Predicting levels of prolonged grief disorder symptoms during the COVID-19 pandemic: An integrated approach of classical data exploration, predictive machine learning, and explainable AI

Prior studies on Prolonged Grief Disorder (PGD) primarily employed classical approaches to link bereaved individuals' characteristics with PGD symptom levels. This study utilized machine learning to identify key factors influencing PGD symptoms during the COVID-19 pandemic. We analyzed data fro...

Full description

Saved in:
Bibliographic Details
Published in:Journal of affective disorders 2024-04, Vol.351, p.746-754
Main Authors: Cherblanc, Jacques, Gaboury, Sébastien, Maître, Julien, Côté, Isabelle, Cadell, Susan, Bergeron-Leclerc, Christiane
Format: Article
Language:English
Subjects:
Artificial Intelligence
Bereavement
COVID-19
Explainable AI
Grief
Humans
Machine learning
Pandemic
Pandemics
Predictive modeling
Prolonged Grief Disorder
Stress Disorders, Post-Traumatic - epidemiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Prior studies on Prolonged Grief Disorder (PGD) primarily employed classical approaches to link bereaved individuals' characteristics with PGD symptom levels. This study utilized machine learning to identify key factors influencing PGD symptoms during the COVID-19 pandemic. We analyzed data from 479 participants through an online survey, employing classical data exploration, predictive machine learning, and SHapley Additive exPlanations (SHAP) to determine key factors influencing PGD symptoms measured with the Traumatic Grief Inventory - Self Report (TGI-SR) from 19 variables, comparing five predictive models. The classical approach identified eight variables associated with a possible PGD (TGI-SR score ≥ 59): unexpected causes of death, living alone, seeking professional support, taking anxiety and/or depression medications, using more grief services (telephone or online supports) and more confrontation-oriented coping strategies, and higher levels of depression and anxiety. Using machine learning techniques, the CatBoost algorithm provided the best predictive model of the TGI-SR score (r2 = 0.6479). The three variables influencing the most the level of PGD symptoms were anxiety, and levels of avoidance and confrontation coping strategies used. This pioneering approach within the field of grief research enabled us to leverage the extensive dataset collected during the pandemic, facilitating a deeper comprehension of the predominant factors influencing the grieving process for individuals who experienced loss during this period. This study acknowledges self-selection bias, limited sample diversity, and suggests further research is needed to fully understand the predictors of PGD symptoms. •Grief complications are predicted using an innovative approach of Machine Learning.•The CatBoost algorithm provide the best predictive model of the TGI-SR score.•The best predictors are anxiety, avoidance and confrontation strategies levels.•Machine Learning is a relevant approach to studying grief in a heuristic way.
ISSN:0165-0327
1573-2517
DOI:10.1016/j.jad.2024.01.236