# Deep learning using electroencephalogram (EEG) data for diagnosing and predicting SSRI response in major depressive disorder

## TL;DR

This study uses deep learning on EEG data to diagnose depression and predict response to antidepressants, offering a more objective and personalized approach to treatment.

## Contribution

The novel application of deep learning to EEG data for both diagnosing MDD and predicting SSRI treatment response is presented.

## Key findings

- EEG-based deep learning models achieved 67.5% accuracy in detecting MDD and 79% accuracy in predicting SSRI response.
- Frontal and parietal alpha activity were identified as key EEG markers for both tasks.
- Model-guided SSRI selection could increase treatment response from 50% to 70%, with a number needed to treat of five.

## Abstract

Major Depression (MDD) is a potentially life-threatening condition that ranks among the diseases with the highest global burden. Despite its prevalence, current diagnostic methods remain largely subjective, and first-line treatments exhibit high rates of non-responders.

This study investigates the application of deep learning (DL) algorithms to electroencephalogram (EEG) data for the MDD-diagnosis and prediction of treatment outcomes following the administration of selective serotonin reuptake inhibitors (SSRIs), using six large, independent datasets with a total of n = 146 for healthy subjects and n = 203 for patients. DL models were trained on one portion of the datasets and tested on unseen data from different subjects. To interpret the classification features, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied.

The models achieve an average accuracy of 67.5% (best fold 70%) in distinguishing MDD patients from healthy controls and mean 79% accuracy (best fold 85%) in predicting SSRI responders. Key EEG markers for both classification tasks revealed by Grad-CAM include alpha activity in the frontal and parietal regions. Simulation of a clinical decision scenario for SSRI treatment selection indicates a number needed to treat (NNT) of five when using a model with 80% predictive accuracy, corresponding to an increase in treatment response from a 50% baseline to 70% with model-guided selection.Conclusion: These findings underscore the clinical potential of EEG-based DL models for stratified treatment in MDD, facilitating accurate therapy choices and reducing ineffective treatments. The results of the integration of objective neurophysiological markers into clinical psychiatry are indicating the potential for more personalized treatment allocation.

This study looked for better ways to diagnose major depression and choose the right treatment. Today, depression is often diagnosed through interviews, and many people do not respond to the first medicine they receive. We tested whether computer models could learn patterns in brain activity (Electroencephalogram -EEG) to identify depression and predict who will benefit from a common antidepressant. We trained deep-learning models on large EEG datasets and tested them on new subjects. The models could detect depression well and even more accurately predict treatment success. These results show that EEG-based computer tools may help doctors choose treatments more accurately and reduce the time patients spend on ineffective therapies.

Olbrich et al. apply deep-learning methods to EEG recordings to detect major depression and predict who will respond to SSRI treatment. They show that the models reach meaningful accuracy and identify key brain activity patterns, supporting the use of EEG-based tools for individualized treatment decisions.