Identification of Heart Rate Variability Features Predictive of Post-operative Atrial Fibrillation in Patients Undergoing Coronary Artery Bypass Graft Surgery

Status: In Publication / Submitted

Authors: Zain Khalpey, Ujjawal Kumar, Nicholas King, Amina H. Khalpey

Abstract

Post-operative atrial fibrillation (POAF) remains one of the most common complications following coronary artery bypass graft (CABG) surgery, affecting 20–40% of patients and significantly increasing morbidity, length of stay, and healthcare costs. This study investigates heart rate variability (HRV) features extracted from continuous perioperative monitoring as early predictive biomarkers for POAF.

Using a machine learning pipeline applied to high-resolution ECG waveform data, we identify specific time-domain, frequency-domain, and nonlinear HRV features that demonstrate strong predictive value for POAF onset. The analysis encompasses preoperative baseline measurements through the first 48 hours post-surgery, enabling identification of the optimal prediction window.

Our findings suggest that HRV-based risk stratification can identify POAF-susceptible patients significantly earlier than current clinical indicators, potentially enabling targeted prophylactic interventions and personalized monitoring protocols.