Health AI and Data Research Group
Driven by Artificial Intelligence (AI) in health, the team develops approaches in scientific AI and computational biology. In this way, multimodal data (including omics information, neuroimaging, and clinical, cognitive and lifestyle data) are integrated to transform research about neurodegeneration, such as Alzheimer’s, into real-world clinical solutions.
Data and Computation-Driven Precision Medicine
Under the leadership of Dr Joaquin Dopazo, the Health AI and Data Research Group primary mission is to transform the vast amount of research data held by the BBRC into useful and actionable knowledge.
To achieve this, the team develops advanced computational models that combine Artificial Intelligence (AI), computational biology and modelling. The aim is to move beyond traditional statistics-based medicine to pave the way for true precision medicine. This allows both treatments and prevention strategies to be tailored to the unique characteristics of each individual.
One of the most innovative areas in which they work is generative AI, with which they develop synthetic patients and agentic models to simulate and study complex health scenarios.
Innovation in Generative AI: Synthetic Patients and Agentic Models
Its research combines Artificial Intelligence (AI), systems biology and computational genomics to identify biomarkers, predict risk and disease progression, and understand the molecular mechanisms underlying Alzheimer’s disease.
Furthermore, it is driving forward new methodologies based on synthetic patients (clinical records generated by AI that simulate real-world medical histories without compromising privacy) to facilitate ethical and safe research. It also utilises agentic AI, capable of autonomously carrying out numerous aspects of the research process and complex decision-making.
These technologies accelerate the generation of biomedical knowledge and its translational application in study cohorts such as ALFA, optimising the transition from research to clinical benefit.
Computational Approaches for Multimodal Data Integration and Biomarker Discovery
Integration and joint analysis of genomic, transcriptomic, proteomic, metabolomic, microbiome and neuroimaging data, as well as clinical, cognitive and lifestyle data, to characterise the heterogeneity of neurodegenerative diseases and identify biomarkers with diagnostic, prognostic and predictive value.
Development of bioinformatics applications for the management of omics data.
Applications of Artificial Intelligence for the Early Prediction of Alzheimer’s Disease and Patient Stratification
Development of AI models aimed at identifying individuals at risk, predicting clinical progression and stratifying patients in the early or preclinical stages of neurodegenerative diseases, with a particular focus on Alzheimer’s disease.
Systems Biology and Mechanistic Modelling to Discover New Therapeutic Targets
Application of pathway models, biological networks and mechanistic approaches to interpret molecular alterations, understand pathogenic mechanisms and propose new therapeutic targets or drug repositioning strategies.
Computational Genomics Applied to Rare Neurodegenerative Diseases
Generation of Synthetic Patients and Simulation of Virtual Cohorts
Development and validation of generative AI methodologies for the creation of synthetic patients (digital twins) and virtual cohorts to facilitate research, model training, hypothesis testing and secure data sharing whilst preserving privacy.
Advanced AI Systems for the Automatic Generation of Biomedical Knowledge
Design of advanced agentic AI systems capable of autonomously exploring biomedical data, scientific literature and knowledge bases to generate hypotheses, integrate evidence, discover relevant relationships and accelerate translational research into neurodegeneration.
