Lima Diniz Araujo Matheus, Winger Trevor, Ghosn Samer, Saab Carl, Srivastava Jaideep, Kazaglis Louis, Mathur Piyush, Mehra Reena
Cleveland Clinic Foundation, Cleveland, OH, USA.
University of Minnesota, Minneapolis, MN, USA.
medRxiv. 2025 May 10:2025.02.27.25322950. doi: 10.1101/2025.02.27.25322950.
Obstructive sleep apnea (OSA) is a prevalent and potentially severe sleep disorder characterized by repeated interruptions in breathing during sleep. Machine learning models have been increasingly applied in various aspects of OSA research, including diagnosis, treatment optimization, and developing biomarkers for endotypes and disease mechanisms.
This narrative review evaluates the application of machine learning in OSA research, focusing on model performance, dataset characteristics, demographic representation, and validation strategies. We aim to identify trends and gaps to guide future research and improve clinical decision-making that leverages machine learning.
This narrative review examines data extracted from 254 scientific publications published in the PubMed database between January 2018 and March 2023. Studies were categorized by machine learning applications, models, tasks, validation metrics, data sources, and demographics.
Our analysis revealed that most machine learning applications focused on OSA classification and diagnosis, utilizing various data sources such as polysomnography, electrocardiogram data, and wearable devices. We also found that study cohorts were predominantly overweight males, with an underrepresentation of women, younger obese adults, individuals over 60 years old, and diverse racial groups. Many studies had small sample sizes and limited use of robust model validation.
Our findings highlight the need for more inclusive research approaches, starting with adequate data collection in terms of sample size and bias mitigation for better generalizability of machine learning models in OSA research. Addressing these demographic gaps and methodological opportunities is critical for ensuring more robust and equitable applications of artificial intelligence in healthcare.
阻塞性睡眠呼吸暂停（OSA）是一种常见且可能严重的睡眠障碍，其特征是睡眠期间呼吸反复中断。机器学习模型已越来越多地应用于OSA研究的各个方面，包括诊断、治疗优化以及开发内型和疾病机制的生物标志物。
本叙述性综述评估机器学习在OSA研究中的应用，重点关注模型性能、数据集特征、人口统计学代表性和验证策略。我们旨在确定趋势和差距，以指导未来的研究并改善利用机器学习的临床决策。
本叙述性综述审查了从2018年1月至2023年3月在PubMed数据库中发表的254篇科学出版物中提取的数据。研究按机器学习应用、模型、任务、验证指标、数据来源和人口统计学进行分类。
我们的分析表明，大多数机器学习应用集中在OSA分类和诊断上，利用了多种数据来源，如多导睡眠图、心电图数据和可穿戴设备。我们还发现，研究队列主要是超重男性，女性、年轻肥胖成年人、60岁以上个体和不同种族群体的代表性不足。许多研究样本量小，且对稳健模型验证的使用有限。
我们的研究结果强调需要采用更具包容性的研究方法，首先要在样本量方面进行充分的数据收集，并减轻偏差，以提高机器学习模型在OSA研究中的可推广性。解决这些人口统计学差距和方法学机会对于确保人工智能在医疗保健中的更稳健和公平应用至关重要。
