A deep learning network was developed to determine Risser stage on adolescent pelvic radiographs. The network had similar accuracy to expert readers, and thus could be implemented to aid physicians to provide a second opinion on staging. Key PointsThe developed deep learning method to automate Risser stage assessment reached 78.0% accuracy, which was comparable to 74.5% agreement between expert readers. Risser stage assessment using deep learning models is promising for the evaluation of skeletal maturity in AIS and could reduce the propagation of error biases within clinical files.

Summary Sleepwalking is a common non‐rapid eye movement (NREM) parasomnia and a significant cause of sleep‐related injuries. While evidence suggest that the occurrence of this condition is partly determined by genetic factors, its pattern of inheritance remains unclear, and few molecular studies have been conducted. One promising candidate is the adenosine deaminase (ADA) gene. Adenosine and the ADA enzyme play an important role in the homeostatic regulation of NREM sleep. In a single sleepwalking family, genome‐wide analysis identified a locus on chromosome 20, where ADA lies. In this study, we examined if variants in the ADA gene were associated with sleepwalking. In total, 251 sleepwalking patients were clinically assessed, and DNA samples were compared to those from 94 unaffected controls. Next‐generation sequencing of the whole ADA gene was performed. Bio‐informatic analysis enabled the identification of variants and assessed variants enrichment in our cohort compared to controls. We detected 25 different coding and non‐coding variants, of which 22 were found among sleepwalkers. None were enriched in the sleepwalking population. However, many missense variants were predicted as likely pathogenic by at least two in silico prediction algorithms. This study involves the largest sleepwalking cohort in which the role of a susceptibility gene was investigated. Our results did not reveal an association between ADA gene and sleepwalking, thus ruling out the possibility of ADA as a major genetic factor for this condition. Future work is needed to identify susceptibility genes.