{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:06:46Z","timestamp":1782846406994,"version":"3.54.5"},"reference-count":76,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"\n Background<\/jats:title>\n Obstructive sleep apnea (OSA) affects nearly one billion people globally and poses a substantial public health threat. Effective and accessible methods for OSA risk identification are urgently needed.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and externally validate a machine learning model derived from multi-parameter pulse oximetry (SpO2) for OSA screening, and to evaluate its performance, interpretability, and robustness across sex and age subgroups.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Of 4156 screened participants, 2195 underwent polysomnography (internal cohort) and 446 received home sleep apnea testing (external cohort). Eight SpO2-derived parameters, including oxygen desaturation index (ODI), hypoxic burden (HB), and ST90 (percentage of sleep time with SpO2 < 90%), were used to construct models. Six machine learning algorithms were trained, with F1-score as the primary metric and area under the curve as the secondary metric. Model interpretability was assessed using Shapley additive explanations and intrinsic feature importance scores.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Nonlinear parameter-risk relationships were observed between oximetry indices and OSA probability. The 4-parameter ODI-HB-MinSpO2-ST90 model achieved optimal performance (F1-score = 0.9516, area under the curve = 0.9879), surpassing all single-parameter models. Shapley additive explanations analysis identified ODI, HB, and MinSpO2 as key predictors. The ODI-HB-MinSpO2-MeanSpO2 configuration demonstrated superior performance in female and younger subgroups, whereas the ODI-HB-MinSpO2-ST90 model remained optimal for male and older participants. Categorical boosting outperformed other algorithms across multiple metrics and remained robust in both subgroup and external validation analyses.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The multi-parameter oximetry model based on the categorical boosting algorithm provides a simple and accurate tool for OSA screening. Sex- and age-stratified strategies can further enhance its clinical applicability.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/80384","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T17:10:06Z","timestamp":1772817006000},"page":"e80384","source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning\u2013Based Multidimensional Oximetry for Obstructive Sleep Apnea Screening: Development and External Validation"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3063-4031","authenticated-orcid":false,"given":"Xuanyu","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4493-6990","authenticated-orcid":false,"given":"Haitong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7448-0885","authenticated-orcid":false,"given":"Rong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2823-5724","authenticated-orcid":false,"given":"Tianming","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6512-8980","authenticated-orcid":false,"given":"Haoan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9160-6886","authenticated-orcid":false,"given":"Pengliang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8136-3361","authenticated-orcid":false,"given":"Ning","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-2600(19)30198-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-023-01496-3"},{"key":"ref3","author":"Troester, MM","year":"2023","journal-title":"The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2196\/51615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2021.10.023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-024-02449-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.smrv.2025.102139"},{"issue":"5","key":"ref8","first-page":"3597","volume":"15","author":"Kong, D","year":"2023","journal-title":"Am J Transl Res"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsac189"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/resp.14754"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/bios14010052"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.202005-510OC"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11325-021-02439-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3512616"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2024.01.015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11325-020-02014-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40604-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3495975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2196\/76795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2024.1353469"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11040612"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108777"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107827"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11325-023-02846-9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-33170-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ad79b4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2018.09.030"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/jsr.70211"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3031004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/resp.13635"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2020.07.015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106523"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000005247"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4236\/jdaip.2019.74012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.10.118"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-019-1402-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-67024-3"},{"key":"ref40","unstructured":"KeGMengQFinleyTWangTChenWMaWYeQLiuTYLightGBM: a highly efficient gradient boosting decision tree2017NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing SystemsDecember 4-9Long Beach California USA31493157"},{"key":"ref41","unstructured":"ProkhorenkovaLGusevGVorobevADorogushAGulinACatBoost: unbiased boosting with categorical features2018NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing SystemsDecember 3-8Montr\u00e9al, Canada66396649"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-09954-8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.spinee.2021.02.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.arbres.2022.08.005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1111\/jsr.13638"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2023.09.007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1183\/09059180.00004213"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/oby.23231"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2019.00849"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2020.03.027"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5935\/1984-0063.20200119"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.31083\/j.rcm2505172"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1186\/s12944-023-01919-8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2025.09.136"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-03129-x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsac179"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.arbres.2022.08.005"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.arbres.2024.07.003"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1111\/crj.13256"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109604"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1111\/resp.14122"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11325-024-03191-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.1005650"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1177\/20552076231152751"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00369-8"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1093\/ehjacc\/zuaf001"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.202203-271OC"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.arbres.2021.02.022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.cn112147-20240206-00072"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2147\/NSS.S287165"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0227778"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamda.2024.105023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2025.1629600"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.2196\/58187"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2196\/39452"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/zsaf078"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:13:51Z","timestamp":1782843231000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":76,"URL":"https:\/\/doi.org\/10.2196\/80384","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.80384","asserted-by":"object"}]},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]}}}