{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:31:52Z","timestamp":1787041912480,"version":"build-2736575974"},"reference-count":30,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Obstructive sleep apnea (OSA) is traditionally classified according to the apnea\u2013hypopnea index (AHI), although AHI alone does not fully capture the heterogeneity of disease severity. This study introduces a novel polysomnography-derived biomarker, the Sleep Disturbance Ratio (SDR), and evaluates its contribution to OSA severity classification using explainable machine learning approaches. Methods: A retrospective study was conducted using polysomnographic data from 767 adults who underwent overnight sleep studies. SDR was calculated as the logarithmic ratio between light sleep (N1 + N2) and restorative sleep (N3 + REM). Predictive models were trained and evaluated using four established machine learning algorithms: Decision Tree, Random Forest, Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN). Model performance was assessed using accuracy, Cohen\u2019s kappa, F1-score, multiclass AUC, ROC analysis, feature importance ranking, partial dependence plots, and clinical risk mapping. Results: Although SDR did not differ significantly across conventional OSA severity groups in univariate analysis (p = 0.77), explainable machine learning analyses consistently demonstrated that increasing SDR was associated with a higher probability of severe OSA, particularly in combination with lower mean oxygen saturation. SDR also showed strong physiological relevance by correlating positively with N2 sleep (r = 0.85) and negatively with N3 sleep (r = \u22120.83), supporting its role as a biomarker of sleep fragmentation. Among the predictive models, Random Forest achieved the highest classification accuracy (75.0%), whereas XGBoost demonstrated the best multiclass discrimination (AUC = 0.895) and the highest ROC performance for severe OSA (AUC = 0.962). ESS remained the most influential predictor across all models. Conclusions: This study introduces SDR as a novel polysomnography-derived biomarker that captures sleep architecture disruption beyond conventional AHI-based assessment. Although SDR is not an independent diagnostic marker, explainable machine learning analyses demonstrated that it provides complementary physiological information for OSA severity classification, particularly when integrated with oxygenation parameters.<\/jats:p>","DOI":"10.3390\/diagnostics16162606","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T12:01:26Z","timestamp":1786968086000},"page":"2606","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and Explainable Machine Learning Validation of a Novel Sleep Disturbance Ratio for Obstructive Sleep Apnea Severity Assessment"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4781-1751","authenticated-orcid":false,"given":"Mehmet","family":"Kabak","sequence":"first","affiliation":[{"name":"Department of Chest Disease, Mardin Artuklu University, Mardin 47200, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8184-9377","authenticated-orcid":false,"given":"Halit","family":"Irmak","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Faculty of Computer Engineering, Mardin Artuklu University, Mardin 47200, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah","family":"K\u0131l\u0131\u00e7","sequence":"additional","affiliation":[{"name":"Department of Chest Disease, Mardin Training and Research Hospital, Mardin 47100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1090-0697","authenticated-orcid":false,"given":"Bar\u0131\u015f","family":"\u00c7il","sequence":"additional","affiliation":[{"name":"Department of Chest Disease, Mardin Training and Research Hospital, Mardin 47100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1016\/S2213-2600(19)30198-5","article-title":"Estimation of the global prevalence and burden of obstructive sleep apnoea: A literature-based analysis","volume":"7","author":"Benjafield","year":"2019","journal-title":"Lancet Respir. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e13066","DOI":"10.1111\/jsr.13066","article-title":"On the rise and fall of the apnea-hypopnea index: A historical review and critical appraisal","volume":"29","author":"Pevernagie","year":"2020","journal-title":"J. Sleep Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1164\/rccm.202105-1274OC","article-title":"Sleep Apnea-Specific Hypoxic Burden, Symptom Subtypes, and Risk of Cardiovascular Events and All-Cause Mortality","volume":"205","author":"Trzepizur","year":"2022","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1093\/eurheartj\/ehy624","article-title":"The hypoxic burden of sleep apnoea predicts cardiovascular disease-related mortality: The Osteoporotic Fractures in Men Study and the Sleep Heart Health Study","volume":"40","author":"Azarbarzin","year":"2019","journal-title":"Eur. Heart J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"zsab134","DOI":"10.1093\/sleep\/zsab134","article-title":"Beyond the apnea-hypopnea index: Alternative diagnostic parameters and machine learning solutions for estimation of sleep apnea severity","volume":"44","author":"Myllymaa","year":"2021","journal-title":"Sleep"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1164\/rccm.201707-1435OC","article-title":"Phenotyping Pharyngeal Pathophysiology using Polysomnography in Patients with Obstructive Sleep Apnea","volume":"197","author":"Sands","year":"2018","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fossland, V., Toften, S., Hals, I.K., Haugdahl, H.S., Thu, O.K., and Sorger, H. (2025). The association between obstructive sleep apnea severity and sleep architecture measured with non-contact radar technology in primary investigation and follow-up on therapy: A pilot study. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0319606"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1053\/smrv.2001.0245","article-title":"Clinical effects of sleep fragmentation versus sleep deprivation","volume":"7","author":"Bonnet","year":"2003","journal-title":"Sleep Med. