Predicting the Apnea-Hypopnea index for the diagnosis of obstructive sleep apnea with cardiovascular and cancer comorbidity using wearable sleep-tracking devices.
| Title: | Predicting the Apnea-Hypopnea index for the diagnosis of obstructive sleep apnea with cardiovascular and cancer comorbidity using wearable sleep-tracking devices. |
|---|---|
| Authors: | Ng HKT; Department of Mathematical Sciences, Bentley University, 175 Forest St., Waltham, MA, 02452, USA.; Nguyen U; Department of Industrial and Management Systems Engineering, University of South Florida, 4202 E. Fowler Avenue, Tampa, FL, 33620, USA.; Akbulut Y; Department of Industrial and Manufacturing Systems Engineering, North Dakota State University, 1315 Centennial Boulevard, Fargo, ND, 58102, USA.; Tran T; Department of Industrial and Management Systems Engineering, University of South Florida, 4202 E. Fowler Avenue, Tampa, FL, 33620, USA.; Vo T; Department of Industrial and Management Systems Engineering, University of South Florida, 4202 E. Fowler Avenue, Tampa, FL, 33620, USA.; Pirim H; Department of Industrial and Manufacturing Systems Engineering, North Dakota State University, 1315 Centennial Boulevard, Fargo, ND, 58102, USA. harun.pirim@ndsu.edu.; Setty A; Sanford Health, University of North Dakota, 5225 23rd Ave S, Fargo, ND, 58104, USA.; Le T; Department of Industrial and Management Systems Engineering, University of South Florida, 4202 E. Fowler Avenue, Tampa, FL, 33620, USA. tqle@usf.edu. |
| Source: | Sleep & breathing = Schlaf & Atmung [Sleep Breath] 2026 Feb 07; Vol. 30 (1), pp. 34. Date of Electronic Publication: 2026 Feb 07. |
| Publication Type: | Journal Article; Research Support, N.I.H., Extramural |
| Language: | English |
| Journal Info: | Publisher: Springer Country of Publication: Germany NLM ID: 9804161 Publication Model: Electronic Cited Medium: Internet ISSN: 1522-1709 (Electronic) Linking ISSN: 15209512 NLM ISO Abbreviation: Sleep Breath Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2005- : Heidelberg ; New York : Springer; Original Publication: Titisee-Neustadt, Germany : Druckbild GmbH |
| MeSH Terms: | Sleep Apnea, Obstructive*/diagnosis ; Sleep Apnea, Obstructive*/epidemiology ; Cardiovascular Diseases*/epidemiology ; Cardiovascular Diseases*/diagnosis ; Polysomnography*/instrumentation ; Neoplasms*/epidemiology ; Neoplasms*/diagnosis ; Wearable Electronic Devices*; Humans ; Comorbidity ; Male ; Middle Aged ; Female ; Adult ; Aged |
| Abstract: | Introduction: Obstructive Sleep Apnea (OSA) is a highly prevelance sleep breathing disorder that imposes, significant public health and economic burdens through its untreated associated comorbidities. The gold standard for diagnosing OSA, polysomnography (PSG), retains several limitations because it is cumbersome to conduct in the sleep lab and requires labor-intensive efforts to annotate the measurement. Furthermore, current research focuses on the alternative of PSG on the general OSA population without specifically considering the OSA comorbid conditions, such as cardiovascular and cancer diseases. There is a need for methods to monitor OSA using features derived from consumer sleep technologies (CSTs), considering comorbid conditions associated with OSA.; Methodology: In this paper, we identify the features that can be collected from CSTs to predict the patient's Apnea-Hypopnea Index (AHI) with the consideration of the comorbid chronic diseases, including cardiovascular disease and cancer. These sleep characteristics include the total recording time, the sleep period time, total sleep time, the