Machine Learning in Guiding rTMS Treatment for GWI-Related Headaches and Body Pain

The goal of this clinical trial is to create a machine learning algorithm to improve active repetitive transcranial magnetic stimulation (rTMS) treatments for veterans and/or active military personnel by alleviating Gulf War Illness related headaches and body pain (GWI-HAP). This study aims to develop and validate a Support Vector Machine (SVM) model that could replace the trial-and-error process by assessing functional connectivity provided by resting state functional magnetic resonance imaging (rs-fMRI) data to predict the most effective rTMS protocol for each person. All participants will be receiving active rTMS treatment. The main questions it intends to answer are: 1. Does the SVM model predict a more effective treatment response rate for predicted respondents undergoing active rTMS at the left dorsolateral prefrontal cortex (DLPFC) compared to predicted non-respondents? 2. Does the SVM model predict a more effective treatment response rate while undergoing active rTMS at the left dorsolateral prefrontal cortex (DLPFC) and left motor cortex (LMC) in predicted respondents compared to predicted non-respondents? Participants will undergo the following: 1. Receive a total of 13 active rTMS treatment sessions over 3-4 months. 2. Visit the clinic for a total of 15 visits for assessments, check ups, and treatments. 3. Keep a daily log of their headaches, muscle and joint pain throughout the study.

This description comes directly from the study's public registry record.

Albert Y Leung, MD  ·  8585528585  ·  ayleung@health.ucsd.edu

Caleb Lopez, BS  ·  8585528585  ·  caleb.lopez@va.gov

Always discuss trial participation with your own doctor first.

Get one email when the public record changes — results posted, or the study's status changes. Nothing else, ever.

We email about this public record only. Unsubscribe anytime with one click. Never medical advice.