I am a Ph.D. student in my final year at CiTIUS (Centro Singular de Investigación en Tecnologías Inteligentes) with the thesis entitled "New statistical contributions in Reproducing Kernel Hilbert Spaces and Frechet spaces with application in personalized medicine." Previously, I have worked for two years as a researcher in the Clinical Epidemiology Unit of Santiago de Compostela's hospital. As a result, I obtained great experience in biomedical research.

As a mathematician, I have a strong background in functional analysis and probability theory. I also have prior experience in statistical inference and in empirical process theories, which constitute the probabilistic tools to understand and design the statistical and ML models of the future. My extensive experience in statistics and machine learning in medicine and related fields gives me a unique insight into the "next" methodological contributions that data science researchers must propose to address the future challenges of precision medicine and AI in medicine, as well as to model efficiently the different research questions that practitioners may ask.

As for the methodological contributions, I have extended the famous statistical and ML concepts of the "energy distance" or the "maximum mean discrepancy" to the setting of incomplete information, such as censored or missing data. I have also proposed the first bi-clustering algorithm for complex data in Reproducing kernel Hilbert Spaces. Regarding modeling contributions, We (Alex Petersen and I) were the first researchers to propose distributional representation strategies to model data from biosensors, such as continuous glucose monitors or accelerometer devices. The introduction of new distributional representations allows to improve the performance that traditional data analysis methods have in these domains. For example, in clinical applications we have provided new findings such as how particular glucose or physical activity profiles can have an impact on our health. In collaboration with Fernando Huelin, I have proposed the first indirect methodology to estimate maximum oxygen consumption with accuracy.

Despite my young age, I have developed most of the projects autonomously, and I possess critical thinking about relevant research and what matters we need to work to "change the world".