Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression

Abstract Identifying predictors of treatment response to repetitive transcranial magnetic stimulation (rTMS) remain elusive in treatment-resistant depression (TRD). Leveraging electronic medical records (EMR), this retrospective cohort study applied supervised machine learning (ML) to sociodemograph...

Full description

Saved in:
Bibliographic Details
Main Authors: Lindsay L. Benster, Cory R. Weissman, Federico Suprani, Kamryn Toney, Houtan Afshar, Noah Stapper, Vanessa Tello, Louise Stolz, Mohsen Poorganji, Zafiris J. Daskalakis, Lawrence G. Appelbaum, Jordan N. Kohn
Format: Article
Language:English
Published: Nature Publishing Group 2025-04-01
Series:Translational Psychiatry
Online Access:https://doi.org/10.1038/s41398-025-03380-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850225738349805568
author Lindsay L. Benster
Cory R. Weissman
Federico Suprani
Kamryn Toney
Houtan Afshar
Noah Stapper
Vanessa Tello
Louise Stolz
Mohsen Poorganji
Zafiris J. Daskalakis
Lawrence G. Appelbaum
Jordan N. Kohn
author_facet Lindsay L. Benster
Cory R. Weissman
Federico Suprani
Kamryn Toney
Houtan Afshar
Noah Stapper
Vanessa Tello
Louise Stolz
Mohsen Poorganji
Zafiris J. Daskalakis
Lawrence G. Appelbaum
Jordan N. Kohn
author_sort Lindsay L. Benster
collection DOAJ
description Abstract Identifying predictors of treatment response to repetitive transcranial magnetic stimulation (rTMS) remain elusive in treatment-resistant depression (TRD). Leveraging electronic medical records (EMR), this retrospective cohort study applied supervised machine learning (ML) to sociodemographic, clinical, and treatment-related data to predict depressive symptom response (>50% reduction on PHQ-9) and remission (PHQ-9 < 5) following rTMS in 232 patients with TRD (mean age: 54.5, 63.4% women) treated at the University of California, San Diego Interventional Psychiatry Program between 2017 and 2023. ML models were internally validated using nested cross-validation and Shapley values were calculated to quantify contributions of each feature to response prediction. The best-fit models proved reasonably accurate at discriminating treatment responders (Area under the curve (AUC): 0.689 [0.638, 0.740], p < 0.01) and remitters (AUC 0.745 [0.692, 0.797], p < 0.01), though only the response model was well-calibrated. Both models were associated with significant net benefits, indicating their potential utility for clinical decision-making. Shapley values revealed that patients with comorbid anxiety, obesity, concurrent benzodiazepine or antipsychotic use, and more chronic TRD were less likely to respond or remit following rTMS. Patients with trauma and former tobacco users were more likely to respond. Furthermore, delivery of intermittent theta burst stimulation and more rTMS sessions were associated with superior outcomes. These findings highlight the potential of ML-guided techniques to guide clinical decision-making for rTMS treatment in patients with TRD to optimize therapeutic outcomes.
format Article
id doaj-art-dbbd7140be5a4dad8b9ae72a9f4c0e22
institution OA Journals
issn 2158-3188
language English
publishDate 2025-04-01
publisher Nature Publishing Group
record_format Article
series Translational Psychiatry
spelling doaj-art-dbbd7140be5a4dad8b9ae72a9f4c0e222025-08-20T02:05:16ZengNature Publishing GroupTranslational Psychiatry2158-31882025-04-011511910.1038/s41398-025-03380-wPredictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depressionLindsay L. Benster0Cory R. Weissman1Federico Suprani2Kamryn Toney3Houtan Afshar4Noah Stapper5Vanessa Tello6Louise Stolz7Mohsen Poorganji8Zafiris J. Daskalakis9Lawrence G. Appelbaum10Jordan N. Kohn11Department of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaSection of Psychiatry, Department of Medical Sciences and Public Health, University of CagliariMorehouse School of MedicineDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaDepartment of Psychiatry, University of CaliforniaHerbert Wertheim School of Public Health and Human Longevity Science, University of CaliforniaAbstract Identifying predictors of treatment response to repetitive transcranial magnetic stimulation (rTMS) remain elusive in treatment-resistant depression (TRD). Leveraging electronic medical records (EMR), this retrospective cohort study applied supervised machine learning (ML) to sociodemographic, clinical, and treatment-related data to predict depressive symptom response (>50% reduction on PHQ-9) and remission (PHQ-9 < 5) following rTMS in 232 patients with TRD (mean age: 54.5, 63.4% women) treated at the University of California, San Diego Interventional Psychiatry Program between 2017 and 2023. ML models were internally validated using nested cross-validation and Shapley values were calculated to quantify contributions of each feature to response prediction. The best-fit models proved reasonably accurate at discriminating treatment responders (Area under the curve (AUC): 0.689 [0.638, 0.740], p < 0.01) and remitters (AUC 0.745 [0.692, 0.797], p < 0.01), though only the response model was well-calibrated. Both models were associated with significant net benefits, indicating their potential utility for clinical decision-making. Shapley values revealed that patients with comorbid anxiety, obesity, concurrent benzodiazepine or antipsychotic use, and more chronic TRD were less likely to respond or remit following rTMS. Patients with trauma and former tobacco users were more likely to respond. Furthermore, delivery of intermittent theta burst stimulation and more rTMS sessions were associated with superior outcomes. These findings highlight the potential of ML-guided techniques to guide clinical decision-making for rTMS treatment in patients with TRD to optimize therapeutic outcomes.https://doi.org/10.1038/s41398-025-03380-w
spellingShingle Lindsay L. Benster
Cory R. Weissman
Federico Suprani
Kamryn Toney
Houtan Afshar
Noah Stapper
Vanessa Tello
Louise Stolz
Mohsen Poorganji
Zafiris J. Daskalakis
Lawrence G. Appelbaum
Jordan N. Kohn
Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
Translational Psychiatry
title Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
title_full Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
title_fullStr Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
title_full_unstemmed Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
title_short Predictive modeling of response to repetitive transcranial magnetic stimulation in treatment-resistant depression
title_sort predictive modeling of response to repetitive transcranial magnetic stimulation in treatment resistant depression
url https://doi.org/10.1038/s41398-025-03380-w
work_keys_str_mv AT lindsaylbenster predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT coryrweissman predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT federicosuprani predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT kamryntoney predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT houtanafshar predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT noahstapper predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT vanessatello predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT louisestolz predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT mohsenpoorganji predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT zafirisjdaskalakis predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT lawrencegappelbaum predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression
AT jordannkohn predictivemodelingofresponsetorepetitivetranscranialmagneticstimulationintreatmentresistantdepression