Data scientists form Microsoft have donated a newly developed tool to Seattle Children’s Research Institute to advance research into sudden infant death syndrome (SIDS). The team will also make the tool available to researchers around the globe.
Although SIDS deaths have plateaued at roughly 4,000 per year in the U.S. since the mid-1990s, researchers are working to discover its causes. A research team led by John Kahan, general manager for customer data and analytics at Microsoft, used deep learning technology and big data to develop methods to identify SIDS causes and craft preventative measures.
The team analyzed public data from the U.S. Centers for Disease Control and Prevention (CDC), including 27,000 sudden and unexplained infant deaths from 2004 to 2010. They then created machine learning and statistical models to interpret the data. These models allowed researchers to search factors such as parents’ age, level of prenatal care and birth order to evaluate how these factors affect SIDS.
The technology verified SIDS correlations already proved by researchers. New correlations were also identified, providing researchers with scientific processes to further SIDS studies.
"The potential of this tool to aid medical research and open new areas of exploration in identifying SIDS risk factors is both impactful and tremendously encouraging," said Nino Ramirez, director of the Center for Integrative Brain Research at Seattle Children's Research Institute. "I am even more amazed by the potential research implications this tool could have for other sudden death disorders like obstructive sleep apnea, epilepsy and mitochondrial diseases. Exploring the data visually ... could provide novel insights and inspire research into any one of these disorders."