Research Activities

Our lab seeks to bridge the gap between advanced machine learning and complex health data, translating raw information into actionable knowledge. We leverage these innovative methodologies to develop scalable, data-driven solutions that advance personalized healthcare and improve clinical outcomes.

Dietary monitoring, assessment, and management

Research in this area focuses on developing AI-based methods for analyzing dietary intake using image-based and data-driven approaches. We aim to enable more accurate, scalable, and personalized nutritional assessment, supporting the shift toward precision nutrition and individualized dietary recommendations.

Causal modeling of lifestyle, genetic, and environmental risk factors for obesity

Research leverages privacy-preserving AI, federated learning, and causal inference on multi-domain data to uncover the complex underlying drivers of obesity. These approaches aim to generate personalized, data-driven interventions and to support healthcare professionals with precise, actionable insights for sustainable weight management.

Diabetes self-management and treatment optimization

Research explores intelligent algorithms that adapt insulin therapy based on real-time glucose and lifestyle data. We develop methods that aim to improve treatment outcomes, reduce risks, and support more effective and adaptive disease management.

Diagnosis, prognosis, and management of acute and chronic lung diseases

Work in this area focuses on AI models for the analysis of medical imaging and clinical data. We aim to support early diagnosis, disease characterization, and continuous monitoring of lung conditions, contributing to improved clinical decision-making.