APMAdvances in Precision Medicine2424-85922424-9106WHIOCE PUBLISHING PTE. LTD.10.18063/APM.v11i5.2016ArticleDevelopment and Validation of an Interpretable Machine Learning Model for Predicting Sleep Disorder Risk in Asthma Patients: A Nationwide Retrospective Cohort Studyhttps://artdesignp.com/journal/APM/11/5/10.18063/APM.v11i5.2016ZhaoWenhao,LiShuang,CuiZiyue,ZhangMengfan,ZhaoZhizheng,LyuShaobo,WuLei20261152026-05-26Background: Sleep disorders are prevalent among patients with asthma and negatively impact disease control, quality of life, and clinical outcomes. This study aimed to develop and validate a machine learning-based model for predicting sleep disorder risk in this population using routinely accessible clinical and physiological biomarkers. Methods: Data from the NHANES 2005–2010 cohort were analyzed. LASSO regression was applied to identify key predictors. Seven machine learning algorithms were subsequently developed and compared. Model performance was evaluated based on discrimination, calibration, and net clinical utility. SHAP analysis was used to interpret the optimal model and provide individualized risk assessments. Results: A total of 1,059 asthma patients were included and randomly divided into training and validation sets. LASSO regression identified seven predictors: hypertension status, congestive heart failure, asthma attack in the past year, serum iron, BMI, HDLC, and eGFR. In the validation set, the optimal model, random forest, demonstrated the highest AUC of 0.800 (95% CI: 0.772–0.828), with satisfactory calibration (Brier score: 0.164) and positive net benefit across a range of threshold probabilities in decision curve analysis. SHAP analysis revealed complex non-linear and threshold effects for metabolic and renal predictors. Conclusion: We developed and validated an interpretable, machine learning-based prediction model for sleep disorder risk in asthma patients using seven accessible clinical and laboratory parameters, offering a practical tool for early identification and targeted interventions in clinical practice.Sleep disorder,Machine learning,Prediction model,Asthma

[1] Oh J, Kim S, Kim M, et al., 2025, Global, Regional, and National Burden of Asthma and Atopic Dermatitis, 1990–2021, and Projections to 2050: A Systematic Analysis of the Global Burden of Disease Study 2021. The Lancet Respiratory Medicine, 13: 425–446. [2] Liu T, Qin H, 2025, Association of Obstructive Sleep Apnea Risk with Allergic Asthma: A Systematic Review and Meta-Analysis. Medicine, 104: e41918. [3] Luyster F, Shi X, Baniak L, et al., 2020, Associations of Sleep Duration with Patient-Reported Outcomes and Health Care Use in US Adults with Asthma. Annals of Allergy, Asthma & Immunology, 125: 319–324. [4] Mindus S, Gislason T, Benediktsdottir B, et al., 2024, Respiratory Symptoms, Exacerbations and Sleep Disturbances Are More Common Among Participants with Asthma and Chronic Airflow Limitation: An Epidemiological Study in Estonia, Iceland and Sweden. BMJ Open Respiratory Research, 11: e002063. [5] Kumar P, Goyal J, Singh K, 2022, Association of Symptoms of Sleep-Related Breathing Disorders with Asthma Control in Indian Children. Indian Journal of Pediatrics, 89: 31–36. [6] Capanoglu M, Ginis T, Buyuktiryaki B, et al., 2024, The Frequency of Sleep-Disordered Breathing in Preschool Children with Asthma and Its Effects on Control of Asthma. Allergologia et Immunopathologia, 52: 38–43. [7] Xu X, Tran T, Golam S, et al., 2025, Systemic Corticosteroid Dose–Response Effects in Asthma: An Observational Cohort Study. ERJ Open Research, 11: 00172-2024. [8] Yau E, Cheung J, Saini B, et al., 2025, Understanding How Sleep Disorders Are Managed in People with Asthma: A Scoping Review of the Literature. Journal of Asthma, 62: 1266–1279. [9] Selsick H, Heidbreder A, Ellis J, et al., 2024, Assessment and Management of Chronic Insomnia Disorder: An Algorithm for Primary Care Physicians. BMC Primary Care, 25: 138. [10] Yang M, Qian X, Zhu L, et al., 2025, Associations of Serum Neurofilament and Asthma: Evidence from the NHANES 2013–2014. Frontiers in Neurology, 16: 1567158. [11] Wang H, Zhang C, Chen B, et al., 2025, Development, Validation, and Visualization of a Machine Learning-Based Predictive Model for Depression Risk in Sleep Disorder Patients. BMC Psychiatry, 26: 91. [12] Xu Y, Goodacre R, 2018, On Splitting Training and Validation Set: A Comparative Study of Cross Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning. Journal of Analysis and Testing, 2: 249–262. [13] Brockmann P, Sanchez T, Castro-Rodriguez J, 2016, Sleep-Disordered Breathing in Children with Asthma: A Systematic Review on the Impact of Treatment. Journal of Asthma and Allergy, 2016: 83. [14] Yau E, Cheung J, Saini B, et al., 2025, Understanding How Sleep Disorders Are Managed in People with Asthma: A Scoping Review of the Literature. Journal of Asthma, 62: 1266–1279.