onset of sleep, the efficiency of sleep, the wakefulness after the onset of sleep, the percentages of N1, N2, N3, REM sleep stages, the latency of REM from sleep onset and the latency of REM from lights off.; Results: Based on these features, we build stepwise regression, LASSO, and XGBoost models to evaluate the risk of a patient having OSA and classify individuals as normal versus OSA, achieving classification accuracies of 68.76%, 69.26%, and 70.4%, respectively. The proposed method has been validated based on the Wisconsin Sleep Cohort Database. To test the generalization of the method, the model was validated on the IRB-approved Sanford Obstructive Sleep Apnea Cancer dataset. XGBoost demonstrated superior performance with the highest Recall (0.9136) and F1 Score (0.7647), while regression and Lasso excel in interpreting the features with the Precision (0.865).; Conclusion: Such performance highlights their effectiveness in identifying OSA cases with comorbidity. Our proposed solutions introduce better interpretability of algorithms and improve the accuracy of OSA detection using CSTs while addressing the limitations of PSG.; (© 2026. The Author(s), under exclusive licence to Springer Nature Switzerland AG.) |
| Competing Interests: | Declarations. Conflict of interest/Competing interests: The authors have no conflict of interest to declare. Ethics approval and consent to participate: The Wisconsin Sleep Cohort dataset is publicly available for download at www.sleepdata.org, The Sanford Obstructive Sleep Apnea and Cancer dataset was collected under the IRB-CTR Retrospective 503- Study number STUDY 00003164 approved by Sanford Health. Consent for publication: N/A. |
| References: | Iannella G, Pace A, Bellizzi MG, Magliulo G, Greco A, De Virgilio A, Croce E, Gioacchini FM, Re M, Costantino A et al (2025) The global burden of obstructive sleep apnea. Diagnostics 15(9):1088. (PMID: 10.3390/diagnostics150910884036190612071658); Masa JF, Rubio M, Findley LJ, Cooperative Group (2000) Habitually sleepy drivers have a high frequency of automobile crashes associated with respiratory disorders during sleep. Am J Respiratory Critical Care Med 162(4):1407–1412. (PMID: 10.1164/ajrccm.162.4.9907019); Javaheri S, Javaheri S, Somers VK, Gozal D, Mokhlesi B, Mehra R, McNicholas WT, Zee PC, Campos-Rodriguez F, Martinez-Garcia MA et al (2024) Interactions of obstructive sleep apnea with the pathophysiology of cardiovascular disease, part 1: Jacc state-of-the-art review. J Am College Cardiol 84(13):1208–1223. (PMID: 10.1016/j.jacc.2024.02.059); Park JG, Ramar K, Olson EJ (2011) Updates on definition, consequences, and management of obstructive sleep apnea. Mayo Clinic Proceed 86(6):549–555. (PMID: 10.4065/mcp.2010.0810); Bonsignore MR, Baiamonte P, Mazzuca E, Castrogiovanni A, Marrone O (2019) Obstructive sleep apnea and comorbidities: a dangerous liaison. Multidisciplinary Respiratory Med 14:1–12. (PMID: 10.4081/mrm.2019.10); Sircu V, Colesnic S-I, Covantsev S, Corlateanu O, Sukhotko A, Popovici C, Corlateanu A (2023) The burden of comorbidities in obstructive sleep apnea and the pathophysiologic mechanisms and effects of cpap. Clocks Sleep 5(2):333–349. (PMID: 10.3390/clockssleep50200253736666010297352); Zinchuk A, Yaggi HK (2020) Phenotypic subtypes of osa: a challenge and opportunity for precision medicine. Chest 157(2):403–420. (PMID: 10.1016/j.chest.2019.09.00231539538); Shouldice RB, O’Brien LM, O’Brien C, Chazal P, Gozal D, Heneghan C (2004) Detection of obstructive sleep apnea in pediatric subjects using surface lead electrocardiogram features. Sleep 