UPMC, Microsoft Partner to Expand Clinical Analytics Infrastructure

Pittsburgh-based UPMC and Microsoft announced a five-year collaboration aimed at expanding and modernizing the health system’s data management, warehousing, and analytics infrastructure to improve patient care.

UPMC began its clinical analytics efforts in 2012. These drove a significant payoff during the COVID-19 pandemic, as UPMC was able to utilize 30 years’ worth of clinical and financial data to develop, assess, and adjust coronavirus response and therapies, according to the press release.

“We’re on a quest to become a true data-driven organization, a ‘learning health system,’” said Oscar Marroquin, MD, chief healthcare data and analytics officer at UPMC, in the press release. “We can do this only if analytics are embedded in everything that we do – from the executive suite to our clinicians at the bedside.”

As part of this vision, UPMC has tapped Microsoft to provide cloud computing, artificial intelligence (AI), and machine-learning (ML) tools to the health system’s clinical analytics team. Using these tools, the analytics team and UPMC clinicians are mining over 13 petabytes of structured clinical data and 18 petabytes of medical imaging data to generate insights that will be used to improve patient care.

“This agreement with Microsoft will allow Oscar and his team to do their work in a faster, more scalable and more sustainable way in the years to come, transforming care for patients,” said Chris Carmody, chief technology officer at UPMC, in the press release. “By modernizing our analytics platform, we’ll also be better able to support expansion and innovation in our Health Plan and other divisions.”

Outside of the pandemic, UPMC has used clinical analytics for other aspects of operations and patient care within the health system. The press release states that UPMC utilizes hourly data feeds across its 40 hospitals, which allows the clinical analytics team to support various quality, finance, innovation, and other improvement efforts.

“Our clinical analytics team enables, with data, the work of all our service lines, service centers and departments,” Marroquin explained. “They partner in a ‘hand and glove’ relationship that starts with data-driven identification of opportunities for continuous improvement of our clinical programs, regardless of where the care is delivered.”

One example of this is a predictive model created by researchers at UPMC and the University of Pittsburgh designed to forecast traumatic brain injury (TBI) outcomes. The model analyzes head computed tomography (CT) scans and clinical data, such as estimates of coma severity and vital signs, blood tests, and heart function information, from TBI patients to predict six-month mortality and other unfavorable outcomes.

The model’s performance was evaluated against the International Mission on Prognosis and Analysis of Clinical Trials in TBI (IMPACT) model and the predictions of three neurosurgeons. The model accurately predicted patient mortality risk and unfavorable outcomes at six months following the traumatic incident, and it outperformed the predictions of the neurosurgeons.