{
  "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.\n\nMethodsWe 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.\n\nResultsThe 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.\n\nConclusionsLatent ECG features extracted by VAE improve prediction of moderate-to-severe OSA when combined with clinical factors.",
  "abstract_shown": true,
  "affiliations": [
    "Division of Medical Informatics, Department of Internal Medicine, University of Kansas Medical Center, Kansas City, KS; Division of Pulmonary, Critical Care and"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "C. Harvey"
    },
    {
      "name": "A. Gupta"
    },
    {
      "name": "B. Halder"
    },
    {
      "name": "J. Thompson"
    },
    {
      "name": "S. Mishra"
    },
    {
      "name": "M. K. Gratton"
    },
    {
      "name": "D. Stevens"
    },
    {
      "name": "A. Noheria"
    },
    {
      "affs": [
        0
      ],
      "name": "D. R. Mazzotti"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d5n47fr106w6t.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.22.26363710",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1.full",
  "id": "d5n47fr106w6t",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "cardiovascular medicine"
    ],
    [
      "openalex",
      "2737|Obstructive Sleep Apnea Research"
    ]
  ],
  "openalex": "W7214082334",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/d5n47fr106w6t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:17Z",
      "native_id": "10.64898/2026.09.22.26363710",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.22.26363710v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:cardiovascular medicine",
      "subfield": "cardiovascular"
    }
  ],
  "title": "Prediction of Obstructive Sleep Apnea Using Variational Autoencoder-Derived Features From 12-Lead ECG",
  "title_text": "Prediction of Obstructive Sleep Apnea Using Variational Autoencoder-Derived Features From 12-Lead ECG",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:17Z",
  "url": "https://research.draconitic.com/paper/d5n47fr106w6t",
  "venue": "medRxiv",
  "versions": []
}