SummaryShort summary of a recent publication, written by scientific experts.
Published: 24 Apr 2023
Machine learning for early detection of attention-deficit/hyperactivity disorder and sleep problems
In this diagnostic study a machine learning (ML) model was developed to facilitate the early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems in children.
Circadian rhythm-based wearable data was analyzed and demonstrated reasonable predictive performance for ADHD (area under curve [AUC], 0.798; sensitivity, 0.756; specificity, 0.716; positive predictive value [PPV], 0.159; and negative predictive value [NPV], 0.976) and sleep problems (AUC, 0.737; sensitivity, 0.743; specificity, 0.632; PPV, 0.036; and NPV, 0.992).
Authors concluded that this approach can facilitate the application of digital phenotypes for early detection or screening in children’s daily lives.