Expertise in insilico model

In silico modeling refers to the use of mechanistic, data-driven, and hybrid computational models to simulate human physiology, disease progression, and medical device interactions with the goal of optimizing diagnosis, therapy, and device design without reliance on animal testing.

In cardiovascular applications, in silico models combine patient-specific anatomy, hemodynamics, electrophysiology, and vessel wall mechanics to predict blood flow, pressure, thrombosis risk, and device–tissue interaction. These models support optimization of stents, valves, catheters, and assist devices, enable virtual cohorts for safety and performance evaluation, and allow longitudinal prediction of disease progression or treatment response.

In oncology, in silico models integrate tumor growth dynamics, vascularization, oxygenation, and treatment effects (radiotherapy, chemotherapy, thermal or particle therapies). Mechanistic PDE models are increasingly coupled with AI and statistical learning to forecast tumor evolution, optimize treatment planning, and personalize

In silico modeling and AI-driven optimization for healthcare and medical devices

We develop in silico modeling and AI-based methodologies to support optimization, safety assessment, and performance prediction in cardiovascular disease, oncology, and critical care. Our approach combines mechanistic physiological models with machine learning and advanced statistics to simulate disease progression, treatment response, and medical device–tissue interaction in a patient-specific and longitudinal manner.

Applications include virtual testing and optimization of cardiovascular and oncological devices, predictive modeling for therapy planning and outcome forecasting, and decision-support tools for critical care. By integrating multimodal clinical data with physics-based models, we enable robust uncertainty quantification and population-level analysis through virtual cohorts.

Already experience in h2020 and acquirred grant in fwf/ffg.