Moving beyond accuracy to overcome translational barriers in depression relapse prediction – Nature Mental Health

moving-beyond-accuracy-to-overcome-translational-barriers-in-depression-relapse-prediction-–-nature-mental-health
  • Comment
  • Published:

Nature Mental Health (2026) Cite this article

Subjects

This Comment argues for better consideration of additional factors, such as external validation, real-world feasibility, and clinical utility, to improve the translation of predictive models for relapse prediction in depression.

This is a preview of subscription content, access via your institution

Access options

Subscribe to this journal

Receive 12 digital issues and online access to articles

79,00 € per year

only 6,58 € per issue

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

39,95 €

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Simulated clinical consequences of varying decision thresholds for a relapse prediction model.

The alternative text for this image may have been generated using AI.

References

  1. Meehan, A. J. et al. Mol. Psychiatry 27, 2700–2708 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  2. Chekroud, A. M. et al. World Psychiatry 20, 154–170 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  3. Moriarty, A. S. et al. J. Affect. Disord. 265, 618–644 (2020).

    Article  PubMed  Google Scholar 

  4. Van Dijk, D. A. et al. J. Affect. Disord. 382, 68–84 (2025).

    Article  PubMed  Google Scholar 

  5. Riley, R. D. et al. Lancet Digit. 7, 100857 (2025).

    Article  Google Scholar 

  6. Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. G. M. Ann. Intern. Med. 162, 55–63 (2015).

    Article  PubMed  Google Scholar 

  7. Moons, K. G. M. et al. BMJ 388, e082505 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  8. Richter, M. et al. Mol. Psychiatry 1–8 (2025).

  9. Efthimiou, O. et al. BMJ 386, e078276 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  10. Moriarty, A. S. et al. Br. J. Psychiatry 221, 448–458 (2022).

    Article  PubMed  Google Scholar 

  11. Baldwin, H. et al. Brain Sci. 12, 934 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  12. Moriarty, A. S. et al. Health Expect. 27, e70059 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  13. Fitzgerald, M., Saville, B. R. & Lewis, R. J. JAMA 313, 409–410 (2015).

    Article  PubMed  Google Scholar 

Download references

Funding

T.H. was funded by the German Research Foundation (DFG SFB/TRR 393, project 521379614).

Author information

Author notes

  1. These authors contributed equally: Nils R. Winter and Marius Gruber.

Authors and Affiliations

  1. Institute for Translational Psychiatry, University of Münster, Münster, Germany

    Nils R. Winter, Marius Gruber, Tim Hahn & Jonathan Repple

  2. Institute for Machine Learning in Medicine with focus area psychiatry, University of Münster, Münster, Germany

    Nils R. Winter & Tim Hahn

  3. Goethe University Frankfurt, University Hospital, Department of Psychiatry, Psychosomatic Medicine and Psychotherapy, Frankfurt, Germany

    Marius Gruber & Jonathan Repple

  4. Goethe University Frankfurt, Cooperative Brain Imaging Center – CoBIC, Frankfurt, Germany

    Marius Gruber & Jonathan Repple

Authors

  1. Nils R. Winter
  2. Marius Gruber
  3. Tim Hahn
  4. Jonathan Repple

Corresponding author

Correspondence to Nils R. Winter.

Ethics declarations

Competing interests

J.R. received speaker’s honoraria from Janssen, Hexal, Neuraxpharm and Novartis. M.G. has received remuneration from Janssen for consultancy services. T.H. has received remuneration from SpringHealth for consultancy services.

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Winter, N.R., Gruber, M., Hahn, T. et al. Moving beyond accuracy to overcome translational barriers in depression relapse prediction. Nat. Mental Health (2026). https://doi.org/10.1038/s44220-026-00661-1

Download citation

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s44220-026-00661-1

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *