AI strategies for clinical decision support systems

Our expertise in Sapienza University of Rome, as researchers, lies in the design and application of artificial intelligence solutions for healthcare decision-making, with particular emphasis on clinical decision support, patient risk assessment, and predictive modeling. We work at the intersection of machine learning, clinical data, and medical workflows to develop AI systems that support clinicians in diagnosis, prognosis, treatment planning, and resource allocation.

I have experience translating complex healthcare data—such as electronic health records, clinical scores, and real-world patient outcomes—into robust and interpretable models. A key focus of my work is ensuring that AI-driven tools are transparent, clinically meaningful, and aligned with real decision-making processes, rather than functioning as black-box predictions. This includes model validation, uncertainty estimation, bias and fairness considerations, and human-in-the-loop decision support.

Our main use cases involved CVDs and diabetes-affected patients.