Validation of an Automated Electronic Algorithm and “Dashboard” to Identify and Characterize Decompensated Heart Failure Admissions across a Medical Center

• Published in: The American heart journal 2017-01, Vol.183, p.40-48
• Main Authors: Cox, Zachary L, PharmD, Lewis, Connie M, NP-C, CHFN, Lai, Pikki, Ph.D, Lenihan, Daniel J, MD
• Format: Article
• Language: English
• Subjects: Age; Aged; Algorithms; Atherosclerosis; Automation; Cardiovascular; Codes; Diuretics - therapeutic use; Electronic Health Records; Female; Heart failure; Heart Failure - diagnosis; Hospitalization; Hospitals; Humans; Identification; Infusions, Intravenous; Laboratories; Male; Middle Aged; Natriuretic Peptide, Brain - blood; Patient admissions; Physicians; Quality; Sensitivity and Specificity; Tertiary Care Centers
• ISSN: 0002-8703; 1097-6744
• DOI: 10.1016/j.ahj.2016.10.001

Background We aim to validate the diagnostic performance of the first fully automatic, electronic Heart Failure (HF) identification algorithm and evaluate the implementation of a HF Dashboard system with 2 components: real-time identification of decompensated HF admissions and accurate characterization of disease characteristics and medical therapy. Methods We constructed a HF identification algorithm requiring 3 of 4 identifiers: B-type natriuretic peptide (BNP) > 400 pg/ml, admitting HF diagnosis, history of HF International Classification of Disease (ICD-9) diagnosis codes, and intravenous diuretic administration. We validated the diagnostic accuracy of the components individually (n = 366) and combined in the HF algorithm (n = 150) compared to a blinded provider panel in two separate cohorts. We built a HF Dashboard within the electronic medical record characterizing the disease and medical therapies of HF admissions identified by the HF algorithm. We evaluated the HF Dashboard 's performance over 26 months of clinical use. Results Individually, the algorithm components displayed variable sensitivity and specificity respectively: BNP> 400 pg/ml (89% and 87%), diuretic (80% and 92%), and ICD-9 code (56% and 95%). The HF algorithm achieved a high specificity (95%), positive predictive value (82%), and negative predictive value (85%) but achieved limited sensitivity (56%) secondary to missing provider-generated identification data. The HF Dashboard identified and characterized 3147 HF admissions over 26 months. Conclusion Automated identification and characterization systems can be developed and utilized with a substantial degree of specificity for the diagnosis of decompensated HF, although sensitivity is limited by clinical data input.