Jorge Corral Acero gained his MS and BS in Chemical Engineering at the University of Valladolid, conducted his Masters thesis at Imperial College of London and completed his post-master research stays at UC Berkeley (neuroengineering) and Harvard Medical School (chest image).
He is currently pursuing a DPhil in Engineering Science at the University of Oxford as a PIC fellow, aiming to gain a better understanding of how cardiac anatomy modulate human cardiovascular diseases (CDVs). More specifically, using a combination of ML techniques and personalised models to assess the heart performance for different disease geno- and phenotype structures.
Jorge has gained diverse and wide international working experience from junior researcher positions in 6 different research groups (Biomedical Image Analysis, ACIL, Maharbiz´s Group, CPSE, HPP and BIOFORGE) and internships in 2 companies (Michelin and Lesaffre).
In the current European socio-political framework, where nations are facing a period of tightening financial constraints and aging population, preventive and personalised medicine is expected to become crucial to improve both the efficiency and efficacy of healthcare systems.
This is particularly important in CVD, the world leading cause of death, accounting for 42% of the European mortality and draining €169billion per year in Europe alone. While CVD is usually associated with changes in structure (morphology) and function, their interplay in modulating disease outcomes is largely unknown.
My personal research interest is therefore to gain a better understanding of the heart morphology to contribute towards early-stage disease identification and personalised medicine. The lack of accurate risk stratification methods in hypertrophic cardiomyopathy, principal cause of sudden cardiac death in the youth, due to the high phenotype heterogeneity of the disease along with the proven impact of morphological remodelling in survival after MI episodes, accounting for several millions worldwide every year, further motivates my research.
Large population studies are facilitated by the recent expansion of big data in cardiovascular medicine. Moreover, the promising deep learning approaches that are revolutionising the medical imaging field expand the possibilities of accurate and fast regression of heart shapes from CMR, granting technical feasibility to such studies. Finally, the potential of integrating morphology with function in personalised computer simulation justifies efforts towards shortcutting and alleviating computational costs, overcoming one of the major limitations of computer modelling. A scenario of breakthroughs emerges and I am excited to become part of it.
My research focuses on gaining a better understanding of how cardiac anatomy modulates human CDV. It involves the development of biomedical image analysis algorithms taking advantages of ML techniques, with an emphasis on the combination with computational models, and applications on cardiac medicine, in particular, hypertrofic cardiomyopathy and myocardium infarction.