Prediction of Emergency Department Revisits among Child and Youth Mental Health Outpatients Using Deep Learning Techniques

Abstract

Abstract Background The proportion of Canadian youth seeking mental health support from an emergency department (ED) has risen in recent years. As EDs typically address urgent mental health crises, revisiting an ED may represent unmet mental health needs. Accurate ED revisit prediction could aid early intervention and ensure efficient healthcare resource allocation. We examine the potential increased accuracy and performance of graph neural network (GNN) machine learning models compared to recurrent neural network (RNN) and a baseline regression models for predicting ED revisit in electronic health record (EHR) data. Methods This study used EHR data for children and youth aged 4–17 seeking services at McMaster Children's Hospital's Child and Youth Mental Health Program outpatient services to develop and evaluate GNN and RNN models to predict whether a child/youth with an ED visit had an ED revisit within 30 days. Candidate GNN and RNN models were developed and the best performing of each model was selected for comparison. Model performance for a GNN, RNN and a logistic regression was evaluated using F1 scores. Results The GNN model outperformed the best performing RNN model by an F1-score increase of 0.0287. Precision, recall, receiver operating characteristic (ROC) curves, and positive and negative predictive values showed that both the RNN and GNN models performed better than the baseline logistic regression model and that performance increases were most noticeable for recall and negative predictive value (59% vs. 66%) than for precision and positive predictive value (62% vs. 66%). Conclusions This study demonstrates the improved accuracy and potential utility of GNN models in predicting ED revisits among children and youth, although model performance may not be sufficient for clinical implementation. Given the improvements in recall and negative predictive value, GNN models should be further explored to develop algorithms that can inform clinical decision-making in ways that facilitate targeted interventions, optimize resource allocation, and improve outcomes for children and youth.