EUVIMEDEUVIMED entdecken
Crossref

Machine Learning Improves Questionnaire‐Based Sleep Apnea Screening: A Multi‐Cohort Multi‐Visit Validation Study

Nhung H Hoang iD, Zilu Liang iD

Journal of Sleep Research · 05.11.2026

DOI: 10.1111/jsr.70495 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Sleep Research, online erschienen am 05.11.2026. Verfasst von Nhung H Hoang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Ubiquitous and Personal Computing Lab, Kyoto University of Advanced Science, Kyoto, Japan. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Obstructive sleep apnea (OSA) affects a large portion of the global population but remains substantially underdiagnosed due to limited access to polysomnography. While machine learning has shown promise for scalable OSA screening, many recent models rely on overnight physiological monitoring and are not validated across heterogeneous cohorts. This study develops and evaluates questionnaire‐based CatBoost models for OSA detection using two large, multi‐cohort datasets (SHHS and WSC). The models use 42 easily obtainable features that require no specialized equipment, which could potentially enable highly accessible screening. We assessed performance through comprehensive internal and external validation, including within‐cohort external testing (SHHS1 SHHS2) and cross‐cohort generalization (SHHS1 WSC1), across three clinically relevant AHI cutoffs ( 5, 15, 30 events/h). In internal validation, models achieved consistently balanced performance with AUC 0.74–0.76, sensitivity 67%–73%, and specificity 62%–70% across all cutoffs. Performance remained stable during within‐cohort external testing at cutoff 15 (AUC 0.75, sensitivity 71%, specificity 65%). However, cross‐cohort validation revealed noticeable performance degradation due to population distribution shifts, most pronounced at 5 where specificity dropped substantially (48.5% 4.7%) when models trained on the older SHHS cohort were applied to the younger WSC population. SHAP analysis confirmed that predictions relied primarily on established clinical risk factors including neck circumference, age, BMI, and symptom history. These results demonstrate that questionnaire‐based machine learning can achieve more balanced sensitivity‐specificity trade‐offs than traditional scoring rules, and highlight the importance of multi‐cohort external testing.

Schlagwörter

Stichwörter der Autor:innen

external validationgeneralizabilitymachine learningscreeningsleep apnea

Autor:innen und Institutionen

  • Ubiquitous and Personal Computing Lab, Kyoto University of Advanced Science, Kyoto, Japan.
  • Institute of Industrial Science, The University of Tokyo, Tokyo, Japan.

ORCID-Profile: Nhung H Hoang, Zilu Liang

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Hoang, N. H., & Liang, Z. (2026). Machine Learning Improves Questionnaire‐Based Sleep Apnea Screening: A Multi‐Cohort Multi‐Visit Validation Study. Journal of Sleep Research. https://doi.org/10.1111/jsr.70495

Vancouver

Hoang NH, Liang Z. Machine Learning Improves Questionnaire‐Based Sleep Apnea Screening: A Multi‐Cohort Multi‐Visit Validation Study. Journal of Sleep Research. 2026. doi:10.1111/jsr.70495

BibTeX
@article{Hoang2026,
  author = {Hoang, Nhung H and Liang, Zilu},
  title = {Machine Learning Improves Questionnaire‐Based Sleep Apnea Screening: A Multi‐Cohort Multi‐Visit Validation Study},
  journal = {Journal of Sleep Research},
  year = {2026},
  doi = {10.1111/jsr.70495}
}
Kostenlos starten →