Breaking Update: Here’s a clear explanation of the latest developments related to Breaking News:Novel Biomarkers Improve Depression Diagnosis Accuracy – EMJ– What Just Happened and why it matters right now.
RESEARCHERS reported that new transcranial magnetic stimulation (TMS) biomarkers, combined with machine learning, accurately distinguished individuals with major depressive disorder (MDD) from healthy controls, addressing a long-standing gap in objective psychiatric diagnostics.
MDD is one of the leading causes of disability globally and remains diagnosed solely through clinical assessment and patient-reported symptoms. Despite advances in neuroimaging and genetics, no validated biological marker has yet entered routine clinical practice.
The new study evaluated whether novel TMS biomarkers derived from cortical excitability could improve diagnostic classification of MDD. TMS is a non-invasive technique that uses magnetic pulses to stimulate specific brain regions and assess neurophysiological responses. It is already used therapeutically for treatment-resistant depression, making its potential diagnostic value especially attractive.
TMS Biomarkers Reveal Depression-Specific Brain Changes
Investigators analysed motor-evoked potentials (MEPs) recorded during TMS of the right primary motor cortex in twenty-six unmedicated patients with MDD and seventeen never-depressed controls. Two newly developed TMS-derived cortical excitability metrics were calculated from peak-to-peak MEP amplitudes. These metrics were designed to capture subtle alterations in neuronal responsiveness that traditional MEP measures may overlook.
A Gradient Boosting machine learning classifier was trained using raw MEPs alone, the novel TMS biomarkers alone, and a combined dataset. While raw MEPs were not predictive of diagnosis, both new metrics significantly improved classification performance. When combined with conventional MEP data, the model achieved 83.3% overall accuracy and 82.3% balanced accuracy in identifying MDD.
These findings suggested that the new metrics captured neurophysiological signatures associated with depression that standard measures failed to detect.
Clinical Implications and Future Directions
The findings should be interpreted considering several limitations. The novel TMS-derived metrics are based on MEPs, which provide only an indirect proxy of cortical excitability and may oversimplify the complex neurobiological mechanisms underlying depression.
The small sample size and lack of external validation also limit generalisability, highlighting the need for larger studies to test performance across diverse populations and depressive subtypes.
Nevertheless, the results supported the potential of TMS biomarkers as candidate tools for objective diagnosis and, eventually, personalised treatment selection. If validated, they could complement clinical assessment and help stratify patients more effectively.
Future studies should also examine whether these measures distinguish MDD from other psychiatric conditions or capture broader, transdiagnostic synaptic dysfunction.
Reference
López Pereyra, S et al. Novel TMS-derived metrics enable machine learning classification of major depressive disorder. NPP—Digit Psychiatry Neurosci. 2026; DOI:10.1038/s44277-025-00053-w.