27(4):784–792. (PMID: 10.1093/sleep/27.4.78415283015); Surrel G, Aminifar A, Rincón F, Murali S, Atienza D (2018) Online obstructive sleep apnea detection on medical wearable sensors. IEEE Trans Biomed Circuits Syst 12(4):762–773. (PMID: 10.1109/TBCAS.2018.282465929993894); Massie F, Van Pee B, Bergmann J (2022) Correlations between home sleep apnea tests and polysomnography outcomes do not fully reflect the diagnostic accuracy of these tests. J Clinical Sleep Med 18(3):871–876. (PMID: 10.5664/jcsm.9744); Setty AR (2017) Underestimation of sleep apnea with home sleep apnea testing compared to in-laboratory sleep testing. J Clinical Sleep Med 13(4):531–532. See also: “Potential Underestimation of Sleep Apnea Severity by At-Home Kits: Rescoring In-Laboratory Polysomnography Without Sleep Staging” on page 551.; Baumert M, Cowie MR, Redline S, Mehra R, Arzt M, Pépin J-L, Linz D (2022) Sleep characterization with smart wearable devices: a call for standardization and consensus recommendations. Sleep 45(12):183. (PMID: 10.1093/sleep/zsac183); Lechat B, Naik G, Reynolds A, Aishah A, Scott H, Loffler KA, Vakulin A, Escourrou P, McEvoy RD, Adams RJ et al (2022) Multinight prevalence, variability, and diagnostic misclassification of obstructive sleep apnea. Am J Respiratory Critical Care Med 205(5):563–569. (PMID: 10.1164/rccm.202107-1761OC); Svensson T, Madhawa K, Chung U, Svensson AK et al (2024) Validity and reliability of the oura ring generation 3 (gen3) with oura sleep staging algorithm 2.0 (ossa 2.0) when compared to multi-night ambulatory polysomnography: A validation study of 96 participants and 421,045 epochs. Sleep Med 115:251–263. (PMID: 10.1016/j.sleep.2024.01.02038382312); Park JH, Wang C, Shin H (2024) FDA-cleared home sleep apnea testing devices. npj Digital Med 7(1):123.; Woerd C et al (2023) Studying sleep: towards the identification of hypnogram features that drive expert interpretation. Sleep 47(3).; Wächter M et al (2020) Unique sleep-stage transitions determined by obstructive sleep apnea severity, age and gender. J Sleep Res 29(2):12895. (PMID: 10.1111/jsr.12895); Le TQ, Cheng C, Sangasoongsong A, Bukkapatnam STS (2013) Prediction of sleep apnea episodes from a wireless wearable multisensor suite. In: 2013 IEEE Point-of-Care healthcare technologies (PHT), pp 152–155.; Le TQ, Cheng C, Sangasoongsong A, Wongdhamma W, Bukkapatnam STS (2013) Wireless wearable multisensory suite and real-time prediction of obstructive sleep apnea episodes. IEEE J Translational Eng Health Med 1:2700109–2700109. (PMID: 10.1109/JTEHM.2013.2273354); Schwab RJ, Erus G (2024) We Can Use Machine Learning to Predict Obstructive Sleep Apnea. Am Thoracic Soc.; An X, Zhou J, Xu Q, Zhao Z, Li W (2025) Artificial intelligence in obstructive sleep apnea: A bibliometric analysis. Digital Health 11:20552076251324450. (PMID: 10.1177/205520762513244464012388211930495); Hwang D, Rusk S, Fernandez C, Nygate Y, Vanasse T, Wodnicki J, Sekhon A, Shi J, Yan R (2024) Utilizing machine learning based on multimodal data to predict pap adherence in patients with osa. In: SLEEP, vol 47.; Su C-T et al (2012) Prediagnosis of obstructive sleep apnea via multiclass mts. Computat Math Methods Med 2012:212498.; Ustun B et al (2016) Clinical prediction models for sleep apnea: The importance of medical history over symptoms. J Clinical Sleep Med 12(2):161–168. (PMID: 10.5664/jcsm.5476); Bozkurt S, Bostanci A, Turhan M (2017) Can statistical machine learning algorithms help for classification of obstructive sleep apnea severity to optimal utilization of polysomnography resources? Methods