Quantifying Risk for Anxiety Disorders in Preschool Children: A Machine Learning Approach

Abstract

Early childhood anxiety disorders are common, impairing, and predictive of anxiety and mood disorders later in childhood. Epidemiological studies over the last decade find that the prevalence of impairing anxiety disorders in preschool children ranges from 0.3% to 6.5%. Yet, less than 15% of young children with an impairing anxiety disorder receive a mental health evaluation or treatment. One possible reason for the low rate of care for anxious preschoolers is the lack of affordable, timely, reliable and valid tools for identifying young children with clinically significant anxiety. Diagnostic interviews assessing psychopathology in young children require intensive training, take hours to administer and code, and are not available for use outside of research settings. The Preschool Age Psychiatric Assessment (PAPA) is a reliable and valid structured diagnostic parent-report interview for assessing psychopathology, including anxiety disorders, in 2 to 5 year old children. In this paper, we apply machine-learning tools to already collected PAPA data from two large community studies to identify sub-sets of PAPA items that could be developed into an efficient, reliable, and valid screening tool to assess a young child's risk for an anxiety disorder. Using machine learning, we were able to decrease by an order of magnitude the number of items needed to identify a child who is at risk for an anxiety disorder with an accuracy of over 96% for both generalized anxiety disorder (GAD) and separation anxiety disorder (SAD). Additionally, rather than considering GAD or SAD as discrete/binary entities, we present a continuous risk score representing the child's risk of meeting criteria for GAD or SAD. Identification of a short question-set that assesses risk for an anxiety disorder could be a first step toward development and validation of a relatively short screening tool feasible for use in pediatric clinics and daycare/preschool settings.

Fig 1. Average accuracy, specificity, and sensitivity by the number of nodes in each tree.

During the training procedure, the number of nodes in the trees was chosen using 10-fold cross-validation. This figure shows the average accuracy, specificity, and sensitivity against the number of nodes in the tree for (left) SAD and (right) GAD. We chose to use trees with the smaller number of nodes producing the highest accuracy: 5 nodes for GAD, 10 nodes for SAD.

Fig 2. ADTree for Separation Anxiety Disorder.

Green boxes represent individual PAPA items; white boxes represent decision points, and blue boxes represent the associated AD-Score.

Fig 3. ADTree for Generalized Anxiety Disorder.

Green boxes represent individual PAPA items, white boxes represent decision points, and blue boxes represent the associated risk AD-Score.

Fig 4. Positive Predictive Value by Risk Scores.

Lines represent the weighted positive predictive value, which is the probability that the child meets criteria for Generalized Anxiety Disorder (GAD) and Separation Anxiety Disorder (SAD) on the full PAPA interview in the PTRTS test sample, for each Risk Score and associated AD-Scores.

Fig 5. Example Clinical Screening Form.

Example of an auto-scoring form populated with questions and AD-Scores from the GAD ADTree depicted in Fig 3. As the examiner answers the questions (denoted as an “X” next to the associated answer in the “Response” column), the score sheet automatically assigns the associated AD-Score and calculates a cumulative risk score using the equation: Risk Score = 1 − (1/(exp(AD − Score) + 1)) with each additional question.