Proving the Business Case for the Internet of Things

Microsoft helps fight sudden infant death syndrome

Steve Rogerson
June 20, 2017



Microsoft is using big data analytics to help researchers fighting sudden infant death syndrome. Its scientists volunteered hundreds of hours to create a free medical research tool to drive breakthroughs addressing the leading cause in the USA of infant mortality.
 
Data scientists from Microsoft donated the research tool to Seattle Children's Research Institute, one of the top five paediatric research centres in the USA, and will make it available to researchers worldwide. They hope to help those working to solve one of the world's biggest medical mysteries, sudden infant death syndrome (SIDS).
 
SIDS is a leading cause of death among children from one to 12 months old. Approximately 4000 infants in the USA die each year from sudden unexpected infant deaths (SUID), which includes SIDS. There has been no significant drop in such deaths since the mid-1990s.
 
A co-worker's loss of a son to SIDS inspired the team of data scientists to contribute hundreds of volunteer hours to create the research tool. John Kahan, Microsoft general manager for customer data and analytics, turned his focus to fighting SIDS after he and his wife, Heather, lost their only son, Aaron, 13 years ago.
 
"My mission is to ensure that no parent experiences the pain of losing a child to SIDS, or worry that their child may be next," Kahan said. "I am incredibly moved and grateful to my team for volunteering their personal time to create this tool for SIDS research."
 
Kahan added that his larger data science team had also spent hundreds of hours outside this project raising money for SIDS research.
 
The team set out to enable researchers without deep technology skills to use big data the same way the world's top technology companies do, to identify more quickly the causes of SIDS and develop preventive measures. Kahan's team accessed publicly available data from the US Centers for Disease Control & Prevention (CDC), including information on 29 million births and over 27,000 sudden and unexplained infant deaths from 2004 to 2010. They created several machine learning and statistical models, which run on Microsoft Azure, to interpret and crunch massive amounts of data.
 
The data are displayed visually on Microsoft’s Power BI business analytics service, allowing researchers to click on thousands of combinations of factors, such as the child's birth order, the parents' ages and the level of pre-natal care a mother received, and see how those factors might be connected. Those connections, or correlations, can be key: in the early 1990s, when sleeping position was found to be correlated with SIDS, new guidance for parents significantly reduced infant deaths.
 
The technology passed an early and important milestone test late last year, verifying correlations with SIDS already discovered by researchers. In addition, new correlations identified by the tool have been provided to Seattle Children's, where paediatric researchers will use scientific processes to see if they point to areas of further study.
 
"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, after seeing a demonstration of the system in November. "I am even more amazed by the potential research implications this tool could have for other sudden death disorders like obstructive sleep apnoea, epilepsy and mitochondrial diseases. Exploring the data visually through Power BI could provide novel insights and inspire research into any one of these disorders."
 
Kahan's team focused on potentially breakthrough research on SIDS at Seattle Children's, including the work of Daniel Rubens, an anaesthesiologist and nationally recognised SIDS researcher, who found a strong connection between SIDS and an abnormality in the inner ear.
 
"This team at Microsoft can help us analyse epidemiological data in ways that were not available before, and to then ask questions and put pieces together in a way we haven't been able to previously," Rubens said.
 
Microsoft Philanthropies donated Azure cloud services to Seattle Children's to power the technology.
 
"Breakthroughs in SIDS research stand to save thousands of young lives each year while providing a degree of comfort for the millions of parents who worry about it in an infant's first year," said Mary Snapp, corporate vice president and head of Microsoft Philanthropies. "We believe cloud services can help unlock the secrets held by SIDS data and provide new insights for the scientists working to identify the causes of, and put an end to, SIDS."
 
Kahan's team is working with Rutgers Robert Wood Johnson Medical School and Seattle Children's to develop protocols for other researchers to access the tool for research.