Development and validation of an automated algorithm to detect atrial fibrillation within stored intensive care unit continuous electrocardiographic data (Preprint)
BACKGROUND Atrial fibrillation (AF) is the most common arrhythmia during critical illness, representing a sepsis-defining cardiac dysfunction associated with adverse outcomes. OBJECTIVE To develop and validate an automated algorithm to accurately identify AF within electronic healthcare data among critically ill patients with sepsis. METHODS Retrospective cohort study of patients hospitalized with sepsis identified from Medical Information Mart for Intensive Care (MIMIC III) electronic health data with linked electrocardiographic (ECG) telemetry waveforms. Within three separate cohorts of 50 patients, we iteratively developed and validated an automated algorithm that identifies ECG signals, removes noise, and identifies irregularly irregular rhythm and premature beats in order to identify AF. We compared the automated algorithm to current methods of AF identification in large databases, including ICD-9 codes and hourly nurse annotation of heart rhythm. Methods of AF identification were tested against gold standard manual ECG review. RESULTS AF detection algorithms that did not differentiate AF from premature atrial and ventricular beats performed modestly, with 76% (95% CI, 61-87%) accuracy. Performance improved (p=0.02) with the addition of premature beat detection (validation set accuracy: 94% [95% CI, 83-99%]). Median time between automated and manual detection of AF onset was 30 minutes (25th-75%ile 0-208 minutes). The accuracy of ICD-9 codes (68%, p=0.0002 vs. automated algorithm) and nurse charting (80%, p=0.02 vs. algorithm) was lower than the automated algorithm. CONCLUSIONS An automated algorithm using telemetry ECG data can feasibly and accurately detect AF among critically ill patients with sepsis, and represents an improvement in AF detection within large databases. CLINICALTRIAL na