Every year in the United States, 1,400 infants die of sudden infant death syndrome, or SIDS. John Kahan lost his son to SIDS and felt compelled to do something to help other families.
Kahan harnessed the data-crunching power of his employer, Microsoft, and the expertise of researchers at Seattle Children's Research Institute to provide life-saving information.
Kahan travels the world photographing wildlife to raise money for SIDS research.
"Aaron Matthew was born in October of 2003, and shortly after he was born, he stopped breathing," he said.
Aaron died a few days later. His death haunts his parents.
"Actually, as I've gotten older, it's become more real to me that this is something that's unacceptable and it's something that we need to change," Kahan said.
A new dad and Microsoft colleague suggested data science might help researchers gain new insight to causes.
"In order for some of the projects to work, you need expertise in both sides," Microsoft AI Senior Director Juan M. Lavista Ferres said. "You have the data scientists and you, more importantly, you need doctors that understand what the data is saying."
They focused on records of 20 million births and about 19,000 unexplained deaths of infants from the Centers for Disease Control and Prevention. The findings from the data analysis were extremely specific.
"We found that just smoking a single cigarette a day during pregnancy doubles your risk of sudden unexpected infant death," Seattle Children's Research Institute neuroscientist Dr. Tatiana M. Anderson said.
Researchers also learned that smoking within three months of conceiving, even if moms quit in the first trimester, increases SIDS risk by 50%. And if no moms smoked during pregnancy, 800 infant deaths could be prevented every year.
"I'm more optimistic than I've ever been before," Kahan said. "We're actually making progress to be able to understand, to be able to prevent this in the future."
He says that's the miracle of Aaron.
The Microsoft and Seattle Children's team says the first study explains 22% of SIDS deaths. They're working on several more papers that take the same granular look at other causes of SIDS.
Someday, Anderson hopes moms will be able to get genetically screened for risk factors before birth so those can be addressed after the baby is born.
TOPIC: SIDS AND SMOKING: THE MIRACLE OF AARON
REPORT: MB #4587
BACKGROUND: About 3,500 babies in the United States die suddenly and unexpectedly each year. A thorough investigation is necessary to learn what caused these deaths. Sudden unexpected infant deaths include sudden infant death syndrome (SIDS), accidental suffocation in a sleeping environment, and other deaths from unknown causes. Although the sudden unexpected infant death (SUID) rate has declined since 1990s, significant racial and ethnic differences continue. SUID rates per 100,000 live births for American Indian/Alaska Native and non-Hispanic black infants were more than twice those of non-Hispanic white infants. SUID rates per 100,000 live births were lowest among Hispanic and Asian/Pacific Islander infants, and deaths due to SIDS accounted for the largest proportion of SUIDs for most racial/ethnic groups, ranging from 40% of SUID among Hispanic infants to 47% of SUID among American Indian/Alaska Native infants. (Source: https://www.cdc.gov/sids/data.htm)
STUDY: Tatiana Anderson, PhD, a Neuroscientist from Seattle Children's Research Institute said, "we get the data through the CDC and they have a publicly available database where they post data for every single birth in the United States and then link that to death certificates. We analyzed over 20 million births in the United States which included over 19,000 cases of sudden and unexpected infant death. And we partnered with Microsoft and professional data scientists who are able to routinely analyze millions of pieces of data." (Source: Tatiana Anderson, PhD)
NEW RESEARCH: An article in the Seattle Times on this collaboration reads, "One discovery is that women who access prenatal care in their first trimester have a lower-than-average risk of giving birth to a baby that dies of SIDS. Starting prenatal care later than that increases the risk by 30 to 40 percent. The reason may not be the medical care alone. Rather it may be that the doctor visit serves to persuade pregnant women to do things like quit smoking or take vitamins. But the data help policymakers more precisely weigh the cost of things like free prenatal care against the impact." The goal is to create an online work sheet on pregnant women that doctors can fill out to get a view into each patient's risk factors for SIDS. (Source: https://www.seattletimes.com/business/bereaved-father-microsoft-data-scientists-crunch-numbers-to-combat-infant-deaths/)