Friday, March 29th, 2019 | 12:00pm - 1:00pm | 42 Church Street Cambridge 02138
AI can optimize your google search, but can it optimize a public health intervention using messy real-world data at scale? It is estimated that 830 women die every day from preventable complications related to pregnancy and childbirth and more than five million children die each year before their fifth birthday. Getting women to deliver in hospital facilities instead of delivering at home and ensuring the provision of quality of care are key to address this public health crisis. Using novel data sets and integrating several machine learning approaches, we demonstrate how programs can develop a more precise approach to closing these gaps. Our case study is from India’s most populous state, Uttar Pradesh where 34 percent more newborns die than in India as a whole, and 55 percent more women die from causes related to pregnancy or childbirth. The talk will also outline the challenges of working with real world data and discuss innovations that are needed not only on the AI front, but also on the data side.
Dr. Sema Sgaier is Co-founder and Executive Director of Surgo Foundation, a privately funded action tank whose mission is combining a customer obsessed agenda with systems thinking to solve complex global development problems. At Surgo, she leads a multi-disciplinary team of data scientists, behavioral scientists, technologists, and development experts. Previously at the Bill & Melinda Gates Foundation, Sgaier led large-scale health programs in India and Africa. She is an assistant adjunct professor of global health at the Harvard T.H. Chan School of Public Health and was selected as a Rising Talent by the Women’s Forum for the Economy and Society. Sema holds a PhD in cellular and molecular biology from New York University, a MA in neuroscience from Brown, and a BSc in molecular biology and genetics from Boğaziçi University (Istanbul).