Martin Vallières is an Assistant Professor in the Department of Computer Science of Université de Sherbrooke. He received a PhD in Medical Physics from McGill University in 2017, and completed post-doctoral training in France and USA in 2018 and 2019. The overarching goal of Martin Vallières’ research is centered on the development of clinically-actionable models to better personalize cancer treatments and care (“precision oncology”). He is an expert in the field of radiomics (i.e. the high-throughput and quantitative analysis of medical images) and machine learning in oncology. Over the course of his career, he has developed multiple prediction models for different types of cancers. His main research interest is now focused on the graph-based integration of heterogeneous medical data types for improved precision oncology.
Week 6 Speaker: MEDomics: integrative data modeling in oncology
Most of the content of Electronic Health Records (EHR) of our hospitals are recorded via sparse data tables with a high probability that some variables or values are missing. The EHR nonetheless possesses a vast amount of heterogeneous data from different sources, most of which are often sub-optimally exploited to characterize and predict disease behavior. For example, medical imaging (e.g. magnetic resonance imaging: MRI) would carry an immense source of potential data for decoding cancer phenotypes. On the other hand, physicians also describe and write important patient characteristics and symptoms related to the disease for almost every medical encounter via free-form medical text notes. In recent years, significant progress in multi-omics technology (e.g. genomics, transcriptomics, etc.) has also created unprecedented opportunities for characterizing the biological processes correlated with diseases. However, combining these heterogeneous data sources in a meaningful way for disease prediction is a challenge. Integrating these analysis methods within the same computing platform is also desirable. In this presentation, I will elaborate on the efforts made over the past few years by an international consortium for the development of such a platform: MEDomicsLab.