UNSTRUCTURED
Artificial intelligence (AI) tools have the potential to objectively identify youth in need of mental health care. Speech signals have demonstrated promise as a source for predicting various psychiatric conditions and transdiagnostic symptoms. Thus, we designed a study testing the association between obsessive compulsive disorder (OCD) diagnosis and symptom severity on vocal features in children and adolescents. Here, we present an analysis plan and statistical report for the study. Audio recordings of clinical interviews of 15 children and adolescents with OCD and 15 children and adolescents without a psychiatric diagnosis will be analyzed. Youth were between 8 and 17 years old. We will test the effect of OCD diagnosis on computationally-derived scores of vocal activation and valence using an analysis of variance. To test the effect of OCD severity classifications on the same computationally-derived vocal scores, we will use logistic regression. Finally, we attempt to create an improved indicator of OCD severity by refining the model with more relevant labels. Models will be adjusted for age and gender. Model validation strategies are outlined. A major strength is that we include age and gender in our models to increase classification accuracy. A major challenge is the suboptimal quality of the audio recordings, which are representative of in-the-wild data and a large body of recordings collected during other clinical trials. This pre-registered analysis plan and statistical report will increase validity of the interpretations of the coming results.