecommons.org/licenses/by-nc/3.0/), permitting all non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited. ISDS 2012 Conference Abstracts An Algorithm That Identifies Coronary and Heart Failure Events In The Electronic Health Record Jawali Jaranilla*1, Thomas E. Kottke1 and Courtney J. Baechler2 1Health Partners Institute for Education and Research, Minneapolis, MN, USA; 2University of Minnesota, Minneapolis, MN, USA Objective The objective of this project was to identify criteria that accurately categorize acute coronary and heart failure events exclusively with electronic health record data so that the medical record can be used for surveillance without manual record review. Introduction Surveillance to track the incidence, prevalence and treatment of disease is a fundamental task of public health. The advent of univer- sal health care coverage in the United States and electronic health records could make the medical record a valuable disease surveil- lance tool. This can only happen, however, if the necessary data can be extracted from the medical record without manual review. Methods We serially compared 3 different computer algorithms to manual record review. The first two algorithms relied on ICD9CM codes, tro- ponin levels, ECG data and echocardiographic data. The 3rd algo- rithm relied on a very detailed coding system, IMO statements, troponin levels and echocardiographic data. Results Cohen’s Kappa for the initial algorithm was 0.47 (95%CI 0.41- 0.54). Cohen’s Kappa was 0.61 (95%CI 0.55-0.68) for the second al- gorithm. Cohen’s Kappa for the third algorithm was 0.99 (95%CI 0.98-1.00). Conclusions We conclude that electronic medical record data are sufficient to categorize coronary heart disease and heart failure events without manual record review. However, only moderate agreement with med- ical record review can be achieved when the classification is based on 4-digit ICD9CM codes because ICD9CM 410.9 includes myocardial infarction with ST elevation (STEMI) and myocardial infarction without ST elevation (nSTEMI). Nearly perfect agreement can be achieved using IMO statements, a more detailed coding system that tracks to ICD9, ICD10 and SnoMED-CT. IMO statements are avail- able in many electronic medical record systems. Keywords validity; surveillance; coronary artery disease; heart failure; electronic medical record Acknowledgments Funding provided by the following: The HealthPartners Research Foun- dation (a partnership grant to TEK); The Heart Disease and Stroke Pre- vention Unit at the Minnesota Department of Health from a Capacity Building - Cooperative Agreement grant from the Centers for Disease Control and Prevention CDC) 5U50DP000721-04; and, NIH training grant T32 HL69764 (supporting CJB). *Jawali Jaranilla E-mail: jjaranil@jhsph.edu Online Journal of Public Health Informatics * ISSN 1947-2579 * http://ojphi.org * 5(1):e159, 2013