Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 5:28:281-293.
doi: 10.1016/j.csbj.2025.07.051. eCollection 2025.

An artificial intelligence-based platform for personalized predictions of Metacognitive Training effectiveness

Caroline König  1 , Pedro Copado  1 , Alfredo Vellido  1 , Àngela Nebot  1 , Cecilio Angulo  2 , Maria Lamarca  3   4   5 , Vanessa Acuña  6 , Fabrice Berna  7 , Steffen Moritz  8 , Łukasz Gawęda  9 , Susana Ochoa  3   4
Affiliations

An artificial intelligence-based platform for personalized predictions of Metacognitive Training effectiveness

Caroline König et al. Comput Struct Biotechnol J. .

Abstract

This study introduces a machine learning (ML)-based platform aimed at predicting the effectiveness of Metacognitive Training (MCT). The platform is meant to function as an experimental prototype in the scope of a clinical research project for a decision support system to assist clinicians in tailoring treatment plans for patients with psychosis. It integrates eight ML models to evaluate MCT effectiveness under a wide range of mental health questionnaires to assess a broad spectrum of psychological symptoms. By incorporating diverse measures, the platform aims to capture a comprehensive understanding of patient profiles, enabling more precise and tailored predictions for treatment personalization. Furthermore, the transparency requirements for artificial intelligence (AI) systems, as outlined in the AI Act regulation of the European Union, are addressed through the implementation of explainable AI models, using post-hoc explanations based on SHAP analysis for each predictive model. Ethical concerns related to ensuring gender-neutral behavior in the system are tackled by conducting a disparate impact analysis, which evaluates biases present in the models enhancing the system's accountability and alignment with ethical and regulatory standards.

Keywords: Explainable artificial intelligence; Fairness; Feature selection; Mental health; Metacognitive Training; Personalized medicine.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest related to the research, authorship, and publication of this article.

Figures

None
Graphical abstract
Fig. 1
Fig. 1
Overview of development tasks.
Fig. 2
Fig. 2
Overview of the system process.
Fig. 3
Fig. 3
Overview of systems and stakeholders.
Fig. 4
Fig. 4
Performance of LR and RF models for the target variables for feature relevance analysis measured as RMSE for regression (left) and accuracy for classification (right).
Fig. 5
Fig. 5
GUI of the prediction result page. The upper part (1) shows the predictions in a tabular format. Part 2 (middle) displays the AI ACT related disclaimer. Part 3 is a graphical representation of the ratio of change. The bottom part (4) highlights the indicators with the lowest improvement.
Fig. 6
Fig. 6
Waterfall plot of the SHAP values to explain the prediction of the PSYRATS delusions target.
See this image and copyright information in PMC

References

    1. Zhang S., Bamakan S.M.H., Qu Q., Li S. Learning for personalized medicine: a comprehensive review from a deep learning perspective. IEEE Rev Biomed Eng. 2018;12:194–208. - PubMed
    1. Egger J., Gsaxner C., Pepe A., Pomykala K.L., Jonske F., Kurz M., et al. Medical deep learning—a systematic meta-review. Comput Methods Programs Biomed. 2022;221 - PubMed
    1. Fusar-Poli P., Schultze-Lutter F. Predicting the onset of psychosis in patients at clinical high risk: practical guide to probabilistic prognostic reasoning. BMJ Ment Health. 2016;19:10–15. - PMC - PubMed
    1. Dwyer D.B., Falkai P., Koutsouleris N. Machine learning approaches for clinical psychology and psychiatry. Annu Rev Clin Psychol. 2018;14:91–118. - PubMed
    1. Stumpp N.E., Sauer-Zavala S. Evidence-based strategies for treatment personalization: a review. Cogn Behav Pract. 2022;29:902–913.

LinkOut - more resources