npj Digital Medicine· 2026Q1
Reinforcement learning for repetitive transcranial magnetic stimulation protocol selection in treatment-resistant depression
- 0citations
- Q1SCImago
- 2026year
Short summary
A reinforcement learning algorithm trained on clinical data recommended repetitive transcranial magnetic stimulation (rTMS) protocols that led to a 0.788-point greater improvement in Patient Health Questionnaire-9 scores compared to standard clinician choices.
AI-generated from the title and abstract; the full text is not read.
Key points
- Reinforcement learning (RL) algorithm trained on routine clinical data to recommend rTMS protocols.
- Algorithm recommendations were associated with 0.788 points greater next-session Patient Health Questionnaire-9 improvement in held-out patients (n=370).
- Following every recommendation was projected to produce 3.22 points of additional improvement.
- Findings suggest RL can identify session-level rTMS treatment patterns linked to greater symptom improvement.
AI-generated from the title and abstract; the full text is not read.
Abstract
Repetitive transcranial magnetic stimulation (rTMS), including intermittent theta-burst stimulation (iTBS), is an established treatment for treatment-resistant depression, but clinicians lack evidence-based guidance for session-level choices among stimulation type, intensity, and laterality. In this study, we investigated whether a reinforcement learning (RL) algorithm trained on routine clinical data could recommend session-level rTMS protocols associated with greater symptom improvement using electronic health record data from 1609 adults treated with rTMS between January 2023 and June 2025 across 19 clinic groups. Among 370 patients from held-out clinics, treatment decisions matching algorithm recommendations were associated with 0.788 points greater next-session Patient Health Questionnaire-9 improvement than treatments that differed (95% CI: 0.634–0.940). Following every recommendation was projected to produce 3.22 points of additional improvement (95% CI: 2.72–3.75). These findings suggest RL can find treatment patterns associated with greater next-session improvement and potentially meaningful improvement accumulated across a treatment episode.
The authors' abstract, as published at the source. npj Digital Medicine, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Neurology (Neuroscience)
NeurologyNeuroscience