Personalized Medicine: Big Data and Machine Learning

Precision and Personalized Medicine
Saturday, February 13, 2016: 8:00 AM-9:30 AM
Marshall Ballroom North (Marriott Wardman Park)
In recent years, great progress has been made in recording an individual’s state of health, down to the molecular level of gene activity and genomic information. However, the ultimate goal of using this information for personalized medicine remains largely unfulfilled. To turn the vision into reality, several issues must be addressed – including an urgent need to use patient data for improved and robust biomarker discovery, leading to improved disease diagnosis, prognosis, and prediction of therapy outcomes. The field of machine learning, which detects patterns, rules, and statistical dependencies in large datasets, has also witnessed dramatic progress. Among other advances, methods for high-dimensional feature selection, causality inference, and data integration have been developed or are underway. These techniques address many of the key methodological challenges faced by personalized medicine. Leading U.S. and European research institutes in machine learning and statistical genetics are working together to develop techniques for robust biomarker discovery and elucidation of the causal mechanisms governing disease outbreak and progress. This session presents research findings and advances in machine learning techniques in these two main areas, focusing on the essential challenge of large-scale data integration.
Gabriela Chira, European Commission
Gunnar Rätsch, Memorial Sloan-Kettering Cancer Center
Applying Advanced Data Analysis and Modeling Techniques to Biological Data
Bertram Müller-Myhsok, Max Planck Institute of Psychiatry
Deciphering Major Depression and Other Psychiatric Illness
Florence Demenais, French Institute of Health and Medical Research, Inserm
Integration of Biological Knowledge and Genomic Data to Identify New Disease Genes
See more of: Precision and Personalized Medicine
See more of: Seminars