Depression is associated with treatment response trajectories in adults with Prolonged Grief Disorder: A machine learning analysis

Adam Calderon; Matthew Irwin; Naomi M Simon; M Katherine Shear; Christine Mauro; Sidney Zisook; Charles F Reynolds 3rd; Matteo Malgaroli

doi:10.1016/j.jad.2025.119536

Depression is associated with treatment response trajectories in adults with Prolonged Grief Disorder: A machine learning analysis

J Affect Disord. 2025 May 27:388:119536. doi: 10.1016/j.jad.2025.119536. Online ahead of print.

Authors

Adam Calderon¹, Matthew Irwin², Naomi M Simon², M Katherine Shear³, Christine Mauro⁴, Sidney Zisook⁵, Charles F Reynolds 3rd⁶, Matteo Malgaroli⁷

Affiliations

¹ Department of Psychiatry, New York University Grossman School of Medicine, New York, NY, USA; Department of Psychology, The Pennsylvania State University, University Park, PA, USA.
² Department of Psychiatry, New York University Grossman School of Medicine, New York, NY, USA.
³ Columbia School of Social Work, Columbia University College of Physicians and Surgeons, New York, NY, USA; Department of Psychiatry, Columbia University College of Physicians and Surgeons, New York, NY, USA.
⁴ Department of Biostatistics, Mailman School of Public Health, Columbia University, New York, NY, USA.
⁵ Department of Psychiatry, University of California, San Diego, USA.
⁶ Department of Psychiatry, Western Psychiatric Institute and Clinic, University of Pittsburgh School of Medicine, Pittsburgh, PA, USA.
⁷ Department of Psychiatry, New York University Grossman School of Medicine, New York, NY, USA. Electronic address: matteo.malgaroli@nyulangone.org.

PMID: 40441659
DOI: 10.1016/j.jad.2025.119536

Abstract

Background: Although evidence-based Prolonged Grief Disorder treatments (PGDT) exist, pretreatment characteristics associated with differential improvement remain unidentified. To identify clinical factors relevant to optimizing PGDT outcomes, we used unsupervised and supervised machine learning to study treatment effects from a double-blinded, placebo-controlled, randomized clinical trial.

Methods: Patients were randomized into four treatment groups for 20 weeks: citalopram with grief-informed clinical management, citalopram with PGDT, pill placebo with PGDT, or pill placebo with clinical management. The trial included 333 PGD patients aged 18-95 years (M = 53.9; SD = 14.4). Symptom trajectories were assessed using latent growth mixture modeling based on Inventory for Complicated Grief scores collected every 4 weeks. The relationship between patient-level characteristics and assigned trajectories was examined using logistic regression with elastic net regularization based on the administration of citalopram, PGDT, and risk factors for developing PGD.

Results: Three response trajectories were identified: lesser severity responders (60 %, n = 200), greater severity responders (18.02 %, n = 60), and non-responders (21.92 %, n = 73). Significant differences between greater severity responders and non-responders emerged by Week 8, persisting through the 6-month follow-up assessment. The elastic net model (AUC = 0.702; F1 = 0.777) indicated that higher baseline depression severity, grief-related functional impairment, and not receiving PGDT were associated with a decreased probability of response.

Limitations: An independent validation cohort of PGDT patients is needed to further study generalizability of findings.

Conclusions: Differential PGDT courses and the role of depression severity and grief-related functional impairment in treatment non-response were identified. These findings underscore the importance of determining clinical factors relevant to optimizing individual treatment strategies.

Keywords: Citalopram; Depression; Machine learning; Prolonged Grief Disorder; Psychotherapy; Trajectories.