Rapid Anxiety and Depression Diagnosis in Young Children Enabled by Wearable Sensors and Machine Learning

This paper presents a new approach for diagnosing anxiety and depression in young children. Currently, diagnosis requires hours of structured clinical interviews and standardized questionnaires spread over days or weeks. We propose the use of a 90-second fear induction task during which time participant motion is monitoring using a commercially available wearable sensor. Machine learning and data extracted from the most clinically feasible 20-second phase of the task are used to predict diagnosis in a sample of children with and without an internalizing diagnosis. We examine the performance of a variety of feature sets and modeling approaches to identify the best performing logistic regression that provides a diagnostic accuracy of 80%. This accuracy is comparable to existing diagnostic techniques, but at a small fraction of the time and cost currently required. These results point toward the future use of this approach in a clinical setting for diagnosing children with internalizing disorders.