An artificial intelligence-based platform for personalized predictions of Metacognitive Training effectiveness
König, Caroline (Intelligent Data Science and Artificial Intelligence Research Center)
Copado-Mendez, Pedro Jesús (Intelligent Data Science and Artificial Intelligence Research Center)
Vellido, Alfredo (Intelligent Data Science and Artificial Intelligence Research Center)
Nebot, Àngela (Intelligent Data Science and Artificial Intelligence Research Center)
Angulo, Cecilio (Intelligent Data Science and Artificial Intelligence Research Center)
Lamarca, Maria (Institut de Recerca Sant Joan de Déu)
Acuña, Vanessa (Universidad de Valparaíso. Departamento de Psiquiatría)
Berna, Fabrice (University Hospital of Strasbourg)
Moritz, Steffen (University Medical Center Hamburg-Eppendorf. Department of Psychiatry and Psychotherapy)
Gawęda, Łukasz (Institute of Psychology (Polònia))
Ochoa, Susana (Institut de Recerca Sant Joan de Déu)
Universitat Autònoma de Barcelona. Departament de Psicologia Clínica i de la Salut

Data:	2025
Descripció:	13 pàg.
Resum:	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.
Nota:	Altres ajuts: This work is part of the European ERAPERMED 2022-292 research project entitled 'Towards a Personalized Medicine Approach to Psychological Treatment of Psychosis' (PERMEPSY) funded by European Union - NextGenerationEU, supported as grant AC22/0053 by the Instituto de Salud Carlos III (ISCIII) in Spain. The PERMEPSY project was supported under the frame of ERA PerMed by: Instituto de Salud Carlos III (IS CIII), Spain; German Federal Ministry of Education and Research (BMBF), Germany; Agence Nationale de la Recherche (ANR), France; National Centre for Research and Development (NCBR), Poland; Agencia Nacional de Investigación y Desarrollo (ANID), Chile.
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	Personalized medicine ; Explainable artificial intelligence ; Feature selection ; Fairness ; Metacognitive Training ; Mental health
Publicat a:	Computational and Structural Biotechnology Journal, Vol. 28 (august 2025) , p. 281-293, ISSN 2001-0370

DOI: 10.1016/j.csbj.2025.07.051
PMID: 40831608

13 p, 2.0 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats