Modelling and Predicting Territorial Health Pathways: Integration of Heterogeneous Data and Multilevel Learning

This PhD position focuses on advancing AI techniques to model and forecast health pathways at a territorial scale. The project, based in Pays de la Loire, France, aims to integrate heterogeneous healthcare data and apply multilevel learning to improve predictive accuracy for regional health systems. The successful candidate will collaborate with academic and industrial partners to develop innovative computational methods, contributing to both research and practical applications in public health. The role requires strong computational skills, proficiency in handling complex datasets, and a commitment to interdisciplinary collaboration.

• Develop AI models capable of integrating heterogeneous healthcare data from multiple sources (e.g., electronic health records, administrative data, and patient-reported outcomes).
• Apply multilevel learning techniques to analyze and predict health trajectories at a territorial scale, accounting for individual, community, and systemic factors.
• Collaborate with academic and industrial partners to ensure the models are scalable, interpretable, and applicable to real-world healthcare settings.
• Conduct empirical validation of the models using real-world healthcare datasets, ensuring robustness and generalizability.
• Publish research findings in peer-reviewed journals and present results at national and international conferences.
• Contribute to the development of policy-relevant insights for regional health authorities and stakeholders.