[2603.21832] Deriving Health Metrics from the Photoplethysmogram: Benchmarks and Insights from MIMIC-III-Ext-PPG

Computer Science > Machine Learning arXiv:2603.21832 (cs) [Submitted on 23 Mar 2026] Title:Deriving Health Metrics from the Photoplethysmogram: Benchmarks and Insights from MIMIC-III-Ext-PPG Authors:Mohammad Moulaeifard, Philip J. Aston, Peter H. Charlton, Nils Strodthoff View a PDF of the paper titled Deriving Health Metrics from the Photoplethysmogram: Benchmarks and Insights from MIMIC-III-Ext-PPG, by Mohammad Moulaeifard and 3 other authors View PDF HTML (experimental) Abstract:Photoplethysmography (PPG) is one of the most widely captured biosignals for clinical prediction tasks, yet PPG-based algorithms are typically trained on small-scale datasets of uncertain quality, which hinders meaningful algorithm comparisons. We present a comprehensive benchmark for PPG-based clinical prediction using the \dbname~dataset, establishing baselines across the full spectrum of clinically relevant applications: multi-class heart rhythm classification, and regression of physiological parameters including respiratory rate (RR), heart rate (HR), and blood pressure (BP). Most notably, we provide the first comprehensive assessment of PPG for general arrhythmia detection beyond atrial fibrillation (AF) and atrial flutter (AFLT), with performance stratified by BP, HR, and demographic subgroups. Using established deep learning architectures, we achieved strong performance for AF detection (AUROC = 0.96) and accurate physiological parameter estimation (RR MAE: 2.97 bpm; HR MAE: 1.13 bpm; SBP...