EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Can we improve prediction of psychotherapy outcomes through pretraining with simulated data?

Niklas Jacobs, Manuel C Voelkle, Norbert Kathmann, Kevin Hilbert

Frontiers in Psychology · 04.11.2026 · 17

DOI: 10.3389/fpsyg.2026.1866418 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Psychology, online erschienen am 04.11.2026. Verfasst von Niklas Jacobs und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, Faculty of Health, Health and Medical University Erfurt, Erfurt, Germany. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

In the context of personalized medicine, machine learning (ML) algorithms are gaining popularity. These algorithms require substantial information, which can be acquired effectively through the use of previously gathered data. Open data and the utilization of synthetization techniques have been proposed to address this need. In this article, we propose and evaluate an alternative approach that uses additional simulated data based on summary statistics published in the literature.

Method

The simulated data were used to pretrain random forests, which were afterward fine-tuned using a real dataset. Here, these terms describe combining trees trained separately on simulated and real data, without updating pretrained trees. We compared the predictive performance of the new approach with that of random forests trained only on real data. A Monte Carlo cross-validation (MCCV) framework with 100 iterations was employed to investigate the significance and stability of the results. Since the first study yielded inconclusive results, a second study with an improved methodology (i.e., systematic information extraction and a different prediction outcome) was conducted.

Results

In Study 1, some pretrained random forests descriptively outperformed the standard random forest. However, this improvement was not significant ( t (99) = 0.89, p = 0.19). Contrary to expectations, in Study 2, the random forest trained only on the real data outperformed the pretrained random forests.

Conclusion

We conclude with a discussion of challenges, such as the scarcity of informative publications, and recommendations for future research.

Schlagwörter

Stichwörter der Autor:innen

fine tuningmachine learningoutcome predictionpretrainingpsychotherapy

Autor:innen und Institutionen

  • Department of Psychology, Faculty of Health, Health and Medical University Erfurt, Erfurt, Germany.
  • Department of Psychology, Faculty of Life Sciences, Humboldt-Universität zu Berlin, Berlin, Germany.
  • Department of Psychology, Faculty of Economics and Behavioral Sciences, University of Freiburg, Freiburg im Breisgau, Germany.

Zitieren

APA

Jacobs, N., Voelkle, M. C., Kathmann, N., & Hilbert, K. (2026). Can we improve prediction of psychotherapy outcomes through pretraining with simulated data?. Frontiers in Psychology, 17. https://doi.org/10.3389/fpsyg.2026.1866418

Vancouver

Jacobs N, Voelkle MC, Kathmann N, Hilbert K. Can we improve prediction of psychotherapy outcomes through pretraining with simulated data?. Frontiers in Psychology. 2026;17. doi:10.3389/fpsyg.2026.1866418

BibTeX
@article{Jacobs2026,
  author = {Jacobs, Niklas and Voelkle, Manuel C and Kathmann, Norbert and Hilbert, Kevin},
  title = {Can we improve prediction of psychotherapy outcomes through pretraining with simulated data?},
  journal = {Frontiers in Psychology},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpsyg.2026.1866418}
}
Kostenlos starten →