Artful Path to Healing - Using Machine Learning for Visual Art Recommendation to Prevent and Reduce Post-Intensive Care Syndrome

Aug 6, 2026

Staying in the intensive care unit (ICU) is often traumatic, leading to post-intensive care syndrome (PICS), which includes physical, psychological, and cognitive impairments. Limited interventions exist for PICS, and evidence suggests that exposure to visual art can help, especially when personalized. The work develops machine learning-based visual art recommendation systems (VARecSys) for therapeutic art experiences after ICU discharge. Four state-of-the-art recommendation engines are evaluated against expert-curated recommendations via a pilot and a large-scale study (n=150). Results indicate temporal affective-state improvements and favorable recommendation quality, supporting personalized art therapy.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages19

Reading Time48 min

AccessFree to download

Abstract

Introduction

Post-intensive care syndrome (PICS) and current interventions

Visual art and art therapy for psychological well-being

Personalization and recommendation systems for therapeutic effectiveness

Artful Path to Healing: Using Machine Learning for Visual Art Recommendation to Prevent and Reduce Post-Intensive Care Syndrome (PICS) Bereket A. Yilma [bereket.yilma@uni.lu](bereket.yilma@uni.lu)[ ](bereket.yilma@uni.lu)University of Luxembourg Luxembourg Chan Mi Kim [c.m.kim@utwente.nl](c.m.kim@utwente.nl)[ ](c.m.kim@utwente.nl)University of Twente The Netherlands Preference Elicitation Recommended Paintings Baseline measures Participants chooses one of the sample paintings Participants are randomly assigned to one of the recommendation sets Gerald C. Cupchik Luis A. Leiva [gerald.cupchik@utoronto.ca](gerald.cupchik@utoronto.ca) luis.leiva@uni.lu University of Toronto University of Luxembourg Canada Luxembourg Guided therapy using the recommended paintings Outcome measures Art therapy relevant measures: Openness to engagement with paintings Level of immersion in paintings PICS relevant measures: (Temporal) enhancement of affective state VA RecSys relevant measures: Accuracy, Diversity, Novelity, Serendipity Figure 1: Overview of our art therapy approach for PICS prevention and treatment. ABSTRACT Staying in the intensive care unit (ICU) is often traumatic, leading to post-intensive care syndrome (PICS), which encompasses physical, psychological, and cognitive impairments. Currently, there are limited interventions available for PICS. Studies indicate that exposure to visual art may help address the psychological aspects of PICS and be more effective if it is personalized. We develop Machine Learning-based Visual Art Recommendation Systems (VARecSys) to enable personalized therapeutic visual art experiences for post-ICU patients. We investigate four state-of-the-art VA RecSys engines, evaluating the relevance of their recommendations for therapeutic purposes compared to expert-curated recommendations. We conduct an expert pilot test and a large-scale user study (n=150) to assess the appropriateness and effectiveness of these recommendations. Our results suggest all recommendations enhance temporal affective states. Visual and multimodal VA RecSys engines compare favourably with expert-curated recommendations, indicating their potential to support the delivery of personalized art therapy for PICS prevention and treatment. This work is licensed under a Creative Commons Attribution International 4.0 License. CHI’24, May 11–16, 2024, Honolulu, HI, USA © 2024 Copyright held by the owner/author(s) . ACM ISBN 979-8-4007-0330-0/24/05 [https://doi.org/10.1145/3613904.3642636](https://doi.org/10.1145/3613904.3642636) CCS CONCEPTS • Information systems → Personalization; Recommender systems; • Computing methodologies → Learning latent representations; • Applied computing → Media arts. KEYWORDS Recommendation; Personalization; Artwork; User Experience; Machine Learning; intensive care unit; rehabilitation; Health ACM Reference Format: Bereket A. Yilma, Chan Mi Kim, Gerald C. Cupchik, and Luis A. Leiva. 2024. Artful Path to Healing: Using Machine Learning for Visual Art Recommendation to Prevent and Reduce Post-Intensive Care Syndrome (PICS) . In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI’24), May 11–16, 2024, Honolulu, HI, USA. ACM, New York, NY, USA, 19 pages. [https://doi.org/10.1145/3613904.3642636](https://doi.org/10.1145/3613904.3642636) 1 INTRODUCTION Patients in the intensive care unit (ICU) generally undergo stressful and traumatic experiences stemming from critical illness, medical procedures, pain, and a hostile environment [20] . Even after ICU discharge, these patients are vulnerable and at a high risk of readmission to the hospital and the ICU [70, 80]. Post-ICU patients often suffer from post-intensive care syndrome (PICS) which refers to“new or worsening impairments in physical, cognitive, or mental health arising after critical illness and persisting beyond acute care hospitalization” [55] . PICS is quite common

FAQs

What problem does this work address?

The work targets post-intensive care syndrome (PICS), which includes impairments in physical, psychological, or cognitive health after critical illness. It focuses on limitations of current PICS interventions.

How are machine learning recommendation systems used in the study?

The study proposes VARecSys to deliver personalized visual art experiences for post-ICU patients. It evaluates recommendations generated by four state-of-the-art recommender engines.

What outcomes are measured and what do the results indicate?

The study measures art-therapy relevant engagement and immersion, along with PICS-related temporal enhancement of affective state. It finds that all recommendation sets improve temporal affective states and that VA RecSys engines compare favorably with expert-curated recommendations.

Aug 6, 2026

Upload by Emma Wilson