OC12 - Machine Learning and Big Data

Comparison Between Clinician and Machine Learning Prediction in a Randomized Controlled Trial for Nonsuicidal Self-Injury
August, 30 | 12:00 - 13:00

Nonsuicidal self-injury is a common health problem in adolescents and associated to future suicidal behavior. Predicting who will benefit from treatment is a critical first step towards personalized treatment approaches. Machine-learning algorithms have been proposed as techniques that might outperform cliniciansÂ’ judgment. The aim of this study was to compare clinician and machine-learning algorithm predictions of which patients would abstain from nonsuicidal self-injury (measured using youth version of Deliberate Self-harm Inventory) after an Internet-delivered emotion regulation therapy (n = 138). Both clinician (accuracy = 0.63) and model-based (accuracy = 0.67) predictions achieved significantly better accuracy than a simple all?respond model (accuracy = 0.49 [95% CI 0.41 to 0.58]), however there was no statistically significant difference between them. Adding clinician predictions to the random forest model did not improve accuracy. Emotion dysregulation was identified as the most important predictor of nonsuicidal self-injury absence. Here we show comparable prediction accuracy between clinicians and a machine-learning algorithm in the psychological treatment of nonsuicidal self-injury in a moderately sized clinical sample among youth. As both prediction approaches achieved modest accuracy, the current results indicate the need for further research to enhance the predictive power of machine-learning algorithms. Screening for emotion dysregulation may be an important factor to consider in the treatment planning of adolescents with nonsuicidal self-injury.

Speakers