Publications

Introduction: Obstructive sleep apnea (OSA) can cause severe complications if left untreated. Several challenges hinder OSA identification in females, resulting in underdiagnosis and undertreatment in this population. This study aimed to develop a machine learning (ML) approach specifically tailored to screen for moderate-to-severe OSA in women. Methods: A retrospective study using clinical records of 1210 women who underwent polysomnography at our institution was conducted. Collected data included demographics, body metrics, nocturnal oxygen saturation levels, medical conditions, medications, laboratory measurements, and polysomnography results. Four ML algorithms to classify participants into moderate-to-severe and none-to-mild OSA groups were employed. Results: Due to the high missingness of laboratory values in the whole cohort, two sets of models were developed: one that considered all subjects but excluded lab tests and another that only used a subgroup of 383 participants and additionally incorporated hemoglobin and lipid profile levels alongside the other features. Without laboratory measurements, the best-performing model was adaptive boosting, which achieved an area under the receiver operating characteristic curve and accuracy of 0.811 and 76.03%, respectively. When lab tests were included, gradient boosting machine outperformed its competitors, with the above metrics reaching 0.872 and 84.42%, respectively. Conclusion: The promising performance of our approach underlines the potential of artificial intelligence in refining screening strategies for OSA in women. Nadir oxygen saturation during sleep emerged as a particularly strong predictor, reinforcing the central role of nocturnal hypoxemia in OSA risk stratification. Future research should focus on incorporating broader clinical inputs and using larger, diverse datasets to deploy a highly accurate and robust model that meets clinical standards and is suitable for real-world implementation.