Klinik ve demografik değişkenlerle obstrüktif uyku apne şiddeti makine öğrenimi tabanlı tahmin edilebilir mi?

Abstract

Amaç: Obstrüktif uyku apne sendromu (OSAS), uyku sırasında üst havayolunun tekrarlayan kollapslarıyla seyreden, aralıklı hipoksemi ve uykunun bölünmesiyle karakterize yaygın bir hastalıktır. Tanı, yüksek maliyetli ve erişimi sınırlı polisomnografi (PSG) ile konulmaktadır. Bu çalışmada yalnızca klinik ve demografik değişkenlere dayalı, PSG verileri kullanılmadan orta-ağır OSAS’ı (AHI ≥15) öngörebilen bir makine öğrenimi (ML) modeli geliştirilmesi amaçlanmıştır. Gereç ve Yöntem: 2019–2024 yılları arasında OSAS şüphesiyle değerlendirilen 1281 erişkin hasta retrospektif olarak incelendi. Değişkenler arasında yaş, cinsiyet, beden kitle indeksi (BKI), boyun çevresi, Epworth Uykululuk Skalası (ESS), sigara kullanımı ve hipertansiyon ile diyabet gibi komorbiditeler yer aldı. Dört algoritma (Random Forest, Gradient Boosting, Lojistik Regresyon ve Destek Vektör Makineleri) kullanılarak eğitim ve test veri setleri oluşturuldu (80/20 bölünme). Model performansı doğruluk, duyarlılık, özgüllük, F1 skoru ve ROC–AUC ile değerlendirildi. Bulgular: Katılımcıların %42,6’sında AHI ≥15 saptandı. En yüksek performans Random Forest modeliyle elde edildi (doğruluk %78,6; duyarlılık 0,95; özgüllük 0,81; F1 skoru 0,88; AUC 0,86). ESS ve BKI en güçlü belirleyiciler olup, yaş, boyun çevresi, sigara, hipertansiyon ve diyabet de katkı sağladı. Model, sınırlı kaynaklarda PSG önceliklendirmesi için pratik bir triyaj aracı olarak kullanılabilir. Sonuç: Makine öğrenimi modeli, yalnızca kolay erişilebilir klinik verilerle orta-ağır OSAS’ı yüksek doğrulukla öngörebilmiştir. Yüksek duyarlılığı ve klinik uygulanabilirliği, modelin erken risk sınıflandırmasında ve PSG kaynaklarının etkin kullanımında yardımcı olabileceğini göstermektedir.

Keywords

• obstrüktif uyku apnesi
• makine öğrenimi
• yapay zeka
• öngörü modeli
• Epworth Uykululuk Skalası

Predicting obstructive sleep apnea severity without polysomnography: a machine learning approach based on clinical and demographic features

Abstract

Aims: Obstructive sleep apnea (OSA) is a prevalent disorder characterized by recurrent upper airway collapse during sleep, causing intermittent hypoxia and sleep fragmentation. Diagnosis depends on polysomnography (PSG), which is resource intensive and not always available. This study aimed to develop and validate a machine learning (ML) model to predict clinically significant OSA (apnea-hypopnea index [AHI]≥15) using only demographic, behavioral, symptomatic, and comorbidity data, without PSG-derived parameters. Methods: A retrospective dataset of 1281 adults evaluated for suspected OSA was analyzed. Variables included age, sex, body-mass index (BMI), neck circumference, Epworth Sleepiness Scale (ESS), smoking status, and comorbidities such as hypertension and diabetes. Four algorithms Random Forest (RF), Gradient Boosting, Logistic Regression, and Support Vector Machine were trained and tested using an 80/20 split and five-fold cross-validation. Model performance was assessed by accuracy, recall, precision, F1-score, and ROC-AUC. Results: Among 1281 participants, 42.6% had AHI≥15. The RF model achieved the best performance with 78.6% accuracy, 0.95 recall, 0.81 precision, 0.88 F1-score, and 0.86 ROC-AUC. ESS and BMI were the strongest predictors, followed by age, neck circumference, smoking, hypertension, and diabetes. The model effectively identified moderate-to-severe OSA cases, offering a practical triage tool for prioritizing PSG in resource-limited settings. Conclusion: The ML model accurately predicted clinically significant OSA using only accessible clinical variables. Its high sensitivity and interpretability support potential integration into clinical workflows for efficient risk stratification and PSG allocation. Prospective multicenter validation is warranted.

