Quantifying cardiovascular autonomic aging with machine learning

Abstract

Machine learning has become an important tool in precision medicine and aging research. We introduce the cardiovascular autonomic age (CAA) gap, a novel metric quantifying the deviation between machine learning-estimated biological age and chronological age based on autonomic cardiovascular function. High-resolution electrocardiograms and continuous blood pressure recordings at rest were collected from 1,060 healthy individuals. From these signals, 29 autonomic indices were derived, including time-, frequency-, and symbol-domain heart rate variability, cardiovascular coupling, pulse wave dynamics, and QT interval features. A Gaussian process regression model was trained on 879 participants to estimate biological age, yielding the CAA. The deviation between CAA and chronological age defined the CAA gap, which was evaluated in two test sets stratified by cardiovascular risk (CVR) using the Framingham risk score. At a 0.5 NEW NOTEWORTHY The cardiovascular autonomic age (CAA) gap is a new machine learning-based marker that reveals when the body ages faster than the clock. Using resting-state cardiovascular recordings from 1,000+ participants, we show that individuals with higher cardiovascular risk exhibit accelerated autonomic aging. The CAA gap could become a sensitive, interpretable tool for early detection and long-term monitoring.