Skip to Content

Astrata Uses NLP to Transform Quality Measurement

For Journalists

Courtney Caprara

Wendy Zellner
Vice President

Want to Make an Appointment or Need Patient Information?
Contact UPMC at


Go to Find a Doctor to search for a UPMC doctor.


PITTSBURGH – As the health insurance industry shifts to digitally measured quality improvement programs, UPMC Enterprises has incubated and launched Astrata, a digital health care quality company. Astrata uses advanced analytics and natural language processing (NLP) to improve value-based care. 


Astrata and its team of data scientists developed cloud-based NLP technologies that allow health insurers to more efficiently analyze unstructured clinical data. This transformative solution generates real-time insights that more accurately assess quality of care and population health against Healthcare Effectiveness Data and Information Set (HEDIS) measures. Both government and private health care payors are increasingly aligning provider compensation to such measures. 


“Traditionally, health insurers use claims information to evaluate health care quality against HEDIS measures. A wealth of additional information is available in medical charts, but it goes uncaptured because the process to extract it is labor-intensive, expensive and unscalable to entire populations,” said Rebecca Jacobson, M.D., M.S., president of Astrata. “Astrata’s unique technology serves as a catalyst for the transition our industry is experiencing and ultimately aims to help health care payors and providers use all the data at their disposal to improve the health of the population as a whole.”


Astrata partnered with UPMC Health Plan, which serves 3.9 million members, to develop and validate its technology. For many important HEDIS measures, health care organizations currently are able to determine their quality rates only once at the end of the year through a manual process, but Astrata’s technology enables year-round monitoring and quality improvement efforts at scale. 


“Over the last two years, UPMC Health Plan abstractors found they can work up to 38 times faster with the implementation of Astrata’s NLP-assisted tools,” said Diane Holder, president and chief executive officer of UPMC Health Plan. “This partnership facilitates a more rapid and accurate flow of thorough, meaningful data between our quality team and our providers.” 


In addition to improving efficiency in HEDIS operations, Astrata is piloting a real-time NLP monitoring platform with UPMC and UPMC Health Plan, focusing first on a HEDIS measure that identifies older women with bone fractures who have not yet received appropriate imaging and intervention for osteoporosis. Identifying candidates for screening often is delayed by months because it relies on claims-based data. Astrata’s tools use NLP to read provider notes and identify members in need of intervention within hours of the fracture occurring. 


Initial findings from the pilot, which began prior to the COVID-19 pandemic, show UPMC Health Plan members signing up for screenings at higher rates after the implementation of Astrata’s technology, possibly because it enabled a UPMC Health Plan representative to contact members more quickly.


“As a 40-hospital health system serving millions of patients across three states, UPMC is always looking for ways to work with our providers and UPMC Health Plan to elevate the quality of care our patients receive. Our work with Astrata to date is only the beginning of understanding how NLP can help us achieve this goal,” said Tami Minnier, chief quality officer, UPMC. 


Jacobson founded Astrata in conjunction with UPMC Enterprises, the innovation and commercialization arm of UPMC. Last year, the company was selected to participate in an exclusive working group assembled by the National Committee for Quality Assurance to determine how NLP can be implemented to improve health care quality measurement. 


Astrata plans to increase its workforce by 30% over the coming year with new opportunities on technical, sales and customer-facing teams.