To explore whether principal component analysis integrating behavioral and imaging data can differentiate individuals with Angelman syndrome from typically developing individuals and other neurodevelopmental disorders, and to assess the potential of multidimensional approaches to generate a quantitative cross-domain severity score.

AS is a rare neurodevelopmental disorder caused by the loss of expression of the maternal UBE3A allele. Patients present with an array of communication deficits, motor impairment, epilepsy, sleep disturbance, and cognitive dysfunction. Given this phenotypic heterogeneity, outcome measurement for clinical trials is challenging. Tools that reliably capture global and domain-specific severity, while clarifying genotype–phenotype correlations, are crucial for the success of ongoing and future clinical trials.

Multidimensional analysis produced coherent severity domains encompassing communication, motor, social/emotional, daily living skills, and brain volumes. The composite score distinguished AS from controls with 98% accuracy and demonstrated consistent performance across different characteristic subsets.

This exploratory study establishes proof of concept that principal component analysis of behavioral and imaging data in AS effectively differentiates disease states and provides preliminary genotype–phenotype characterization. These preliminary findings provide a foundation upon which ongoing studies will refine best practices for applying multidimensional methods to larger datasets, like such as the Angelman Syndrome Natural History Study, with the goal of advancing future clinical applications.