Overcoming sleep disordered breathing and ensuring sufficient good sleep time for a healthy life expectancy

Sleep-Energy: An Energy Optimization Method to Sleep Stage Scoring

Sleep is essential for physical and mental health. Polysomnography (PSG) procedures are labour-intensive and time-consuming, making diagnosing sleep disorders difficult. Automatic sleep staging using Machine Learning (ML) - based methods has been studied extensively, but frequently provides noisier predictions incompatible with typical manually annotated hypnograms. We propose an energy optimization method to improve the quality of hypnograms generated by automatic sleep staging procedures. The method evaluates the system's total energy based on conditional probabilities for each epoch's stage and employs an energy minimisation procedure. It can be used as a meta-optimisation layer over the sleep stage sequences generated by any classifier that generates prediction probabilities. The method improved the accuracy of state-of-the-art Deep Learning models in the Sleep EDFx dataset by 4.0% and in the DRM-SUB dataset by 2.8%.

Differences of Craniofacial Characteristics in Oral Breathing and Pediatric Obstructive Sleep Apnea

BACKGROUND

Oral breathing (OB) was considered associated with specific craniofacial structures and same for pediatric obstructive sleep apnea (OSA). This study aimed to investigate the differences of craniofacial structures between OB and OSA.

METHODS

In this retrospective study, 317 children under age 18 years were recruited and divided into OB group, OSA group, and control group. OSA group (15 boys, 4 girls) were referred from qualified sleep center and diagnosed as pediatric OSA with full-night polysomnography. OB group (10 boys, 10 girls) were mostly referral from pediatric or ENT department, some of whom undertook polysomnography and were not OSA. Control group consisted of orthodontic patients within the same period. Lateral cephalograms were obtained in all groups and their parameters were compared with Chinese normal values and each other.

RESULTS

R-PNS of OB group (18.04 ± 2.49 mm) was greater than OSA group (14.27 ± 4.36 mm) and even control group (16.22 ± 3.91 mm) (P < 0.01). U1-NA was also the greatest in OB group (7.15 ± 2.92 mm), followed by OSA group (4.88 ± 2.66 mm), while control group was the smallest (5.71 ± 2.94 mm) (P < 0.05). In addition, OB group presented the smallest adenoids and tonsils among three groups. Bony nasopharynx development, mandibular length and growth direction of mandible of OB group were all better than OSA group.

CONCLUSION

Despite of oral breathing, anatomical morphology (well-developed dentoalveolar structures; mild adenotonsillar hypertrophy) might protect children from developing OSA.