V. Kaldo, Sweden

Karolinska Institutet Department of Psychology Clinical Neuroscience
Clinical Psychologist. Started clinical work and research on internet-delivered CBT (ICBT) in 1999, and has since 2008 been a part of developing, evaluating and implementing ICBT for a range of psychiatric disorders at the Internet Psychiatry Clinic and Karolinska Institutet in Stockholm. Since 2018 a professor of clinical psychology at the Linnaeus University.

Moderator Of 1 Session

Clinical/Therapeutic
Date
Sun, 11.04.2021
Session Time
15:30 - 17:00
Room
Channel 7
Session Description
The Live Q&A of this session will take place in the Live Sessions auditorium. Please refer to the interactive programme for the exact time and channel.

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.

Session Icon
Pre-Recorded with Live Q&A, Section

Presenter Of 2 Presentations

Symposium: Next Chapters in the Story of Internet-based CBT: Implementation, Personalisation and AI-driven Decision Support Tools (ID 131) No Topic Needed
Symposium: Next Chapters in the Story of Internet-based CBT: Implementation, Personalisation and AI-driven Decision Support Tools (ID 131) No Topic Needed

S0044 - AI-driven Adaptive Treatment Strategies in Internet-delivered CBT

Session Icon
Pre-Recorded with Live Q&A, Section
Date
Sun, 11.04.2021
Session Time
15:30 - 17:00
Room
Channel 7
Lecture Time
16:21 - 16:38
Presenter

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.

Hide