Scientists at the University of Surrey have introduced a new technique that reads brain signals to identify the exact type of depression with a high degree of accuracy. The study reports achieving a 91 percent correct classification when distinguishing the specific depression subtype from other mood states, and the findings were published in Biomedical Signal Processing and Control.
Mixed anxiety and depressive disorder is a condition where symptoms of anxiety and depression appear together in roughly equal measures. Clinicians often face a tougher challenge here because the boundaries between anxiety and depressive symptoms can blur, leading to more intense manifestations and greater difficulty in selecting effective treatments. The International Classification of Diseases, 10th Revision ICD-10 names this condition mixed anxiety and depressive disorder, and clear diagnostic criteria remain elusive, which can complicate precise diagnosis and personalized care. In this landscape, timely identification and intervention are crucial to prevent lasting harm and to guide appropriate therapeutic strategies.
In the study, researchers recorded five minutes of electroencephalography EEG data from fifteen patients diagnosed with anxiety depressive disorder and nine with what researchers describe as typical depressive states. Brain activity was sampled at sixty-eight distinct sites, and machine learning models were employed to generate activity maps that differentiate the neurophysiological patterns of patients with anxious depression from those without it. This approach aimed to reveal objective biomarkers that clinicians could use to support diagnoses that are traditionally based on clinical interviews and self-reported symptoms.
The team observed that individuals with anxiety depressive disorder tended to show stronger electrical signals in the brain’s right hemisphere, a pattern that emerged more consistently when participants had their eyes closed during EEG recording. These findings suggest that certain resting-state brain dynamics may be linked to the co-occurring anxiety and depressive features in this subgroup of patients. The researchers emphasize that eye closure amplified the discriminative signals, pointing to the potential for refining EEG protocols to improve diagnostic accuracy in real-world settings.
Looking ahead, the investigators plan a series of follow-up experiments designed to optimize the method and broaden its applicability. The overarching goal is to help clinicians more reliably recognize anxiety depressive disorder, enabling quicker, more targeted care and reducing the risk of delayed treatment and its associated consequences. While the current results are promising, experts caution that larger studies across diverse populations are needed to validate the technique before it becomes a routine clinical tool. The research highlights how advances in brain signal analysis and machine learning can complement traditional assessment methods, offering a new layer of evidence to support decision-making in mental health care. This work is expected to contribute to a more nuanced and data-driven understanding of how anxiety and depression intersect, ultimately guiding more personalized treatment approaches for patients affected by this complex condition. Attribution: Biomedical Signal Processing and Control, University of Surrey researchers.