New Delhi: An analysis of electric signals from the brain and stomach, along with clinical symptoms, may help predict outcomes within a week or 10 days of starting an antidepressant treatment, researchers from the Indian Institute of Technology Kanpur (IIT-K) and Ganesh Shankar Vidyarthi Memorial Medical College have found.
The findings, published in the journal Frontiers in Psychiatry, could enable an earlier assessment of a patient’s response to the treatment, as opposed to the conventional four to six period typically required, they said.
Depression is a mental health disorder marked by persistent feelings of sadness and hopelessness and a disinterest in activities. Studies have shown that up to 30 per cent of the affected population may not respond to an adequate pharmacological therapy.
“Our study shows that objective non-invasive brain and gut electrophysiological signals collected in about the first week of treatment already contain valuable information about treatment response to precisely guide the intervention,” author Pragathi Priyadharsini Balasubramani, assistant professor at IIT-K’s department of cognitive science, said.
Electrical activity in the brain and stomach using electroencephalography (EEG) and electrogastrography (EGG) was examined, respectively, and analysed together with clinical symptom data.
The signals, recorded within the first 7-10 days of initiating treatment, were found to help identify patients unlikely to respond to an antidepressant.
“We found that different symptom profiles were associated with distinct patterns of brain and gut physiology linked to treatment outcomes.
“Recognising these biological subtypes helps explain why patients respond differently to the same medication and facilitates personalised treatment strategies,” first author Amal Jude Ashwin Francis, a PhD scholar at IIT-K’s department of cognitive science, said.
The researchers looked at 206 participants, including 144 treatment-naive patients with depression. EEG and EGG signals were recorded at the start of treatment and again about a week later.
The predictive model identified patients unlikely to respond to an antidepressant treatment with an 84 per cent sensitivity (correctly identifying a non-responder) and a 78 per cent specificity (correctly identifying someone not a non-responder) during development.
When tested on an independent patient cohort, the model achieved a 77.3 per cent overall accuracy, with an 80 per cent specificity and 71.4 per cent sensitivity in identifying non-responders, the researchers said.
“Our findings suggest that combining brain and gut electrophysiological markers with clinical phenotyping offers a promising, scalable approach to personalise depression treatment,” the authors wrote.
“This approach could guide clinicians in developing more effective and tailored medication strategies, ultimately improving patient outcomes,” they said.
Further studies across larger and more diverse patient groups will be needed to validate the approach, the team added.
