301. Multimodal MRI signatures predict ketamine antidepressant response in treatment-resistant depression: a machine-learning analysis of independent clinical trials
P-C Wu, T-P Su, C-T Li, Y-M Bai, M-H Chen · 2026
Read 301. Multimodal MRI signatures predict ketamine antidepressant response in treatment-resistant depression: a machine-learning analysis of independent clinical trials by P-C Wu, T-P Su, C-T Li, Y-M Bai, M-H Chen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13556379.txt.
Description
P-C Wu and four co-authors used machine learning in two thousand twenty-six to forecast who will respond to ketamine for stubborn depression. Ketamine acts fast, but responses vary widely, so a pre-treatment marker would help doctors choose. They drew data from two separate randomized trials, training on one and testing on the other.
Features joined resting brain connectivity, network graph measures, and brain structure. A nearest-neighbour classifier, tuned with careful feature picking and noise-based data boosting, hit about eighty-one percent accuracy on the unseen trial. It was especially good at spotting non-responders. Selected features centred on networks linking the thalamus, vision, and salience.
Catalog record
| CREATOR | P-C Wu, T-P Su, C-T Li, Y-M Bai, M-H Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |