Structural imaging predictors of ketamine response in treatment-resistant depression: a machine learning approach.
Linda Bryant, Laith Alexander, Sergio Mena, Yael Jacob, Jenna Jubeir, Mu Li, Philipp T Neukam, Laurel S Morris, James W. Murrough, Rebecca B Price, Nikolaos Koutsouleris, Mitul A. Mehta, Mario F Juruena, Fiona Coutts, Paris Alexandros Lalousis
Translational Psychiatry May 12, 2026 DOI: 10.1038/s41398-026-04085-4 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Observational cohort Peer reviewed |
|---|---|
| Sample size | 99 |
| Population | Adults with treatment-resistant depression |
| Intervention | Ketamine |
| Dose | 0.5 mg/kg |
| Duration | Single infusion, response assessed 24 h post-infusion |
| Topics | Depression Esketamine Ketamine |
| Key findings | A support vector classifier using pre-treatment structural MRI data predicted ketamine response with 72% balanced accuracy in the discovery sample and 60% in external validation, with frontal gray matter volume predicting response and cerebellar volume predicting non-response. |
Abstract
Ketamine has demonstrated rapid antidepressant efficacy in treatment-resistant depression (TRD), but clinical decision-making is challenging due to variability in individual response. Current trial-and-error prescribing practices may expose patients to ineffective treatment and avoidable adverse effects, underscoring the need for reliable predictive tools to optimize treatment selection and support personalized, evidence-based care. We developed a machine-learning model (support vector classifier) to predict antidepressant response to ketamine using pre-treatment structural MRI data. The model was trained on 99 adults with TRD given a single intravenous ketamine infusion (0.5 mg/kg). Clinical response was defined as a ≥50% reduction in MADRS scores 24 h post-infusion. Internal validation used repeated nested cross-validation, and generalizability was tested in two independent ketamine-treated cohorts (n = 51) and a saline-treated control group (n = 49). Among ketamine-treated participants, 52 (52.5%) responded to treatment. The model achieved a balanced accuracy of 72.2% (sensitivity = 72.3%, specificity = 73.1%, AUC = 0.72) in the discovery sample and 60.0% (p = 0.01, AUC = 0.65) in external validation. Greater gray matter volume in frontal regions predicted response, whereas greater cerebellar volume predicted non-response. Performance dropped to chance in the saline cohort (BAC = 41.1%, AUC = 0.45), supporting pharmacologic specificity. These findings present the first machine-learning model for the prediction of ketamine response in TRD using structural neuroimaging and highlight its potential utility for stratified treatment planning and biomarker-informed interventions while providing mechanistic insight into neuroanatomical predictors of antidepressant response.
Comparable studies
Other observational and cohort studies on ketamine for depression, most cited first.
| Study | Year | Design | Participants |
|---|---|---|---|
| Concomitant BDNF and sleep slow wave changes indicate ketamine-induced plasticity in major depressive disorder Patients with treatment-resistant major depressive disorder | 2012 | Observational cohort | n = 30 |
| Altered peripheral immune profiles in treatment-resistant depression: response to ketamine and prediction of treatment outcome Healthy controls and actively depressed patients with treatment-resistant depression... | 2017 | Observational cohort | n = 59 |
| Clinical Predictors of Ketamine Response in Treatment-Resistant Major Depression Treatment-resistant inpatients with DSM-IV-TR-diagnosed major depressive disorder or... | 2014 | Post hoc analysis of pooled data from four studies | n = 108 |
| An investigation of amino-acid neurotransmitters as potential predictors of clinical improvement to ketamine in depression Drug-free patients with major depressive disorder | 2011 | Observational cohort | n = 14 |
| Efficacy of ketamine therapy in the treatment of depression Drug-free/naïve men with severe depression, no history of psychotic disorder, head... | 2019 | Observational cohort | n = 25 |