ResearchAI Research

AI Predicts rTMS Depression Therapy Outcomes with High Accuracy

Wael Korani, Md Fahimul Kabir Chowdhury, Sadam AlQadi, Priyan Malarvizhi kumar, Reza Rostami, Reza Kazemi· July 28, 2026 View original

Summary

Researchers developed a deep learning classifier using EEG signals and a custom Convolutional Neural Network to predict the success of rTMS therapy for Major Depressive Disorder. The method achieved 93.60% accuracy, outperforming existing models and offering a computationally efficient solution for clinical use.

This study introduces an innovative approach to predict the effectiveness of repetitive transcranial magnetic stimulation (rTMS) therapy for major depressive disorder (MDD) using electroencephalogram (EEG) signals. The core of the method involves transforming EEG data into images using advanced time-frequency techniques, specifically Fourier-Bessel Series Expansion with Euclidean Distance (FBSE-ED). These processed EEG images are then fed into a lightweight, custom-designed Convolutional Neural Network (CNN). The model was trained and validated on private rTMS databases, demonstrating remarkable accuracy in predicting treatment outcomes. The proposed framework achieved a classification accuracy of 93.60% with the FBSE-ED representation, significantly surpassing traditional methods and more complex deep learning models. This efficient and interpretable system is designed for practical deployment in psychiatric clinics, aiming to support earlier and more targeted clinical decision-making.

Why it matters

This research offers a promising tool for clinicians to predict the success of rTMS therapy for depression early, enabling more personalized and effective treatment plans and potentially reducing the time and cost associated with ineffective treatments.

How to implement this in your domain

  1. 1Evaluate integrating AI-powered predictive analytics into clinical decision support systems for mental health.
  2. 2Collaborate with AI researchers to pilot similar EEG-based prediction models for other neurological or psychiatric treatments.
  3. 3Invest in secure data infrastructure to collect and process physiological signals like EEG for AI model training.
  4. 4Train clinical staff on the interpretation and application of AI-generated predictions in patient care.

Who benefits

HealthcarePharmaceuticalsMedical DevicesMental Health Services

Key takeaways

  • AI can accurately predict rTMS depression therapy outcomes using EEG signals.
  • The proposed CNN model with FBSE-ED representation achieved 93.60% accuracy.
  • This method offers a computationally efficient and interpretable solution for clinical deployment.
  • Early prediction can lead to more targeted and effective patient treatment plans.

Original post by Wael Korani, Md Fahimul Kabir Chowdhury, Sadam AlQadi, Priyan Malarvizhi kumar, Reza Rostami, Reza Kazemi

"arXiv:2607.22776v1 Announce Type: new Abstract: Repetitive transcranial magnetic stimulation (rTMS) is a non invasive therapy for Major Depressive Disorder (MDD). In this study, we generate images using two time frequency methods to represent EEG signals: Fourier-Bessel Series Ex…"

View on X

Originally posted by Wael Korani, Md Fahimul Kabir Chowdhury, Sadam AlQadi, Priyan Malarvizhi kumar, Reza Rostami, Reza Kazemi on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research

AI ResearchAI Engineering & DevTools

StageGuard Improves Sleep Staging by Enforcing Physiological Constraints

StageGuard is a new framework that enhances automated sleep staging by integrating physiology-informed priors, ensuring that deep learning models produce hypnograms that adhere to known biological rules. It significantly reduces physiologically implausible transitions and fragmentation while maintaining or improving accuracy.

Juntang Wang, Yihan Wang, Hao Wu, Jiayu Gao, Shixin Xu, Dongmian ZouJul 28, 2026
AI ResearchAI Engineering & DevToolsAI News & Tools

AI Model Improves Trustworthy Flood Prediction with Explainability

Researchers developed Context-Aware Concept Distillation (CACD), a framework that distills opaque Deep Learning models into interpretable, hydrology-aware surrogates for flood prediction. This method provides verifiable causal narratives required by disaster response authorities, achieving high fidelity and outperforming black-box baselines globally.

Eli Levinkopf, Efrat Morin, Claudia V. GoldmanJul 28, 2026
AI ResearchAI Engineering & DevTools

Diffusion Models' Generative Quality Gets Comprehensive Theoretical Analysis

This research provides a unified theoretical framework for understanding the generalization and convergence of score-based diffusion models. It decomposes the total generative error into four interpretable components, quantifying how training data, discretization, and optimization affect sample fidelity.

Jinshu Huang, Yiming Jiang, Chunlin WuJul 28, 2026