Entropy-Based Measures of Hypnopompic Heart Rate Variability Contribute to the Automatic Prediction of Cardiovascular Events.
Entropy (Basel, Switzerland) February 20, 2020 Xueya Yan, Lulu Zhang, Jinlian Li et al.
Surges in sympathetic activity near the end of nocturnal sleep may contribute to cardiovascular events. Analyzing heart rate variability (HRV) during the hypnopompic period (the transition from sleep to waking) helps predict cardiovascular disease (CVD). In 2,217 initially CVD-free subjects, those who later developed CVD showed significant alterations in hypnopompic HRV. Machine learning models using hypnopompic HRV metrics achieved 81.4% accuracy for short-term CVD prediction (within two years), a 10.7% improvement over long-term prediction. Removing HRV metrics reduced short-term predictive performance by over 6%. Entropy-based complexity measures of hypnopompic HRV contributed more to prediction than conventional HRV measures.