Using machine learning to increase access to and engagement with trauma-focused interventions for posttraumatic stress disorder.

Abstract

Background: Post-traumatic stress disorder (PTSD) poses a global public health challenge. Evidence-based psychotherapies (EBPs) for PTSD reduce symptoms and improve functioning (Forbes et al., Guilford Press, 2020, 3). However, a number of barriers to access and engagement with these interventions prevail. As a result, the use of EBPs in community settings remains disappointingly low (Charney et al., Psychological Trauma: Theory, Research, Practice, and Policy, 11, 2019, 793; Richards et al., Community Mental Health Journal, 53, 2017, 215), and not all patients who receive an EBP for PTSD benefit optimally (Asmundson et al., Cognitive Behaviour Therapy, 48, 2019, 1). Advancements in artificial intelligence (AI) have introduced new possibilities for increasinfg access to and quality of mental health interventions.

Aims: The present paper reviews key barriers to accessing and engaging in EBPs for PTSD, discusses current applications of AI in PTSD treatment and provides recommendations for future AI integrations aimed at reducing barriers to access and engagement.

Discussion: We propose that AI may be utilized to (1) assess treatment fidelity; (2) elucidate novel predictors of treatment dropout and outcomes; and (3) facilitate patient engagement with the tasks of therapy, including therapy practice. Potential avenues for technological advancements are also considered.