Keywords

• Obstructive sleep apnea
• machine learning
• artificial intelligence
• prediction model
• epworth sleepiness scale

References

1. Benjafield AV, Ayas NT, Eastwood PR, et al. Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysis. Lancet Respir Med. 2019;7(8):687-698. doi:10.1016/S2213-2600 (19)30198-5
2. Jordan AS, McSharry DG, Malhotra A. Adult obstructive sleep apnoea. Lancet. 2014;383(9918):736-747. doi:10.1016/S0140-6736(13)60734-5
3. Marin JM, Carrizo SJ, Vicente E, Agusti AG. Long-term cardiovascular outcomes in men with obstructive sleep apnoea-hypopnoea with or without treatment with continuous positive airway pressure: an observational study. Lancet. 2005;365(9464):1046-1053. doi:10.1016/S01 40-6736(05)71141-7
4. McNicholas WT, Bonsigore MR; Management Committee of EU COST ACTION B26. Sleep apnoea as an independent risk factor for cardiovascular disease: current evidence, basic mechanisms and research priorities. Eur Respir J. 2007;29(1):156-178. doi:10.1183/09031936.000274 06
5. Peppard PE, Young T, Barnet JH, Palta M, Hagen EW, Hla KM. Increased prevalence of sleep-disordered breathing in adults. Am J Epidemiol. 2013;177(9):1006-1014. doi:10.1093/aje/kws342
6. Kapur VK, Auckley DH, Chowdhuri S, et al. Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: an American Academy of sleep medicine clinical practice guideline. J Clin Sleep Med. 2017;13(3):479-504. doi:10.5664/jcsm.6506
7. Levy J, Álvarez D, Del Campo F, Behar JA. Deep learning for obstructive sleep apnea diagnosis based on single channel oximetry. Nat Commun. 2023;14(1):4881. doi:10.1038/s41467-023-40604-3
8. Álvarez D, Cerezo-Hernández A, Crespo A, et al. A machine learning-based test for adult sleep apnoea screening at home using oximetry and airflow. Sci Rep. 2020;10(1):5332. doi:10.1038/s41598-020-62223-4

9. Tsai CY, Huang HT, Cheng HC, et al. Screening for obstructive sleep apnea risk by using machine learning approaches and anthropometric features. Sensors (Basel). 2022;22(22):8630. doi:10.3390/s22228630
10. Rosa JCFD, Peres A, Gasperin Júnior L, Martinez D, Fontanella V. Diagnostic accuracy of oximetry for obstructive sleep apnea: a study on older adults in a home setting. Clinics (Sao Paulo). 2021;76:e3056. doi:10. 6061/clinics/2021/e3056
11. Gutierrez-Tobal GC, Alvarez D, Crespo A, Del Campo F, Hornero R. Evaluation of machine-learning approaches to estimate sleep apnea severity from at-home oximetry recordings. IEEE J Biomed Health Inform. 2019;23(2):882-892. doi:10.1109/JBHI.2018.2823384
12. Senaratna CV, Perret JL, Lodge CJ, et al. Prevalence of obstructive sleep apnea in the general population: a systematic review. Sleep Med Rev. 2017;34:70-81. doi:10.1016/j.smrv.2016.07.002
13. Yaggi HK, Concato J, Kernan WN, Lichtman JH, Brass LM, Mohsenin V. Obstructive sleep apnea as a risk factor for stroke and death. N Engl J Med. 2005;353(19):2034-2041. doi:10.1056/NEJMoa043104
14. Kim RD, Kapur VK, Redline-Bruch J, et al. An economic evaluation of home versus laboratory-based diagnosis of obstructive sleep apnea. Sleep. 2015;38(7):1027-1037. doi:10.5665/sleep.4804
15. Suri J, Suri TA. Review of the current status of home sleep apnea testing vis-à-vis in-lab polysomnography: is old still gold? Indian Journal of Sleep Medicine. 2023;17:99-102. doi:10.5005/jp-journals-10069-0106 “
16. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32. doi:10.1023/A: 1010933404324
17. Kuhn M, Johnson K. Applied predictive modeling. New York: Springer; 2013. doi:10.1007/978-1-4614-6849-3