A Nomogram for Predicting ADHD and ASD in Child and Adolescent Mental Health Services (CAMHS).

To enhance the early detection of Attention Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) by leveraging clinical variables collected at child and adolescent mental health services (CAMHS). This study included children diagnosed with ADHD and/or ASD ( = 857). Three logistic regression models were developed to predict the presence of ADHD, its subtypes, and ASD. The analysis began with univariate logistic regression, followed by a multicollinearity diagnostic. A backward logistic regression selection strategy was then employed to retain variables with < 0.05. Ethical approval was obtained from the local ethics committee. The models' internal validity was evaluated based on their calibration and discriminative abilities. The study produced models that are well-calibrated and validated for predicting ADHD (incorporating variables such as physical activity, history of bone fractures, and admissions to pediatric/psychiatric services) and ASD (including disability, gender, special education needs, and Axis V diagnoses, among others). Clinical variables can play a significant role in enhancing the early identification of ADHD and ASD.