PhD Supervisor: Vicente García Díaz (UNIOVI) Auxiliary supervisors: David Camacho (UPM), Jerry C.-W. Lin (SUT), Shen Yin (NTNU); R&D cooperation: BioKeralty, TNP

Objectives: Interpretable and explainable AI methods, algorithms and services are key factors for trustworthy applications in Health Informatics. The project will focus on accuracy of the machine learning models to associate a cause to an effect and the ability of the parameters to justify results. The first and necessary condition is dimensionality reduction to minimise model complexity and overfitting and automatic support for feature selection and extraction for explainable AI models. In particular, the work will focus on predicting and handling the onset and progression of chronic diseases such as diabetes, heart disease and Alzheimer, focusing on early intervention strategies.

Expected Results: The DC3 will be expected to experiment with different sets of data applied to health informatics and understanding the best way to treat them and next to experimenting with different technologies to interpret and explain models applied to chronic diseases such as diabetes, heart disease or Alzheimer.

Applied research: The research results on models and services to improve the current state of the art in predicting and handling different chronic diseases. They will be verified by BioKeralty in its healthcare applications. Newly developed models and services can potentially extend the portfolio of technology used by BioKeralty in its health centers and hospitals. The TNP will support DC3 with DNA laboratories.

Planned secondments: UPM (4 months); NTNU(4 months); SUT (4 months)                   

Enrolment in Doctoral degree: UNIOVI