Washington, DC -- Surgo Foundation is launching the Surgo Machine Learning Initiative for Precision Public Health (ML4PxP) to explore the feasibility of applying causal machine learning methods to international development data. Machine learning presents an opportunity to examine an exponentially growing body of data with a fresh perspective beyond the confines of traditional statistics.
“There has been a lot of buzz surrounding machine learning in the international development industry, yet we actually know very little about how it can be applied and where it can add value,” says Sema Sgaier, co-founder and executive director of Surgo Foundation. A tremendous amount of effort has been focused on improving global health and development outcomes by scaling specific interventions. Yet, little is known about the causal chain of factors that drive outcomes. Machine learning can help us reconstruct this story line and find the key intervention points. “We aim to answer two fundamental questions: Is causal machine learning a reliable and scalable complement to traditional statistical analysis? And can machine learning uncover new insights from previously unconnected data sets?”
Machine learning is a subfield of artificial intelligence that allows systems to learn from data and even predict outcomes without explicit rule-based programming. Today’s machine learning technology can devise learning algorithms that discover relationships between data points with minimal subjective assumptions. In other words, machine learning doesn’t require researchers to start with a hypothesis.
In the international development sector, most analyses are done using traditional statistics, examining vertical data sets and testing an established hypothesis. This method often misses the opportunity to look at the whole system. By linking large, unconnected data sets without a preconceived hypothesis, machine learning has the potential to uncover a fuller set of relationships between data points.
Surgo has formed a strong and diverse consortium of partners across the private and non-profit sectors including the Bill and Melinda Gates Foundation (BMGF), GNS Healthcare, the University of Sussex, and the University of Manitoba. In its first proof-of-concept project, ML4PxP will begin by testing several potential causal machine learning approaches on reproductive, maternal, and child health data sets from Uttar Pradesh, India. Together, the consortium is innovating to determine whether and how such models can be applied to help solve big international development questions. This initiative is part of a larger partnership between Surgo Foundation and BMGF to advance cutting-edge research and the uptake of evidence for decision-making.
About Surgo Foundation: A privately funded Action Tank whose mission is to catalyze the global development sector to meet their promise by developing solutions and tools that put customers at the center. As with this machine learning initiative, Surgo incubates, tests, and scales solutions so others don’t have to.
About the Bill & Melinda Gates Foundation: Guided by the belief that every life has equal value, the Bill & Melinda Gates Foundation works to help all people lead healthy, productive lives. In developing countries, it focuses on improving people's health and giving them the chance to lift themselves out of hunger and extreme poverty.
About GNS Healthcare: Solves healthcare’s matching problem by transforming massive and diverse data streams to precisely match therapeutics, procedures, and interventions to individuals to improve health outcomes and lower costs. Their causal learning and simulation platform, REFS, accelerates the discovery of what works for whom and why.
About University of Manitoba: One of Canada’s largest and research intensive universities offering over 100 academic programs, including professional disciplines such as medicine, law and engineering. University of Manitoba leads the Uttar Pradesh Technical Support Unit (TSU) project, which is funded by The Bill & Melinda Gates Foundation.
About University of Sussex: A leading research-intensive university near Brighton, England with over 15,000 students and strong research credentials in machine learning and artificial intelligence.