- Cloud Providers Reaffirm Support for Healthcare Interoperability
- Providence St. Joseph Health to Deploy Cloud-Based Health IT with AI
Through support from AWS Machine Learning Research, Pitt and CMU researchers expect to accelerate development and product commercialization efforts across eight initiatives.
These initiatives those with the potential to generate an individual risk rating for each cancer patient, use verbal and visual indications of a patient to diagnose and treat symptoms of mental health, and decrease medical diagnostic mistakes by mining information in the medical record of a patient.
“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.”
Pitt Team Uses AWS to Improve Treatment of Aneurysms
A Pitt research team led by David Vorp, Ph.D., are employing AWS cloud resources to enhance the diagnosis and therapy of abdominal aortic aneurysms, a leading cause of death in Western countries.
“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,” said Vorp, associate dean for research at Pitt’s Swanson School of Engineering.
In addition, a CMU research team led by Russell Schwartz, Ph.D., and Jian Ma, Ph.D., will use AWS support to generate algorithms and develop software tools to better understand tumor cell origin and evolution. This project will use machine learning to obtain insight into the development of tumors and predict how they are likely to grow in the future.
“Data-driven, genomic methods guided by an understanding of cancers as evolutionary systems have relevance to numerous aspects of clinical cancer care,” said Schwartz, professor of biological sciences and computational biology at CMU. “These include determining which precancerous lesions are likely to become cancers, which cancers have a good or bad prognosis, and which of those with bad prognoses might respond long-term to specific therapies.”
The PHDA combines health sciences research at Pitt, computer science and machine learning at CMU, and clinical care, patient information, and commercialization knowledge at UPMC.
“This collaboration with AWS complements the unique strengths of the PHDA’s founders and will provide unparalleled resources to our researchers,” said Tal Heppenstall, president of UPMC Enterprises, which funds the PHDA’s work. “By leveraging AWS machine learning and artificial intelligence services, we can help Pittsburgh become the premier hub of technology innovation in health care, drawing innovators from companies big and small to join us in this critical effort to revolutionize the delivery of health care.”
UCLA Deploys Azure Cloud for AI-Powered Medical Research
In May, UCLA Health announced a similar cloud alliance with Microsoft Azure to enable AI and machine learning for medical research.
UCLA said it would use Azure cloud computing tools to process large volumes of data and identify data patterns.
“The integration of information from structured data, like lab results and medication information, with unstructured data, like documentation, genomics and medical images, creates an incredibly powerful big-data learning platform for discovery,” explained Michael Pfeffer, M.D., assistant vice chancellor and CIO for UCLA Health Sciences.
Mohammed Mahbouba, M.D., chief data officer for UCLA Health Sciences, commented: “Analyzing large data sets to make scientific discoveries is a race against time. Using machine learning to analyze a combination of clinical and genomics data can provide critical insights, but doing so with a traditional computing infrastructure can require significant processing time. Azure enables us to quickly deploy and scale high-performance computing environments that can reduce the required processing time — sometimes from months to days — to make discoveries.”