AAIDT

The project aims to investigate the use of artificial intelligence (AI) algorithms to support therapeutic decision-making, with the goal of improving the reliability, transparency, and safety of AI-based healthcare solutions while addressing their legal and ethical implications.

In particular, the project focuses on developing methodologies for validating the accuracy, robustness, and reliability of AI algorithms in clinical settings; investigating explainable AI techniques to make algorithmic decisions understandable to healthcare professionals and patients; analyzing legal aspects related to medical liability, data protection, and regulatory compliance; and examining ethical challenges concerning patient autonomy, informed consent, fairness, and the doctor-patient relationship.

The project adopts an interdisciplinary approach combining computer science, software engineering, law, and ethics. A specific case study focuses on the use of AI algorithms for prioritizing medical treatments and allocating limited healthcare resources during emergencies. Expected outcomes include theoretical frameworks, validation methodologies, practical guidelines, and an AI-based prototype evaluated in terms of robustness and explainability.

Partners

University of Bergamo – Department of Management, Information and Production Engineering: Angelo Gargantini (PI)

University of Bergamo – Department of Law: Massimo Foglia