Amazon and Pitt Health Data Alliance Strike Machine Learning Deal for Patient Care

Amazon’s trek into healthcare continues through a machine learning research sponsorship with the Pittsburgh Health Data Alliance (PHDA) aimed at improving cancer diagnostics, precision medicine, voice-enabled technologies and medical imaging.

The PHDA uses big data generated in healthcare to progress the treatment and prevention of diseases. Through the sponsorship, scientists from the University of Pittsburgh and Carnegie Mellon University hope to accelerate research and product commercialization efforts across eight projects.

Zariel Johnson, Ph.D., program manager at University of Pittsburgh Medical Center Enterprises who is overseeing the PHDA projects, told Inside Digital Health™ that four of the projects fit into the area of precision and personalized medicine.

“These projects will focus on how to perform analyses on existing data to better predict the right treatment of an individual patient or what the best timing of the treatment is,” Johnson said.

Two of those projects will use genomic data, while the other two will use imaging and outcomes data to build better tools to understand what types of treatments are best, she said.

“The other four projects announced have more of a diverse area of focus,” Johnson continued.

Two will be related to voice and speech, one will focus on multimodal learning to better understand the risk of breast cancer and the final project is related to medical coding.

“All eight projects are ones that can benefit from using cloud computing or machine learning resources that Amazon Web Services can make available,” she said. “By using those tools, the research teams have a better ability to scale prototypes and do testing and training more efficiently, rather than using local servers.”

Scaling the prototypes could allow such technologies and resources to be implemented more easily into a healthcare system, she said.

“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, Ph.D., vice president of machine learning for Amazon Web Services. “We are excited to bring our machine-learning services and cloud computing resources to support the high-impact work being done at the PHDA.”

David Vorp, Ph.D., associate dean of research at Pitt’s Swanson School of Engineering, and his research team are using Amazon Web Services tools to improve the diagnosis and treatment of abdominal aortic aneurysms.

“With the latest advances in machine learning, we are developing an algorithm that will provide clinicians with an objective, predictive tool to guide surgical interventions before symptoms appear, improving patient outcomes,” Vorp said.

A Carnegie Mellon University research team also plans to use Amazon Web Services resources to develop algorithms and software to better understand the origin and evolution of tumor cells. The researchers will use machine learning to learn more about the development of tumors and to predict how they will change in the future.

“By leveraging (Amazon Web Services) machine learning and artificial intelligence services, we can help Pittsburgh become the premier hub of technology innovation in healthcare, drawing innovators from companies big and small to join us in this critical effort to revolutionize the delivery of healthcare,” said Tal Heppenstall, president of University of Pittsburgh Medical Center Enterprises.

Get the best insights in digital health directly to your inbox.

RELATED

Amazon's Path of Disruption

UPMC Forms Telemedicine Company for Infectious Diseases

$1.5 Trillion for Disruption? Amazon, Google, Silicon Valley Try to Upend Healthcare