Healthcare is an expensive industry. Every year, the United States spends about $9,000 per capita on healthcare, higher than in many other industrial countries. And despite that extra spending, U.S. health outcomes aren’t any better than countries that spend less — in some instances, they’re worse.
One way to lower costs and increase quality in the healthcare system would be to predict which patients will get sick, and while predicting the future seems impossible, that’s exactly what data science and machine learning startup KenSci is hoping to do. Today the company announced that it has raised $8.5 million in a Series A investment round, led by Ignition Partners, to kick their program into high gear.
KenSci was spun out of the University of Washington Tacoma in 2015 by two childhood friends — professor Ankur Teredesai, who heads the UW Tacoma’s center for data science, and longtime Microsoft exec Samir Manjure.
Its goal is simple: “We are really on a mission to fight death with data science,” Manjure told GeekWire.
“Underneath that, what we’re doing is building a risk prediction platform for healthcare that helps uncover various kinds of risks, whether those be clinical risks, financial risks, or operational risks,” he said.
“Today the healthcare system is more of a disease management system,” said Sunny Neogi, KenSci head of growth.
Patients come to a hospital when they are sick, they explain their symptoms, and receive treatment. But to be truly effective, health care systems need to be more proactive in identifying which patients will have further complications or will likely develop serious diseases, he said.
KenSci’s software attempts to solve this puzzle this by aggregating patient data from a number of existing sources, including data collected from patient devices, electronic medical records, and public records. The platform then assembles the data so its machine learning systems can use it to predict future risks.
The platform is currently being applied the six biggest killers in the U.S., including sepsis, cancer, and heart attacks.
Dr. Greg Mckelvey, KenSci’s head of clinical insights, said one of the biggest challenges in building healthcare technology is how a company approaches working with the healthcare system.
“If you start with technology — if you’re a tool looking for a problem to solve — you’re going to be broken apart on the rocks of the healthcare system and how challenging it is. So we really reversed that, we started with healthcare first,” McKelvey said.
He said KenSci’s founders started by speaking to physicians about the problems they faced in hospitals, “and then really looked into their toolkits as data scientists to find things that could apply and really solve the problems that people are facing on the ground.”
That approach is having a notable effect. Eleven health systems are now using KenSci’s platform, with two more unannounced partnerships in the works. Collectively, they are using the platform to predict risk for over 15 million patients.
“We’re seeing huge traction. The market is hungry for predictive analytics in healthcare,” Neogi said. Part of that excitement is because of the increasing pressure for healthcare systems to move from a volume-based pricing model to a value-based model, where providers charge for positive health outcomes instead of for the number of services a patient receives.
KenSci currenly employs 25 people at its headquarters in downtown Seattle. Investors Osage University Partners and Mindset Ventures also took part in this round of funding.