Skip to main content
Aller à la page d’accueil de la Commission européenne (s’ouvre dans une nouvelle fenêtre)
français fr
CORDIS - Résultats de la recherche de l’UE
CORDIS

Advancing Breast cancer Individualised Generative AI for Longitudinal Outcomes

Objectif

ABIGAIL4D pioneers a new approach to personalised oncology by developing and validating a 4D Generative AI system prototype that can learn disease evolution over time and support safer, more informed treatment decisions in early breast cancer. Today, decision support tools rely on static or single-modality data and cannot estimate how an individual patient would respond to alternative therapies. This limits clinical ability to compare options and optimise outcomes.
ABIGAIL4D combines multimodal longitudinal data, including imaging, pathology, genomics, and clinical variables, into a temporal model that reconstructs and forecasts tumour response, survival and toxicity. The system introduces counterfactual analysis to estimate patient-specific benefit and risk for different treatment strategies, such as escalation and de-escalation of chemotherapy or radiotherapy. Specialised AI agents (Radiology, Pathology, Oncology and Patient) collaborate through a stateful orchestrator to generate explainable recommendations with quantified uncertainty. Clinicians remain in control at all times, supported by transparent rationales linked to clinical concepts and guidelines.
The methodology follows a staged design: requirements co-creation with clinicians; development of the GenAI backbone and multi-agent framework; trust-by-design mechanisms for traceability, reproducibility and explainability; and validation in controlled, multi-centre lab settings. Regulatory documentation aligned with EU Medical Device Regulation and the AI Act will support future certification.
ABIGAIL4D AI agents and system, aim at enabling in the future personalised treatment decisions and more efficient care pathways. Expected benefits will include better therapy selection, fewer unnecessary scans and reduced burden for patients and healthcare systems. ABIGAIL4D provides a foundation for future expansion to other solid tumours, contributing to Europe’s leadership in responsible AI driven precision medicine

Champ scientifique (EuroSciVoc)

Mots‑clés

Programme(s)

Thème(s)

Régime de financement

HORIZON-EIC - HORIZON EIC Grants

Voir tous les projets financés dans le cadre de ce programme de financement

Appel à propositions

(s’ouvre dans une nouvelle fenêtre) HORIZON-EIC-2025-PATHFINDERCHALLENGES-01

Voir tous les projets financés au titre de cet appel

Coordinateur

FUNDACIO EURECAT
Contribution nette de l'UE
€ 898 875,00
Adresse
AVENIDA UNIVERSITAT AUTONOMA 23
08290 Cerdanyola Del Valles (Barcelona)
Espagne
Région
Este Cataluña Barcelona
Type d’activité
Research Organisations
Liens
Coût total
Aucune donnée

Participants (9)