This paper is in the following e-collection/theme issue:

Clinical Information and Decision Making (1754) Research Instruments, Questionnaires, and Tools (693) Insomnia and Sleep Hygiene (222) Machine Learning (1872) New Methods (1073) Sleep Apnea (33) Sleep Monitoring, Sleep Quality, Sleep Disorders (241) mHealth for Diagnosis (76)

Published on in Vol 26 (2024)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/51615, first published .
Efficient Screening in Obstructive Sleep Apnea Using Sequential Machine Learning Models, Questionnaires, and Pulse Oximetry Signals: Mixed Methods Study

Efficient Screening in Obstructive Sleep Apnea Using Sequential Machine Learning Models, Questionnaires, and Pulse Oximetry Signals: Mixed Methods Study

Efficient Screening in Obstructive Sleep Apnea Using Sequential Machine Learning Models, Questionnaires, and Pulse Oximetry Signals: Mixed Methods Study

Authors of this article:

Nai-Yu Kuo1, 2, 3 Author Orcid Image ;   Hsin-Jung Tsai2 Author Orcid Image ;   Shih-Jen Tsai2, 3 Author Orcid Image ;   Albert C Yang1, 2, 4, 5 Author Orcid Image
Article Authors Cited by Tweetations (1) Metrics
All Time | Last Month | Last Six Months | Last Year
National Sleep Research Resource (SleepData.org) National Sleep Research Resource (SleepData.org) @SleepDataNSRR

Undiagnosed #SleepApnea harms long-term health. This study shows a 2-step ML model using a questionnaire + pulse oximeter can detect moderate/severe cases with 89% precision—supporting earlier, at-home intervention and reduced healthcare burden https://t.co/gCB6Cps1dk

4:52 PM · Jun 03, 2025

0
0