V. Kaldo, Sweden
Karolinska Institutet Department of Psychology Clinical NeuroscienceModerator of 1 Session
Proposed by the EPA Section on Psychotherapy -This symposium will present current knowledge, development and clinical experiences on internet-based cognitive behavioural therapy (ICBT) developed in various settings and countries. Presentations include a description of the journey towards national implementation of ICBT and its outcomes in Sweden (MK), of individually tailored ICBT with different modes of delivery and different degrees of therapist support. Moreover, a presentation by VK include Adaptive Treatment Strategies, where a wide range of data before and during treatment are processed by an AI-driven clinical decision support tool guiding the adaption of therapist-guided ICBT at the individual level. Another presentation (KM) will describe the implementation of a national ICBT clinic in Denmark, from the first initial steps through to becoming a national service. Current evidence of effectiveness and implementation efforts conducted at the clinic. JB will report on a pilot study comparing online versus face-to-face transdiagnostic therapy in Arabic-speaking refugees. She will describe the different aspects of tailoring treatment contents in these two settings and discuss potential advantages of a tailored approach for the specific patient population.
Presenter of 2 Presentations
Live Q&A
S0044 - AI-driven Adaptive Treatment Strategies in Internet-delivered CBT
ABSTRACT
Abstract Body
Introduction
Adaptive Treatment Strategies warns therapists of patients at risk of treatment failure to prompt an adaption of the intervention. Internet-delivered Cognitive Behavioural Therapy (ICBT) collects a wide range of data before and during treatment and can quickly be adapted by adjusting the level of therapist support.
Objectives
To evaluate how accurate machine learning algorithms can predict a single patient’s final outcome and evaluate the opportunities for using them within an Adaptive Treatment Strategy.
Methods
Over 6000 patients at the Internet Psychiatry Clinic in Stockholm receiving ICBT for major depression, panic disorder or social anxiety disorder composed a training data set for eight different machine learning methods (e.g. k-Nearest Neighbour, random forest, and multilayer perceptrons). Symptom measures, messages between therapist and patient, homework reports, and other data from baseline to treatment week four was used to predict treatment success (either 50% reduction or under clinical cut-off) for each primary symptom outcome.
Results
The Balanced Accuracy for predicting failure/success always were significantly better than chance, varied between 56% and 77% and outperformed the predictive precision in a previous Adaptive Treatment Strategy trial. Predictive power increased when data from treatment weeks was cumulatively added to baseline data.
Conclusions
The machine learning algorithms outperformed a predictive algorithm previously used in a successful Adaptive Treatment Strategy, even though the latter also received input from a therapist. The next steps are to visualize what factors contributes most to a specific patient’s prediction and to enhance predictive power even further by so called Ensemble Learning.