Accurate and Interpretable Prediction of Antidepressant Treatment Response from Receptor-informed Neuroimaging
Hanna M. Tolle, Andrea I. Luppi, Timothy Lawn, Leor Roseman, David Nutt, Robin Carhart-Harris, Pedro A. M. Mediano
bioRxiv (Cold Spring Harbor Laboratory) preprint DOI: 10.1101/2025.07.02.662710 (opens in new tab)
Summary
AI-generated from the abstractA geometric deep learning model called graphTRIP predicts post-treatment depression severity from pretreatment clinical and brain imaging data. Trained on a clinical trial comparing psilocybin and escitalopram, it achieves strong predictive accuracy (r = 0.75) and generalizes to an independent dataset. The model links better outcomes to reduced functional coupling within serotonin systems and broader serotonergic integration with sensory-motor networks. Causal analysis shows a group-level advantage of psilocybin over escitalopram but identifies individuals with specific stress-related neuromodulatory profiles who may benefit more from escitalopram, advancing precision medicine and biomarker discovery in depression.
Study at a glance
| Characteristics | Clinical trial |
|---|---|
| Population | Patients with major depressive disorder |
| Interventions | Psilocybin Escitalopram |
| Topics | Psychedelic-assisted therapy |
| Keywords | Depression treatment Antidepressant therapy Mdd treatment Psilocybin therapy |
| Citations | 1 |
| Registration | NCT03429075 |
| Key finding | The graphTRIP model accurately predicts post-treatment depression severity using pretreatment data and identifies that reduced functional coupling within serotonin systems and broader serotonergic integration with sensory-motor networks are linked to better outcomes, with psilocybin showing a group-level advantage over escitalopram but escitalopram benefiting individuals with specific stress-related neuromodulatory profiles. |
Abstract
Conventional antidepressants show moderate efficacy in treating major depressive disorder. Psychedelic-assisted therapy holds promise, yet individual responses vary, underscoring the need for predictive tools to guide treatment selection. Here, we present graphTRIP (graph-based Treatment Response Interpretability and Prediction) – a geometric deep learning architecture that enables three advances: 1) accurate prediction of post-treatment depression severity using only pretreatment clinical and neuroimaging data; 2) identification of robust, patient-specific biomarkers; and 3) causal analysis of treatment effects and underlying mechanisms. Trained on data from a clinical trial comparing psilocybin and escitalopram (NCT03429075), graphTRIP achieves strong predictive accuracy (r = 0.75, p < 10−8), and generalises both to an independent dataset and across brain atlases. The model links better outcomes to reduced functional coupling within serotonin systems, and broader serotonergic integration with sensory-motor networks. Finally, causal analysis reveals a group-level advantage of psilocybin over escitalopram, but also identifies individuals with specific stress-related neuromodulatory profiles who may benefit more from escitalopram. Overall, this work advances precision medicine and biomarker discovery in depression.