Analysis of Longitudinal Phenotypes and Disease Trajectories at Population Scale using Deep Learning
Monday, November 20, 2023
Multi-step disease and prescription trajectories are key to the understanding of human disease progression patterns and their underlying molecular level etiologies. While they are useful in descriptive approaches to produce longitudinal patient stratification they can also be used for predictive purposes. The talk will present deep learning approaches that work from life course data comprising millions of patients. We use data covering 7-10 million patients from Denmark and the USA collected over a 15-40 year period and use them predict future outcomes, including mortality and specific diagnoses, such as pancreatic cancer. Disease trajectories and explainable AI can generate hypotheses that can be followed up using molecular level data, including omics data, leading to investigations that venture into causal and mechanistic aspects of disease progression.
Post Talk Link: ClickHere
Passcode: 8aFg+gWk
Speaker/s
Søren Brunak is a Danish Physicist and Biological Researcher working with machine learning in the domains of bioinformatics, systems biology, and health informatics. He is Professor of Disease Systems Biology at the University of Copenhagen, as well as a Medical Informatics Officer at Rigshospitalet in Denmark. In 1993, he became the Founding Director of the Center for Biological Sequence Analysis (CBS) at the Technical University of Denmark (DTU), heading one of the largest multi-disciplinary research groups in bioinformatics in Europe. In 2007, he became one of the Founding Research Directors at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen. His program for Disease Systems Biology combines molecular level systems biology and the analysis of phenotypic data from the healthcare sector. He has been a Member of the Royal Swedish Academy of Sciences since 2016, a Member of the European Molecular Biology Organization since 2009, and a Member of the Royal Danish Academy of Sciences and Letters since 2004.
Related
Polygenic Score Modeling to Investigate Genotype-Phenotype Associations
Read More
Trustworthy Machine Learning: Transparency, Collaboration, and Evaluation
Read More