Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

The AI-Therapist Duo: Exploring the Potential of Human-AI Collaboration in Personalized Art Therapy for PICS Intervention

Bereket A. Yilma, Chan Mi Kim, Geke Ludden, Thomas van Rompay, Luis A. Leiva

TL;DR

This study tackles PICS by integrating human expertise with AI-driven art-recommendation systems to personalize therapy. It compares a visual-only ResNet-50 and a multimodal BLIP-based HITL pipeline, validating them through expert evaluation and a large user study (N=150). Results show HITL approaches improve recommendation relevance, elicit mood improvements, and cut therapists’ preparation time by about half, while underscoring the continued need for expert oversight to prevent negative content. The work demonstrates a scalable, safer path to personalized art therapy and suggests broad applicability to other emotionally supportive healthcare interventions.

Abstract

Post-intensive care syndrome (PICS) is a multifaceted condition that arises from prolonged stays in an intensive care unit (ICU). While preventing PICS among ICU patients is becoming increasingly important, interventions remain limited. Building on evidence supporting the effectiveness of art exposure in addressing the psychological aspects of PICS, we propose a novel art therapy solution through a collaborative Human-AI approach that enhances personalized therapeutic interventions using state-of-the-art Visual Art Recommendation Systems. We developed two Human-in-the-Loop (HITL) personalization methods and assessed their impact through a large-scale user study (N=150). Our findings demonstrate that this Human-AI collaboration not only enhances the personalization and effectiveness of art therapy but also supports therapists by streamlining their workload. While our study centres on PICS intervention, the results suggest that human-AI collaborative Art therapy could potentially benefit other areas where emotional support is critical, such as cases of anxiety and depression.

The AI-Therapist Duo: Exploring the Potential of Human-AI Collaboration in Personalized Art Therapy for PICS Intervention

TL;DR

This study tackles PICS by integrating human expertise with AI-driven art-recommendation systems to personalize therapy. It compares a visual-only ResNet-50 and a multimodal BLIP-based HITL pipeline, validating them through expert evaluation and a large user study (N=150). Results show HITL approaches improve recommendation relevance, elicit mood improvements, and cut therapists’ preparation time by about half, while underscoring the continued need for expert oversight to prevent negative content. The work demonstrates a scalable, safer path to personalized art therapy and suggests broad applicability to other emotionally supportive healthcare interventions.

Abstract

Post-intensive care syndrome (PICS) is a multifaceted condition that arises from prolonged stays in an intensive care unit (ICU). While preventing PICS among ICU patients is becoming increasingly important, interventions remain limited. Building on evidence supporting the effectiveness of art exposure in addressing the psychological aspects of PICS, we propose a novel art therapy solution through a collaborative Human-AI approach that enhances personalized therapeutic interventions using state-of-the-art Visual Art Recommendation Systems. We developed two Human-in-the-Loop (HITL) personalization methods and assessed their impact through a large-scale user study (N=150). Our findings demonstrate that this Human-AI collaboration not only enhances the personalization and effectiveness of art therapy but also supports therapists by streamlining their workload. While our study centres on PICS intervention, the results suggest that human-AI collaborative Art therapy could potentially benefit other areas where emotional support is critical, such as cases of anxiety and depression.

Paper Structure

This paper contains 22 sections, 1 equation, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Art therapy and its role in mental health
  4. State-of-the-Art Digital Art Therapy
  5. Method: Human-in-the-Loop VA RecSys for PICS intervention
  6. Materials
  7. Expert evaluation
  8. Results
  9. User study
  10. Apparatus
  11. Participants
  12. Design
  13. Procedure
  14. Results
  15. Analysis of recommendation quality measures
  16. ...and 7 more sections

Figures (8)

  • Figure 1: Diagram of the VA RecSys pipeline, from automatic feature extraction to automatic painting selection.
  • Figure 2: Overview of the painting selection process using three different approaches: Expert, HITL Visual, and HITL Multimodal.
  • Figure 3: Distribution (box plots) of user ratings for the user-centric dependent variables of recommendation quality. Dots denote mean values.
  • Figure 4: Mood improvement comparison before and after art therapy.
  • Figure 5: Individual Positive Affect Negative Affect Schedule (PANAS) scores per dimension.
  • ...and 3 more figures