PulseAI detected arterial waveform fiducial points with errors ≤12.6 ms and AIx correlated strongly (r=0.990) with arterial stiffness in single-site cuff measures.
Does PulseAI accurately detect fiducial points on brachial cuff waveforms for single-site assessment of arterial stiffness compared to human annotation?
PulseAI enables accurate, automated, single-site monitoring of arterial stiffness from brachial cuff waveforms, matching human-annotated labels.
Absolute Event Rate: 0% vs 0%
• Arterial stiffness is clinically valuable, but complex to assess routinely. • PulseAI reliably detects fiducial points across diverse waveform morphologies. • Spectral machine learning achieves comparable performance with lower complexity. • AIx derived from PulseAI correlates with arterial stiffness assessed via PTT. • PulseAI enables automated, single-site arterial stiffness monitoring. Arterial stiffness is a fundamental characteristic of circulatory physiology and a well-established predictor of cardiovascular risk and mortality. However, routine clinical assessment remains limited by the need for dual-site measurements. To address this challenge, we developed a machine learning algorithm – PulseAI – for automated fiducial point detection on brachial cuff waveforms for single-site assessment of arterial stiffness. PulseAI was trained and evaluated using a clinical dataset comprising 5,215 waveforms from 145 heterogeneous subjects. Performance was assessed on fiducial point predictions accuracy (inflection point, t i , and dicrotic notch, t n ) and downstream pulse waveform analysis (PWA) metrics. Our multi-channel convolutional neural network (PulseAI) reported a median IQR on mean absolute error for fiducial point detection of 5 3, 10 ms. PulseAI demonstrated high accuracy in predicting t i (r = 0.913, p < 0.0001) and t n (r = 0.939, p < 0.0001), with an average prediction error of 12.6 ms and 6.2 ms for t i and t n , respectively. While the t n results are comparable to other academic models reporting ∼10 ms errors, our approach provides both fiducial point indices from a single model. PWA features derived from PulseAI closely matched those derived from human-annotated labels, including systolic pressure–time integral (r = 0.988, p < 0.0001), augmentation index (AIx) (r = 0.990, p < 0.0001), and end systolic pressure (r = 0.998, p < 0.0001). AIx tertiles showed statistically significant association with height-adjusted pulse transit time (p < 0.05), used as a surrogate of arterial stiffness, demonstrating the model’s sensitivity to stiffness-related changes. These findings demonstrate that PulseAI enables accurate fiducial point detection and represents a clinically viable tool for automated, single-site monitoring of arterial stiffness.
Tamborini et al. (Sat,) reported a other. PulseAI detected arterial waveform fiducial points with errors ≤12.6 ms and AIx correlated strongly (r=0.990) with arterial stiffness in single-site cuff measures.