For two days in December, researchers and students converged on Technion to hear from the world’s foremost experts on one of the most dynamic and groundbreaking fields today: using deep learning and big data to improve healthcare.
Technion recently hosted the first ever “Biomedical Informatics – Big Data Science” Conference, drawing a large audience eager to hear about the latest developments in this fascinating field. Applying deep learning to medical data makes it possible to generate new hypotheses and to make discoveries that would not have been possible in the past. The conference was brilliantly organized by Prof. Roy Kishony, world authority on antibiotic resistance and Head of the Technion Lokey Center for Life Sciences and Engineering and Dr. Kira Radinsky, visiting Technion professor and director of data science of eBay. Their unique synergy resulted in a precise mix of speakers who covered a wide range of topics – from practical applications of data science in medical care to ethical precision medicine and next generation healthcare. In the course of two days, 24 eminent speakers from around the world shared their latest research findings with the international audience. The conference was sponsored by Yad Hanadiv.
“We’re living in a fascinating era for scientific research, an era where extensive data is used to improve diagnoses and treatments”
– President Prof. Peretz Lavie
Prof. Shai Shen-Orr, of the Rappaport Faculty of Medicine and the conference organizing team, addressed the ongoing efforts to build a cell-centered view of genomic data that can be integrated with primary immunology literature.
Experts from around the world included Prof. Nigam Shah from Stanford University, who described the initiative he leads, which takes data from electronic health records and uses machine learning to help doctors answer clinical questions. Dr. Hannah Bayer, a neuroscientist from New York University, spoke about the HUMAN Project, which studies 10,000 New York City residents over a period of 20 years, tracking everything from financial and social data to environmental and health factors.
