A recent peer-reviewed article in Preventing Chronic Disease, published by the Centers for Disease Control, demonstrates how IMO’s enhanced interface terminology service was superior to current population classification techniques using standard reimbursement coding in medical records systems and as a disease surveillance tool.
A recent peer-reviewed article1 in Preventing Chronic Disease, published by the Centers for Disease Control, demonstrates how IMO’s enhanced interface terminology service was superior to current population classification techniques using standard reimbursement coding in medical records systems and as a disease surveillance tool.
The study was designed to identify and accurately categorize acute coronary heart disease and heart failure events using exclusively electronic health record (EHR) data. Using EHR data along to accurately categorize disease would allow the medical record to be used as a cardiovascular surveillance tool, and eliminate the need for manual medical record review. The study compared two computer algorithms using standard 4-digit ICD-9-CM and IMO’s Interface terminology to a manual record review (the gold standard). The authors found only moderate agreement (57% and 67%) was achieved when the classification is based solely on 4-digit ICD-9-CM codes. However, the authors reported greater than 99% agreement was achieved using IMO interface terminology. The resulting Cohen’s κ for the initial algorithm was 0.47 (95% confidence interval [CI], 0.41–0.54). Cohen’s κ was 0.61 (95% CI, 0.55–0.68) for the second algorithm. Cohen’s κ for the third algorithm using IMO was 0.99 (95% CI, 0.98–1.00).
The authors concluded that electronic medical record data are sufficient to categorize coronary heart disease and heart failure events without manual record review. However, when the classification is based on 4-digit ICD-9-CM codes only moderate agreement with medical record review can be achieved. When using IMO interface terminology - clinician-friendly terms mapped to reference terminologies such as SNOMED CT® as well as ICD-9-CM and ICD-10-CM - nearly perfect agreement can be achieved.
Click here for the entire press release: CDC Article
1. Kottke TE, Baechler CJ. An Algorithm That Identifies Coronary and Heart Failure Events in the Electronic Health Record. Prev Chronic Dis 2013;10:120097.
Copyright © 2013 Intelligent Medical Objects, Inc. IMO and INTELLIGENT MEDICAL OBJECTS are registered trademarks of Intelligent Medical Objects, Inc. All rights reserved.
SNOMED CT is a registered trademark of the International Health Terminology Standards Development Organisation