Lecture: 'Development of an Integrated Platform for Advanced Medical Research Based on AI'
The digital transformation of healthcare has led to an unprecedented growth in the volume and heterogeneity of clinical data. At the same time, aging populations and rising demands on healthcare systems require cost-effective, scalable solutions. Artificial intelligence (AI) has emerged as a powerful tool in clinical research, however, it demands structured, large-scale, high-quality datasets. The extensive preparation required before data can be used for AI training poses a significant bottleneck between data acquisition and algorithm development.
The TransCOR platform has been designed to accelerate data-driven clinical research, with a special focus on the creation of AI models. This platform aims to become an agile development environment that connects clinicians and researchers efficiently, providing secure and reusable tools for data management, exploration, curation, annotation and interpretation that can be easily tailored to the very specific needs of each project use case. The platform infrastructure has been successfully deployed in two cloud systems and on-premise at two hospitals. It is being actively used in 18 ongoing research projects by over 60 users (including clinicians and researchers across three continents), and has processed millions of clinical data samples so far, demonstrating its robustness and scalability in real-world research environments. By aligning technical infrastructure with clinical needs and regulatory requirements, the TransCOR platform significantly reduces barriers in translational AI research and promotes faster, more reliable innovation in healthcare.
About the speakers
Josa Prats i Valero is a Lead Software Engineer at the TransCOR research group of Universitat Pompeu Fabra in Barcelona. She holds a Bachelor's Degree in Audiovisual Systems and a Master's Degree in Computational Biomedical Engineering. She works on the design, implementation and deployment of software solutions specially conceived to support medical research. Her goal is to create modern, reliable, efficient tools that enhance the research process.
Gabriel Bernardino is a Ramon y Cajal fellow at the TransCOR group at UPF. He holds an Engineer's Degree in Computer Science and a Bachelor in Mathematics by the Universitat Politècnica de Catalunya, and a Msc in Mathematics by the University of Bonn. He did a PhD in Information and Communication Technologies (Universitat Pompeu Fabra, Barcelona, Spain, 2019), carried out in collaboration with Philips Research (Paris, France) within the Marie Swodlaska Curie European Industrial Doctorate Cardiofunxion. Afterwards, he was a postdoctoral researcher in CREATIS (Lyon, France). His research objective is to improve current assessment of cardiovascular images. While machine learning has shown great potential in computer vision, its applications to medical images are still challenging, given data scarcity and the amount of noise present. His aim is to develop machine learning techniques that not only learn from data, but also incorporate physiological knowledge, thus being more robust and interpretable. His research focuses on deriving interpretable biomarkers of pathologies from populations, useful not only for diagnosis purposes but also to understand the underlying pathophysiology. Currently, his main clinical interest lies in fetal cardiology: identifying how cardiovascular abnormalities cause a gestational impairment in fetal ultrasound images (Doppler and B-mode).
The digital transformation of healthcare has led to an unprecedented growth in the volume and heterogeneity of clinical data. At the same time, aging populations and rising demands on healthcare systems require cost-effective, scalable solutions. Artificial intelligence (AI) has emerged as a powerful tool in clinical research, however, it demands structured, large-scale, high-quality datasets. The extensive preparation required before data can be used for AI training poses a significant bottleneck between data acquisition and algorithm development.
The TransCOR platform has been designed to accelerate data-driven clinical research, with a special focus on the creation of AI models. This platform aims to become an agile development environment that connects clinicians and researchers efficiently, providing secure and reusable tools for data management, exploration, curation, annotation and interpretation that can be easily tailored to the very specific needs of each project use case. The platform infrastructure has been successfully deployed in two cloud systems and on-premise at two hospitals. It is being actively used in 18 ongoing research projects by over 60 users (including clinicians and researchers across three continents), and has processed millions of clinical data samples so far, demonstrating its robustness and scalability in real-world research environments. By aligning technical infrastructure with clinical needs and regulatory requirements, the TransCOR platform significantly reduces barriers in translational AI research and promotes faster, more reliable innovation in healthcare.
About the speakers
Josa Prats i Valero is a Lead Software Engineer at the TransCOR research group of Universitat Pompeu Fabra in Barcelona. She holds a Bachelor's Degree in Audiovisual Systems and a Master's Degree in Computational Biomedical Engineering. She works on the design, implementation and deployment of software solutions specially conceived to support medical research. Her goal is to create modern, reliable, efficient tools that enhance the research process.
Gabriel Bernardino is a Ramon y Cajal fellow at the TransCOR group at UPF. He holds an Engineer's Degree in Computer Science and a Bachelor in Mathematics by the Universitat Politècnica de Catalunya, and a Msc in Mathematics by the University of Bonn. He did a PhD in Information and Communication Technologies (Universitat Pompeu Fabra, Barcelona, Spain, 2019), carried out in collaboration with Philips Research (Paris, France) within the Marie Swodlaska Curie European Industrial Doctorate Cardiofunxion. Afterwards, he was a postdoctoral researcher in CREATIS (Lyon, France). His research objective is to improve current assessment of cardiovascular images. While machine learning has shown great potential in computer vision, its applications to medical images are still challenging, given data scarcity and the amount of noise present. His aim is to develop machine learning techniques that not only learn from data, but also incorporate physiological knowledge, thus being more robust and interpretable. His research focuses on deriving interpretable biomarkers of pathologies from populations, useful not only for diagnosis purposes but also to understand the underlying pathophysiology. Currently, his main clinical interest lies in fetal cardiology: identifying how cardiovascular abnormalities cause a gestational impairment in fetal ultrasound images (Doppler and B-mode).
Mixed event
Wednesday, April 15, 2026
1776211200000
/events/conference-development-of-an-integrated-platform-for-advanced-medical-research-based-on-ai
events_en