Incorporating respiratory signals for machine learning-based multimodal sleep stage classification: a large-scale benchmark study with actigraphy and heart rate variability

Krauß D, Richer R, Küderle A, Jukic J, German A, Leutheuser H, Regensburger M, Winkler J, Eskofier B (2025)

Publication Type: Journal article

Publication year: 2025

Journal

Sleep American Academy of Sleep Medicine

Abstract

Insufficient sleep quality is directly linked to various diseases, making reliable sleep monitoring crucial for prevention, diagnosis, and treatment. As sleep laboratories are cost- and resource-prohibitive, wearable sensors offer a promising alternative for long-term unobtrusive sleep monitoring at home. Current unobtrusive sleep detection systems are mostly based on actigraphy (ACT) that tend to overestimate sleep due to a lack of movement in short periods of wakefulness. Previous research established sleep stage classification by combining ACT with cardiac information but has not investigated the incorporation of respiration in large-scale studies. For that reason, this work aims to systematically compare ACT-based sleep-stage classification with multimodal approaches combining ACT, heart rate variability (HRV) as well as respiration rate variability (RRV) using state-of-the-art machine- and deep learning algorithms. The evaluation is performed on a publicly available sleep dataset including more than 1000 recordings. Respiratory information is introduced through ECG-derived respiration features, which are evaluated against traditional respiration belt data. Results show that including RRV features improves the Matthews Correlation Coefficient (MCC), with long short-term memory (LSTM) algorithms performing best. For sleep staging based on AASM standards, the LSTM achieved a median MCC of 0.51 (0.16 IQR). Respiratory information enhanced classification performance, particularly in detecting wake and rapid eye movement (REM) sleep epochs. Our findings underscore the potential of including respiratory information in sleep analysis to improve sleep detection algorithms and, thus, help to transfer sleep laboratories into a home monitoring environment. The code used in this work can be found online at https://github.com/mad-lab-fau/sleep_analysis.

Authors with CRIS profile

Daniel Krauß Machine Learning and Data Analytics Lab Robert Richer Machine Learning and Data Analytics Lab Arne Küderle Machine Learning and Data Analytics Lab Jelena Jukic Department of Molecular Neurology Alexander German Department of Molecular Neurology Heike Leutheuser Machine Learning and Data Analytics Lab Martin Regensburger Department of Molecular Neurology Jürgen Winkler Professur für Molekulare Neurologie Björn Eskofier Lehrstuhl für Informatik 14 (Machine Learning and Data Analytics)

Additional Organisation(s)

Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS)

Related research project(s)

Sensorbasierte Bewegungs- und Schlafanalyse beim Parkinson-Syndrom (SFB 1483 EmpkinS D04) Empatho-Kinaesthetic Sensor Technology (SFB 1483 EmpkinS) July 1, 2021 - June 30, 2025

How to cite

APA:

Krauß, D., Richer, R., Küderle, A., Jukic, J., German, A., Leutheuser, H.,... Eskofier, B. (2025). Incorporating respiratory signals for machine learning-based multimodal sleep stage classification: a large-scale benchmark study with actigraphy and heart rate variability. Sleep. https://doi.org/10.1093/sleep/zsaf091

MLA:

Krauß, Daniel, et al. "Incorporating respiratory signals for machine learning-based multimodal sleep stage classification: a large-scale benchmark study with actigraphy and heart rate variability." Sleep (2025).

BibTeX: Download