Prediction of Attention-Deficit/Hyperactivity Disorder Diagnosis Using Brief,Low-Cost Clinical Measures: A Competitive Model Evaluation

Abstract

Proper diagnosis of attention-deficit/hyperactivity disorder (ADHD) is costly, requiring in-depth evaluation via interview, multi-informant and observational assessment, and scrutiny of possible other conditions. The increasing availability of data may allow the development of machine-learning algorithms capable of accurate diagnostic predictions using low-cost measures to supplement human decision-making. We report on the performance of multiple classification methods used to predict a clinician-consensus ADHD diagnosis. Methods ranged from fairly simple (e.g., logistic regression) to more complex (e.g., random forest) but emphasized a multistage Bayesian approach. Classifiers were evaluated in two large (N > 1,000) independent cohorts. The multistage Bayesian classifier provided an intuitive approach consistent with clinical workflows and was able to predict expert consensus ADHD diagnosis with high accuracy (> 86%)—though not significantly better than other methods. Results suggest that parent and teacher surveys are sufficient for high-confidence classifications in the vast majority of cases, but an important minority require additional evaluation for accurate diagnosis.