Sex differences in rTMS treatment response: A deep learning-based EEG investigation

Area of Science:

• Neuroscience
• Psychiatry
• Artificial Intelligence

Background:

• Major Depressive Disorder (MDD) is a prevalent mental health condition with variable treatment responses.
• Repetitive transcranial magnetic stimulation (rTMS) is an emerging neuromodulation technique for MDD treatment.
• Understanding factors influencing rTMS efficacy, including sex differences, is crucial for personalized treatment.

Purpose of the Study:

• To investigate sex-specific differences in patient response to rTMS for MDD.
• To develop and validate a deep learning (DL) model for predicting rTMS treatment response.
• To identify potential sex-specific antidepressant effects of rTMS.

Main Methods:

• A novel convolutional LSTM-based deep learning pipeline was developed.
• The model was trained to classify 50 MDD patients (25 female, 25 male) based on rTMS treatment response.
• Five distinct classification models were generated to analyze sex-specific and combined response patterns.

Main Results:

• The DL models achieved high overall test accuracies, ranging from 93.3% to 99.2%.
• Specific models demonstrated excellent predictive performance for female responders (95.2%) and male responders (99.2%).
• A model predicting response in both sexes combined also showed high accuracy (96.6%).

Conclusions:

• The developed DL approach shows significant potential for predicting rTMS treatment response in MDD patients.
• Results suggest the presence of sex-specific effects influencing rTMS antidepressant efficacy.
• This approach could facilitate more personalized and effective rTMS interventions for MDD.