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.5664\/jcsm.10532","article-title":"Application of artificial intelligence in the diagnosis of sleep apnea","volume":"19","author":"Bazoukis","year":"2023","journal-title":"J. Clin. Sleep Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.sleep.2024.09.041","article-title":"Machine-learning-based classification of obstructive sleep apnea using 19-channel sleep EEG data","volume":"124","author":"Kim","year":"2024","journal-title":"Sleep Med."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kim, Y.J., Jeon, J.S., Cho, S.E., Kim, K.G., and Kang, S.G. (2021). Prediction Models for Obstructive Sleep Apnea in Korean Adults Using Machine Learning Techniques. Diagnostics, 11.","DOI":"10.3390\/diagnostics11040612"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"4967","DOI":"10.1007\/s00405-025-09377-x","article-title":"Artificial intelligence in the diagnosis of obstructive sleep apnea: A scoping review","volume":"282","author":"Kara","year":"2025","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"597","DOI":"10.5664\/jcsm.2172","article-title":"American Academy of Sleep Medicine. Rules for scoring respiratory events in sleep: Update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine","volume":"8","author":"Berry","year":"2012","journal-title":"J. Clin. Sleep Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"zsab030","DOI":"10.1093\/sleep\/zsab030","article-title":"Metrics of sleep apnea severity: Beyond the apnea-hypopnea index","volume":"44","author":"Malhotra","year":"2021","journal-title":"Sleep"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/j.arbres.2022.08.005","article-title":"Hypoxic burden in obstructive sleep apnea: Present and future","volume":"59","author":"Gozal","year":"2023","journal-title":"Arch. Bronconeumol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1097\/MCP.0000000000001122","article-title":"Hypoxic burden\u2014Definitions, pathophysiological concepts, methods of evaluation, and clinical relevance","volume":"30","author":"Parekh","year":"2024","journal-title":"Curr. Opin. Pulm. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"172","DOI":"10.31083\/j.rcm2505172","article-title":"The Hypoxic Burden, Clinical Implication of a New Biomarker in the Cardiovascular Management of Sleep Apnea Patients: A Systematic Review","volume":"25","author":"Coso","year":"2024","journal-title":"Rev. Cardiovasc. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1513\/pats.200709-155MG","article-title":"The epidemiology of adult obstructive sleep apnea","volume":"5","author":"Punjabi","year":"2008","journal-title":"Proc. Am. Thorac. Soc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s11325-026-03672-5","article-title":"\u201cPhenotyping obstructive sleep apnea: A pathway to precision medicine\u201d","volume":"30","author":"BaHammam","year":"2026","journal-title":"Sleep Breath."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, K., Geng, S., Shen, P., Zhao, L., Zhou, P., and Liu, W. (2024). Development and application of a machine learning-based predictive model for obstructive sleep apnea screening. Front. Big Data, 7.","DOI":"10.3389\/fdata.2024.1353469"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"6379","DOI":"10.1038\/s41598-023-33170-7","article-title":"Application of various machine learning techniques to predict obstructive sleep apnea syndrome severity","volume":"13","author":"Han","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"19756","DOI":"10.1038\/s41598-024-70647-5","article-title":"Enhanced machine learning approaches for OSA patient screening: Model development and validation study","volume":"14","author":"Dai","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.csbj.2025.04.033","article-title":"Status and opportunities of machine learning applications in obstructive sleep apnea: A narrative review","volume":"28","author":"Araujo","year":"2025","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1056\/NEJMcp1816152","article-title":"Obstructive Sleep Apnea in Adults","volume":"380","author":"Veasey","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2567","DOI":"10.1109\/JBHI.2020.3043507","article-title":"Detailed Assessment of Sleep Architecture with Deep Learning and Shorter Epoch-to-Epoch Duration Reveals Sleep Fragmentation of Patients with Obstructive Sleep Apnea","volume":"25","author":"Korkalainen","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Karuga, F.F., Kaczmarski, P., Bia\u0142asiewicz, P., Szmyd, B., Jaromirska, J., Grzybowski, F., Gebuza, P., Sochal, M., and Gabryelska, A. (2023). REM-OSA as a Tool to Understand Both the Architecture of Sleep and Pathogenesis of Sleep Apnea-Literature Review. J. Clin. Med., 12.","DOI":"10.3390\/jcm12185907"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e941066","DOI":"10.12659\/MSM.941066","article-title":"A Systematic Review of Publications on the Associations Between Sleep Architecture and Arterial Hypertension","volume":"29","author":"Kanclerska","year":"2023","journal-title":"Med. Sci. Monit."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"275","DOI":"10.5664\/jcsm.26797","article-title":"Improving the utility of interpreting sleep fragmentation","volume":"3","author":"Stepanski","year":"2007","journal-title":"J. Clin. Sleep Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI","volume":"32","author":"Tjoa","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s44163-024-00114-7","article-title":"Explainable and interpretable artificial intelligence in medicine: A systematic bibliometric review","volume":"4","author":"Frasca","year":"2024","journal-title":"Discov. Artif. Intell."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2606\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:21:57Z","timestamp":1787041317000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":30,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162606"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162606","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]}}}