Hostname: page-component-5c6d5d7d68-xq9c7 Total loading time: 0 Render date: 2024-08-27T13:48:03.090Z Has data issue: false hasContentIssue false
  • English
  • Français

Tackling adversity through innovation: A pilot study exploring VR as a tool to identify and diagnose depression

Published online by Cambridge University Press:  27 August 2024

S. Sutori  and
Karolinska Institutet: E. Eliasson, G. Hadlaczky, I. Todorov, V. Carli; University of Padua: F. Mura, V. Cardi; Polytechnic University of Valencia: V. Ortiz, M.A. Raya; University of Pisa: A.L. Alfeo, V. Catrambone, G. Valenza
S. Sutori*
Affiliation:
1National Centre for Suicide Research and Prevention (NASP), LIME, Karolinska Institutet, Solna, Sweden
*
*Corresponding author.

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
Introduction

The final aim of the EXPERIENCE project is to enable individuals to record and share extended-personal realities in Virtual Reality (VR) - which entails the consideration of a person’s neurophysiological, psychological, and cognitive states. One prospective application is using this technology to aid in assessing symptoms of affective disorders.

Objectives

The objective is to test the ability of a pre-designed VR environment to differentiate between individuals with depressive symptoms and healthy controls (HCs) via machine learning algorithms.

Methods

Conducted as a pilot study in Italy, we recruited 100 volunteers, comprising 50 HCs and 50 individuals with moderate depressive symptoms assessed via the PHQ-9. Through a 40–60-minute VR engagement, comprehensive data on cognitive (inc. cognitive flexibility, sustained attention, working memory, processing speed), behavioral (exploration, attentional bias), and physiological (heart-rate variability, skin conductance) variables was collected. Subsequently, an explainable artificial intelligence model (xAI) was trained on data from 80% of the sample and tested on the remaining 20% in terms of accuracy for between-group classification.

Results

Following an iterative process that considered both the importance assigned to each variable in the different models and the theoretical relevance of these variables to depression the final model achieved an average accuracy of 71% (with individual trials ranging from 64.5% to 77.1%). Key predictors included exploratory behaviors and heart-rate variability during both exploration and cognitive tasks.

Conclusions

These results are comparable, however remain below the levels of accuracy achieved based on fMRI and DTI data alone (around 80%). Nonetheless, the EXPERIENCE system, slated for refinement beyond this pilot phase, shows potential in integrating multimodal data for evaluating affective disorder symptoms, aiming for a more objective screening and diagnostic approach at a lower cost.

Acknowledgement

The EXPERIENCE project is funded by the European Commission H2020 Framework Program, Grant No. 101017727.

Disclosure of Interest

None Declared

Type
Abstract
Information
European Psychiatry , Volume 67 , Special Issue S1: Abstracts of the 32nd European Congress of Psychiatry , April 2024 , pp. S18 - S19
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Copyright
© The Author(s), 2024. Published by Cambridge University Press on behalf of European Psychiatric Association
Submit a response

Comments

No Comments have been published for this article.