Inf Med 56(4):308–318. (PMID: 10.3414/ME16-01-008428590499); Huang W-C, et al (2020) Support vector machine prediction of obstructive sleep apnea in a large-scale chinese clinical sample. Sleep 43(7).; Ramesh J et al (2021) Towards validating the effectiveness of obstructive sleep apnea classification from electronic health records using machine learning. Healthcare 9(11):1450. (PMID: 10.3390/healthcare9111450348284968622500); Zhang L et al (2021) Moderate to severe osa screening based on support vector machine of the chinese population faciocervical measurements dataset: a cross-sectional study. BMJ Open 11(9):048482. (PMID: 10.1136/bmjopen-2020-048482); Holfinger SJ et al (2022) Diagnostic performance of machine learning-derived osa prediction tools in large clinical and community-based samples. Chest 161(3):807–817. (PMID: 10.1016/j.chest.2021.10.02334717928); Yeghiazarians Y, Jneid H, Tietjens JR, Redline S, Brown DL, El-Sherif N, Mehra R, Bozkurt B, Ndumele CE, Somers VK et al (2021) Obstructive sleep apnea and cardiovascular disease: a scientific statement from the american heart association. Circulation 144(3):56–67. (PMID: 10.1161/CIR.0000000000000988); Karsten R, Rijken J, Toprak I, Kant E, Bree R, Smeele L, Brekel M, Vries N, Ravesloot M (2024) Prevalence of obstructive sleep apnea after treatment for advanced t-stage head and neck cancer. Eur Arch Oto-Rhino-Laryngology 281(4):1941–1952. (PMID: 10.1007/s00405-024-08467-6); Le T, Huynh P, Sharma A, Setty A, Blanchard M, Ng HKT, Luo Y, Le T (2024) A narrative review of the relationship between head and neck cancer and obstructive sleep apnea: Clinical studies and statistical analysis. Sleep Med Rev 102010.; Nguyen D, Hoang C, Huynh PK, Truong T, Nguyen D, Sharma A, Le TQ (2024) Multi-level phenotypic models of cardiovascular disease and obstructive sleep apnea comorbidities: A longitudinal wisconsin sleep cohort study. arXiv:2406.18602.; Wong KA, Paul A, Fuentes P, Lim DC, Das A, Tan M (2023) Screening for obstructive sleep apnea in patients with cancer–a machine learning approach. Sleep Adv 4(1):042. (PMID: 10.1093/sleepadvances/zpad042); Zhou DJ, Chahal R, Gotlib IH, Liu S (2024) Comparison of lasso and stepwise regression in psychological data. Methodology 20(2):121–143. (PMID: 10.5964/meth.11523); Venables WN, Ripley BD (2002) Modern Applied Statistics with S, 4th edn. Springer, New York. ISBN 0-387-95457-0.; Tibshirani R (1996) Regression shrinkage and selection via the lasso. J Royal Statistical Society Series B (Methodological) 58(1):267–288. (PMID: 10.1111/j.2517-6161.1996.tb02080.x); Bentéjac C, Csörgő A, Martínez-Muñoz G (2021) A comparative analysis of gradient boosting algorithms. Artif Intell Rev 54(3):1937–1967. (PMID: 10.1007/s10462-020-09896-5); Shahveisi K et al (2018) Sleep architecture in patients with primary snoring and obstructive sleep apnea. Basic Clinical Neurosc J 9(2):147–156. (PMID: 10.29252/nirp.bcn.9.2.147); Bianchi MT et al (2010) Obstructive sleep apnea alters sleep stage transition dynamics. PLoS ONE 5(6):11356. (PMID: 10.1371/journal.pone.0011356) |
| Grant Information: | U54GM128729 National Institute of General Medical Sciences of the National Institutes of Health |
| Contributed Indexing: | Keywords: Classification; Consumer sleep technologies; Machine learning; Regression models |
| Entry Date(s): | Date Created: 20260207 Date Completed: 20260207 Latest Revision: 20260326 |
| Update Code: | 20260326 |
| DOI: | 10.1007/s11325-025-03565-z |
| PMID: | 41653357 |
| Database: | MEDLINE |
Journal Article; Research Support, N.I.H., Extramural