强化学习用于难治性抑郁症重复经颅磁刺激方案选择的研究
Reinforcement learning for repetitive transcranial magnetic stimulation protocol selection in treatment-resistant depression
本研究探索强化学习算法是否能基于常规临床数据推荐与症状改善相关的单次rTMS方案。利用1609名成人2023年1月至2025年6月在19个诊所组接受rTMS治疗的电子健康记录数据,在370名预留诊所患者中,与算法推荐相符的治疗决策关联着下一次PHQ-9评分改善增加0.788分(95% CI: 0.634–0.940)。
- Article
- Open access
- Published: 19 October 2026
- Jason B. Gibbons ORCID: orcid.org/0000-0002-1724-68971,
- Nicolas Leenaerts2,
- Shan H. Siddiqi3,
- Susan A. Murphy2,4,
- Loreen Straub1,
- David B. Hathaway3,
- Jie Yang1,
- Alejandro G. Szmulewicz5,
- Meekang Sung1,
- Rajendra Aldis6,
- Jacob C. Jameson7,
- Richard Wyss1,
- Rachel Wood8,
- Matthew Ruble8,
- Cason Elliott8,
- Denise H. Mulcahy8,
- Stanley Lyndon3 na1 &
- …
- Philip S. Wang1 na1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
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.
Funding
This work was supported by the National Institute on Drug Abuse under award 1K01DA061975 and the National Institute of Mental Health under award 1UG3MH141096-01. The funders had no role in study design, analysis, or the decision to submit.
Author information
Author notes
These authors jointly supervised this work: Stanley Lyndon, Philip S. Wang.
Authors and Affiliations
Division of Pharmacoepidemiology & Pharmacoeconomics, Mass General Brigham, Harvard Medical School, Boston, MA, USA
Jason B. Gibbons, Loreen Straub, Jie Yang, Meekang Sung, Richard Wyss & Philip S. Wang
Department of Statistics, Harvard University, Cambridge, MA, USA
Nicolas Leenaerts & Susan A. Murphy
Department of Psychiatry, Mass General Brigham, Harvard Medical School, Boston, MA, USA
Shan H. Siddiqi, David B. Hathaway & Stanley Lyndon
Department of Computer Science, Harvard University, Cambridge, MA, USA
Susan A. Murphy
Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA
Alejandro G. Szmulewicz
Department of Psychiatry, Cambridge Health Alliance, Cambridge, MA, USA
Rajendra Aldis
Department of Health Policy, Harvard Medical School, Boston, MA, USA
Jacob C. Jameson
Discovery Behavioral Health, Irvine, CA, USA
Rachel Wood, Matthew Ruble, Cason Elliott & Denise H. Mulcahy
Authors
- Jason B. Gibbons
- Nicolas Leenaerts
- Shan H. Siddiqi
- Susan A. Murphy
- Loreen Straub
- David B. Hathaway
- Jie Yang
- Alejandro G. Szmulewicz
- Meekang Sung
- Rajendra Aldis
- Jacob C. Jameson
- Richard Wyss
- Rachel Wood
- Matthew Ruble
- Cason Elliott
- Denise H. Mulcahy
- Stanley Lyndon
- Philip S. Wang
Corresponding author
Correspondence to Jason B. Gibbons.
Ethics declarations
Competing interests
Jason B. Gibbons has a financial interest in Adaptive Testing Technologies, a company that develops online mental and behavioral health assessment tools. Dr. Gibbons’ interests were reviewed and are managed by BWH and Mass General Brigham in accordance with their conflict-of-interest policies. All other authors declare no competing financial or nonfinancial interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Gibbons, J.B., Leenaerts, N., Siddiqi, S.H. et al. Reinforcement learning for repetitive transcranial magnetic stimulation protocol selection in treatment-resistant depression. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03417-4
Received: 04 June 2026
Accepted: 05 October 2026
Published: 19 October 2026
DOI: https://doi.org/10.1038/s41746-026-03417-4
来源:Nature 健康护理主题 · nature.com