MUSC researchers used machine learning on fMRI scans to predict which smokers would benefit from repetitive transcranial magnetic stimulation (rTMS) for quitting smoking.
Key Details
- 1MUSC study combines machine learning and fMRI to personalize rTMS for smoking cessation.
- 242 participants took part in an earlier study, split into real vs sham TMS groups.
- 3The salience network's connectivity in the brain, analyzed by AI, correlated best with positive rTMS outcomes.
- 4Machine learning enabled predictions of individual responsiveness to rTMS based on brain network analysis.
- 5Study published in Brain Connectivity; NIH grant support cited.
- 6The research establishes groundwork for precision neuromodulation and larger future trials.
Why It Matters
This study demonstrates how imaging AI can enhance precision medicine by analyzing fMRI scans to tailor neuromodulation therapies. The approach could extend to other substance use disorders, highlighting a broader potential impact for radiology-based AI tools.
Source
EurekAlert
Related News
•EurekAlert
AI Method Automates X-ray Absorption Spectroscopy for Material Analysis
Researchers have developed an AI-based approach to automate and enhance the analysis of X-ray absorption spectroscopy (XAS) data for materials science.
•EurekAlert
BraDiPho: New 3D AI Atlas Integrates Brain Dissections with MRI
Researchers have developed BraDiPho, a tool that merges ex-vivo photogrammetric brain dissection data with in-vivo MRI tractography using AI.
•EurekAlert
AI Maps Genetic Factors Shaping the Corpus Callosum via MRI Scans
USC researchers used AI to analyze MRI scans and uncover the genetic architecture of the brain's corpus callosum.