Pittsburgh Health Data Alliance, AWS join on machine learning effort

A consortium of three Pittsburgh institutions, focused on turning big data into better health, is joining forces with Amazon Web Services as part of a machine learning research sponsorship.

The Pittsburgh Health Data Alliance, which includes Carnegie Mellon University, the University of Pittsburgh and UPMC, will leverage AWS machine learning services to improve patient care through cancer diagnostics, precision medicine, voice-enabled technologies and medical imaging.

“New machine learning technologies and advances in computing power, like those offered by Amazon SageMaker and Amazon EC2, are making it possible to rapidly translate insights discovered in the lab into treatments and services that could dramatically improve human health,” according to PDHA’s announcement.


Also See: UPMC cuts hospital readmission rates with ML algorithm

“We believe that machine learning can significantly accelerate the progress of medical research and help translate those advances into treatments and improved experiences for patients,” said Swami Sivasubramanian, vice president of machine learning for AWS. “We are excited to bring our machine learning services and cloud computing resources to support the high-impact work being done at the PHDA.”

As part of the initiative, PHDA researchers from CMU and Pitt will engage in eight projects, including an effort to create an individual risk score for cancer patients, enabling doctors to better predict the course of their disease and response to treatment.

UPMC Enterprises, the integrated health system’s commercialization arm, funds PHDA—which was formed in 2015—and UPMC will provide de-identified clinical data to support the projects under the machine learning research sponsorship with AWS.

“UPMC is a customer of AWS,” comments Rob Hartman, director of translational science at UPMC Enterprises. “It’s also important to note that AWS is building cloud-based tools and resources to support innovation and cutting-edge research and applications in healthcare.”

Hartman contends that PHDA includes three complementary Pittsburgh-based institutions bringing together CMU’s world-class computer science and machine learning, Pitt’s expertise in biomedical research, and UPMC’s academic medical center.

“AWS has a great track record of working with academic researchers and institutions, and have an understanding of what those needs are in the academic setting,” says Zariel Johnson, a program manager at UPMC Enterprises, who manages PHDA’s day-to-day activities.

According to Johnson, four of the projects that AWS is supporting as part of this machine learning research sponsorship fall into the category of precision and personalized medicine. She adds that an overall goal of PHDA is to select projects that have the potential for commercialization.

AWS’s primary role in the machine learning research sponsorship with PHDA is to “enhance those projects, not only with their funding, but also with the resources and expertise that they can provide—particularly on the computational side,” adds Hartman.