arXiv AI
Combining scEEG and PPG for reliable sleep staging
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 4
Rethinking PPG-based Sleep Staging: Datasets, Metrics, and Benchmarks
arXiv:2608. 00943v1 Announce Type: cross Abstract: Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at least 30 seconds, reflecting the minimum temporal resolution of the clinical scoring standard.
arXiv Machine Learning
Sep 22
Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction
The study compares six state‑of‑the‑art sleep‑staging foundation models on the MESA polysomnography dataset under three signal conditions: EEG only, ECG only, and EEG+ECG. Results show that EEG alone yields the highest accuracy (BIOT macro‑F1 = 0.7237), while switching to ECG alone incurs a consistent accuracy loss of about 0.35 macro‑F1 and reduces data rate to one‑third. Adding ECG to EEG offers little benefit for most models, indicating that EEG carries most of the sleep‑staging signal and that wearable‑compatible ECG alone is a viable but less accurate alternative.
arXiv Machine Learning
Oct 19
ECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep Health
ECG‑SDI is a single‑lead electrocardiography framework that provides continuous sleep‑depth profiling and digital biomarker extraction. Trained on 12,392 overnight polysomnographic recordings, the two‑stage deep learning model achieved strong correlations with conventional sleep stages (0.828–0.848) and high REM classification AUROCs (0.954–0.977). The approach identified a disturbed sleep subtype linked to poorer subjective quality and higher mortality, and demonstrated measurable improvements in sleep‑depth metrics after CPAP therapy, suggesting its utility for home‑based sleep monitoring.
arXiv AI
Sep 10
Learning transferable human physiology from two million hours of sleep with SleepFM-2
SleepFM-2 is a foundation model trained on 282,511 polysomnography recordings, covering over two million hours of multimodal sleep physiology. It outperforms its predecessor in disease prediction, sleep scoring, and event detection, and its representation improves performance across diverse tasks—including wearable sensing, subjective sleep reports, and transfer to other EEG modalities. When combined with age, sex, and BMI, the model meets stringent discrimination criteria for 215 EHR phenotypes, adding reproducible information beyond demographics for 155 of them.
arXiv Machine Learning
Oct 12
PPG-Bench: A Unified Benchmark for PPG Foundation Models
PPG-Bench is an open‑source benchmark that evaluates five publicly available photoplethysmography (PPG) foundation models across nine datasets and 26 tasks, covering cardiovascular state estimation, activity, sleep, screening, and identification. The benchmark tests models under four downstream regimes—linear probing, random forests, frozen MLP probes, and end‑to‑end finetuning—while also comparing them to three controls: a random/constant baseline, a deterministic pulse‑rate‑variability feature set, and a generic time‑series foundation model (MOMENT). Results show that over a third of task‑regime combinations yield no advantage for any PPG foundation model over the baseline, and in most cases no PPG‑specific model outperforms the simple controls, indicating that current PPG foundation models lack generalised, transferable representations.
arXiv Machine Learning
Jun 18
Beyond AHI: An Interpretable Causal-Discovery-Guided Framework for Sleep Recovery in Connected Health
arXiv:2606. 18506v1 Announce Type: new Abstract: Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such as sleepiness and fatigue.