Prediction of Obstructive Sleep Apnea Using Variational Autoencoder-Derived Features From 12-Lead ECG
- 1Division of Medical Informatics, Department of Internal Medicine, University of Kansas Medical Center, Kansas City, KS; Division of Pulmonary, Critical Care and
Abstract
BackgroundObstructive sleep apnea (OSA) is a highly prevalent sleep disorder. Major risk factors include obesity, older age, and male sex. Given the well-established association between OSA and cardiovascular disease, markers of cardiovascular health derived from electrocardiography (ECG) may help identify individuals with undiagnosed OSA. This study evaluated whether 12-lead ECG features improve machine learning-based prediction of OSA beyond established clinical factors.
MethodsWe conducted a retrospective cohort study of individuals who underwent diagnostic sleep studies at the University of Kansas Health System Sleep Disorders Center (2004-2025) and had a 12-lead ECG acquired within one year. Standard ECG features (intervals, amplitudes, voltage-time integrals, morphology descriptors) were extracted from the representative beat. Latent representations were derived using two variational autoencoder (VAE) models pretrained on >1 million ECGs: a 30-dimensional representative-beat VAE and a 90-dimensional full 10-second ECG VAE. Three LightGBM models were trained: clinical factors only (age, sex, weight, height, body mass index [BMI], Epworth sleepiness scale [ESS]), ECG features only, and a combined model. Feature selection and hyperparameter tuning were performed separately for each model within a 5-fold cross-validation scheme. The outcome was moderate-to-severe OSA (AHI[≥]15 events/h), evaluated by AUROC (bootstrapped 95% CI) in a 10% holdout test set.
ResultsThe dataset included 7,699 individuals (52.2% women, mean age 58.0 {+/-} 14.2 years, BMI 33.6{+/-}8.2 kg/m{superscript 2}, ESS 8.8{+/-}5.1; 36.4% with moderate-to-severe OSA) Training AUROC (95% CI) was 0.71 (0.66-0.76) for the combined model, versus 0.65 (0.59-0.70) for the clinical-only model and 0.66 (0.61-0.72) for the ECG-only model. Holdout test AUROC was 0.78 (combined), 0.69 (clinical-only), and 0.71 (ECG-only). Feature importance identified age, BMI, weight, ECG VAE latent variables, height, sex, and P-wave voltage-time integral as relevant contributor to the predictions.
ConclusionsLatent ECG features extracted by VAE improve prediction of moderate-to-severe OSA when combined with clinical factors.
Related
- Prediction of lncRNA–cervical cancer associations using a multi-view collaborative variational autoencoder with knowledge distillation transfer learning
- Lesion-Specific Prediction of Segmental Fractional Flow Reserve Using Deep Learning and Optical Coherence Tomography-Derived Features
- Fungal Sensitization and the Manifestation of Asthmatic Features in Chronic Obstructive Pulmonary Disease
- Development and validation of an interpretable machine learning model for early prediction of mortality in ICU patients with chronic obstructive pulmonary disease and heart failure
- Comparing Demographic and Clinical Features of Obstructive Sleep Apnea Patients With and Without Sleepiness: A Cross‐Sectional Study
BibTeX
@misc{harvey2026prediction,
title = {{Prediction of Obstructive Sleep Apnea Using Variational Autoencoder-Derived Features From 12-Lead ECG}},
author = {C. Harvey and A. Gupta and B. Halder and J. Thompson and S. Mishra and M. K. Gratton and D. Stevens and A. Noheria and D. R. Mazzotti},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.22.26363710},
url = {https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Prediction of Obstructive Sleep Apnea Using Variational Autoencoder-Derived Features From 12-Lead ECG
AU - C. Harvey
AU - A. Gupta
AU - B. Halder
AU - J. Thompson
AU - S. Mishra
AU - M. K. Gratton
AU - D. Stevens
AU - A. Noheria
AU - D. R. Mazzotti
PY - 2026
DA - 2026/09/22
PB - medRxiv
DO - 10.64898/2026.09.22.26363710
UR - https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1
AB - BackgroundObstructive sleep apnea (OSA) is a highly prevalent sleep disorder. Major risk factors include obesity, older age, and male sex. Given the well-established association between OSA and cardiovascular disease, markers of cardiovascular health derived from electrocardiography (ECG) may help identify individuals with undiagnosed OSA. This study evaluated whether 12-lead ECG features improve machine learning-based prediction of OSA beyond established clinical factors. MethodsWe conducted a retrospective cohort study of individuals who underwent diagnostic sleep studies at the University of Kansas Health System Sleep Disorders Center (2004-2025) and had a 12-lead ECG acquired within one year. Standard ECG features (intervals, amplitudes, voltage-time integrals, morphology descriptors) were extracted from the representative beat. Latent representations were derived using two variational autoencoder (VAE) models pretrained on >1 million ECGs: a 30-dimensional representative-beat VAE and a 90-dimensional full 10-second ECG VAE. Three LightGBM models were trained: clinical factors only (age, sex, weight, height, body mass index [BMI], Epworth sleepiness scale [ESS]), ECG features only, and a combined model. Feature selection and hyperparameter tuning were performed separately for each model within a 5-fold cross-validation scheme. The outcome was moderate-to-severe OSA (AHI[≥]15 events/h), evaluated by AUROC (bootstrapped 95% CI) in a 10% holdout test set. ResultsThe dataset included 7,699 individuals (52.2% women, mean age 58.0 {+/-} 14.2 years, BMI 33.6{+/-}8.2 kg/m{superscript 2}, ESS 8.8{+/-}5.1; 36.4% with moderate-to-severe OSA) Training AUROC (95% CI) was 0.71 (0.66-0.76) for the combined model, versus 0.65 (0.59-0.70) for the clinical-only model and 0.66 (0.61-0.72) for the ECG-only model. Holdout test AUROC was 0.78 (combined), 0.69 (clinical-only), and 0.71 (ECG-only). Feature importance identified age, BMI, weight, ECG VAE latent variables, height, sex, and P-wave voltage-time integral as relevant contributor to the predictions. ConclusionsLatent ECG features extracted by VAE improve prediction of moderate-to-severe OSA when combined with clinical factors.
ER -