An artificial intelligence-based platform for personalized predictions of Metacognitive Training effectiveness
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.
Authors
- Łukasz Gawęda (ORCID: https://orcid.org/0000-0001-6578-1846)
- Pedro Copado (ORCID: https://orcid.org/0000-0003-4219-5056)
- Vanessa Acuña (ORCID: https://orcid.org/0009-0009-9409-2244)
- Susana Ochoa
- Fabrice Berna
- Caroline König (ORCID: https://orcid.org/0000-0002-7543-8686)
- Àngela Nebot (ORCID: https://orcid.org/0000-0002-4621-8262)
- Alfredo Vellido (ORCID: https://orcid.org/0000-0002-9843-1911)
- Cecilio Ángulo (ORCID: https://orcid.org/0000-0001-9589-8199)
- Steffen Moritz (ORCID: https://orcid.org/0000-0001-8601-0143)
- María Lamarca (ORCID: https://orcid.org/0009-0009-6426-560X)
Institutions
- Universitat Autònoma de Barcelona (ES)
- Inserm (FR)
- Universität Hamburg (DE)
- Instituto de Salud Carlos III (ES)
- Centro de Investigación Biomédica en Red de Salud Mental (ES)
- University Medical Center Hamburg-Eppendorf (DE)
- Institute of Psychology (PL)
- Parc Sanitari Sant Joan de Déu (ES)
- Université de Strasbourg (FR)
- University of Valparaíso (CL)
- Universitat Politècnica de Catalunya (ES)
- Polish Academy of Sciences (PL)
Publication Details
- Journal
- Computational and Structural Biotechnology Journal
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1016/j.csbj.2025.07.051
- Citations
- 2
- Primary Topic
- Mental Health Research Topics
- Type
- article
- Field-Weighted Citation Impact
- 4.24
Funders
- European Commission
- Agence Nationale de la Recherche
- Bundesministerium für Bildung und Forschung
- Agencia Nacional de Investigación y Desarrollo
- Instituto de Salud Carlos III
- Narodowe Centrum Badań i Rozwoju