Abstract
Background and objectives: Timely treatment of pediatric obstructive sleep apnea (OSA) can prevent or reverse neurocognitive and cardiovascular morbidities. However, whether distinct phenotypes exist and account for divergent treatment effectiveness remains unknown. In this study, our goal is threefold: i) to define new data-driven pediatric OSA phenotypes, ii) to evaluate possible treatment effectiveness differences among them, and iii) to assess phenotypic information in predicting OSA resolution. Methods: We involved 22 sociodemographic, anthropometric, and clinical data from 464 children (5-10 years old) from the Childhood Adenotonsillectomy Trial (CHAT) database. Baseline information was used to automatically define pediatric OSA phenotypes using a new unsupervised subject-based association network. Follow-up data (7 months later) were used to evaluate the effects of the therapeutic intervention in terms of changes in the obstructive apnea-hypopnea index (OAHI) and the resolution of OSA (OAHI < 1 event per hour). An explainable artificial intelligence (XAI) approach was also developed to assess phenotypic information as OSA resolution predictor at baseline. Results: Our approach identified three OSA phenotypes (PHOSA1-PHOSA3), with PHOSA2 showing significantly lower odds of OSA recovery than PHOSA1 and PHOSA3 when treatment information was not considered (odds ratios, OR: 1.64 and 1.66, 95 % confidence intervals, CI: 1.03-2.62 and 1.01-2.69, respectively). The odds of OSA recovery were also significantly lower in PHOSA2 than in PHOSA3 when adenotonsillectomy was adopted as treatment (OR: 2.60, 95 % CI: 1.26-5.39). Our XAI approach identified 79.4 % (CI: 69.9-88.0 %) of children reaching OSA resolution after adenotonsillectomy, with a positive predictive value of 77.8 % (CI: 70.3 %-86.0 %). Conclusions: Our new subject-based association network successfully identified three clinically useful pediatric OSA phenotypes with different odds of therapeutic intervention effectiveness. Specifically, we found that children of any sex, >6 years old, overweight or obese, and with enlarged neck and waist circumference (PHOSA2) have less odds of recovering from OSA. Similarly, younger female children with no enlarged neck (PHOSA3) have higher odds of benefiting from adenotonsillectomy.

Abstract

Abstract

Abstract

Abstract
Study Objectives Unsupervised machine learning-an approach that identifies patterns and structures within data without relying on labels-has demonstrated remarkable success in various domains of sleep research. This underscores the broader utility of machine learning, suggesting that its capabilities extend beyond current applications and warrant further exploration for novel insights in sleep studies, focusing specifically on unsupervised machine learning.Methods This paper outlines a scoping review conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines for scoping reviews. A comprehensive search covering various search terms focusing on the intersection between unsupervised machine learning and sleep led to 3960 publications. After screening all titles and abstracts with two independent reviewers, ultimately, 356 publications were included in the full-text review. The data extracted from the full texts included information about the machine learning methods and types of sleep data, as well as the study population.Results There has been a steep increase in the number of publications in this research area in the past 10 years. Clustering is the most commonly used method, but other methods are gaining popularity. Apart from classical polysomnography, data from wearable devices, nearables, video, audio, and medical imaging techniques have been used as input to unsupervised machine learning. The broad search allowed us to explore various applications within sleep research, ranging from the general population to populations with various sleep disorders.Conclusion The review mapped existing research on unsupervised learning in sleep research, identified gaps in the literature, and derived directions for future research. Statement of Significance Sleep is a transdisciplinary research field. With the rise of unsupervised machine learning and its emergence in sleep research, there is a pressing need to cultivate a mutual understanding across disciplinary boundaries to curate meaningful applications of unsupervised machine learning. This scoping review aims to serve as a foundation to facilitate collaboration across disciplines and ultimately contribute to the elevation of sleep research, by identifying novel ways of applying unsupervised machine learning.