Bridging the Gender Gap in Obstructive Sleep Apnea: A Machine Learning Approach to Screening Women for...

Obstructive sleep apnea (OSA) can lead to 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 women for moderate-to-severe OSA.

A retrospective study was conducted using clinical records of 1,210 women who underwent polysomnography at our institution. Collected data included demographics, body metrics, nocturnal oxygen saturation levels, medical conditions, medications, laboratory measurements, and polysomnography results. Four ML algorithms were employed to classify participants into moderate-to-severe and none-to-mild OSA groups.

Due to the high missingness of laboratory values in the whole cohort, two sets of models were developed: one utilizing all subjects but excluding lab tests, and another restricted to a subgroup of 383 participants that additionally incorporated hemoglobin and lipid profile 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.

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 develop a highly accurate, robust model that meets clinical standards and is suitable for real-world implementation.