• Find people
• Intranet

Artificial Intelligence and Data in Health Joaquín Dopazo Blázquez

The Artificial Intelligence and Data in Health Research Group develops advanced computational methods to transform complex biomedical data into actionable knowledge for translational research, personalized medicine, and clinical decision-making. Our work lies at the intersection of bioinformatics, clinical genomics, systems medicine, artificial intelligence, and the secondary use of large-scale clinical data.

The group's main objective is to contribute to a more predictive, preventive, and personalized medicine through the integration of omics, clinical, and population-level data. To achieve this, we develop models, algorithms, computational resources, and validation strategies aimed at facilitating the use of complex biomedical data in real-world research and healthcare settings.

The group has a strong translational and collaborative focus, with expertise in clinical genomics, rare diseases, cancer, molecular epidemiology, drug repurposing, real-world data analysis, and artificial intelligence applied to healthcare.

Research Areas

• Clinical Genomics

The group develops and applies bioinformatics methods for the interpretation of genomic data in clinical and translational settings. This research area includes the analysis of genetic variants, the integration of genomic and clinical information, the prioritization of disease-associated genes and variants, and the development of resources that facilitate the incorporation of genomics into clinical practice.

Our activity in this field is closely linked to participation in CIBERER (https://www.ciberer.es/) and builds on a long-standing track record in rare diseases, hereditary cancer, and personalized medicine. The group has contributed to the development of resources and strategies for the interpretation of individual and population genomes, including the Spanish Variant Server (CSVS; https://csvs.babelomics.org/) and SPACNACS (https://csvs.clinbioinfosspa.es/spacnacs/), as well as genomic surveillance and molecular epidemiology initiatives.

This area also encompasses cancer research, genetic susceptibility studies, germline and somatic variant analyses, and molecular epidemiology projects such as SIEGA (https://www.clinbioinfosspa.es/projects/siega/), which focus on the use of genomic sequencing for the surveillance, characterization, and monitoring of infectious agents and their impact on public health. This work embraces a One Health perspective.

• Systems Medicine

Systems medicine is one of the group's core research areas. Our goal is to understand disease as the result of coordinated alterations in molecular networks, signaling pathways, cellular processes, and complex pathophysiological mechanisms.

In this context, the group has developed and applied methodologies such as HiPathia (http://hipathia.babelomics.org/), designed to model the functional activity of signaling pathways from omics data. These models enable the interpretation of transcriptomic and genomic data from a mechanistic perspective, the identification of biological processes altered in disease, and the generation of hypotheses regarding mechanisms of action, biomarkers, and potential therapeutic interventions.

This research area also includes mechanism-based drug repurposing, disease modeling, disease map analysis, and hypothesis validation using real-world clinical data. The objective is to connect molecular information with clinical phenotypes and health outcomes, facilitating the translation of computational biology into biomedical and clinical applications.

• Real-World Evidence Generation

The group develops methods for generating evidence from real-world data, including electronic health records, population registries, administrative databases, pharmacy records, laboratory results, medical imaging, and other data generated during routine clinical care.

This line of research is based on the premise that routinely collected clinical data constitute a strategic source of knowledge for biomedical research, outcomes evaluation, healthcare planning, and personalized medicine. The rigorous, ethical, secure, and reproducible use of these data enables the study of entire populations, the identification of disease patterns, the evaluation of clinical trajectories, and the development of predictive models applicable in real-world settings.

Research topics include the development of early disease predictors, risk stratification models, retrospective population studies, health outcomes analyses, treatment evaluation, and the external validation of clinical algorithms. Through its participation in initiatives such as IMPaCT Data (https://impact-data.bsc.es/), which the group co-leads, and OmicsSpace (https://omicspace.iislafe.es/), the group has a particular interest in federated and standardized approaches that enable the reuse of clinical data while preserving privacy, governance, and analytical traceability.

• Artificial Intelligence in Medicine

The group develops and applies advanced artificial intelligence techniques for the analysis of complex biomedical data. This research area includes interpretable machine learning, clinical predictive models, multimodal data integration, generative artificial intelligence, biomedical foundation models, and AI-based systems that support research activities.

A specific area of interest is the generation of synthetic patient data, conceived as a tool to facilitate research, model training and validation, methodological evaluation, and the secure sharing of information when access to real-world data is restricted. The group addresses both the technical aspects and the ethical, methodological, and regulatory challenges associated with the generation and use of synthetic health data.