UPMC to Fund Six Projects Through Pittsburgh Health Data Alliance

In an effort to solve some of health care’s toughest challenges through the innovative use of technology, UPMC Enterprises will fund six projects created under the umbrella of the Pittsburgh Health Data Alliance.

Announced in March 2015, the alliance is a unique collaboration among the University of Pittsburgh, UPMC, and Carnegie Mellon University (CMU). It will focus on building new companies that create data-intensive software and services to improve health care delivery.

With this first round of funding, researchers from Pitt and CMU will develop technologies aimed at reducing patient falls, preventing and monitoring pressure ulcers, improving the accuracy of cancer diagnoses, and providing personalized treatment recommendations. UPMC’s funding for these innovations is expected to total more than $3 million over the next six months, as the commercial potential of these products is further explored.

“We are excited to move forward with the first of many exceptional ideas in the Health Data Alliance pipeline,” said Tal Heppenstall, president of UPMC Enterprises. “This promising start bodes well for the alliance’s goal of transforming health care by unleashing the creativity and entrepreneurialism of leading scientists and clinicians in Pittsburgh.”

One of the funded projects is being developed by the alliance’s CMU-led Center for Machine Learning and Health, which is headed by Eric Xing, a professor in the Department of Machine Learning, CMU School of Computer Science.

Called the Clinical Genomics Modeling Platform, this project’s technology will serve as an engine to build precision-medicine models for various diseases and populations. It could help doctors determine, for example, whether patients with a certain disease should be sent home with monitoring or sent to the intensive care unit. Leading the platform’s development are Carl Kingsford and Christopher Langmead, both associate professors of computational biology at CMU.

The remaining five projects are being developed by Pitt’s Center for Commercial Applications of Healthcare Data, which is led by Michael Becich, professor and chair of the Department of Biomedical Informatics, Pitt School of Medicine. Descriptions of the five projects follow.

• MEDIvate, a smartphone application intended to make it easy for patients to update and share medication lists. It will also remind patients to take their medications. The project is led by Philip Empey, an assistant professor, and James Coons, an associate professor, both in Pitt’s School of Pharmacy.

• The Tumor-Specific Driver Identification (TDI) System, software that will provide personalized genomic information to cancer clinicians about the genetic drivers of an individual patient’s tumors. Tumor-specific algorithms will be used for real-time mining of genetic “big data” to enable personalized treatments for cancer patients. TDI also is expected to lead to the discovery of new cancer drivers and may be used by pharmaceutical companies to identify novel drugs. Project investigators are Xinghua Lu and Gregory Cooper, associate professor and professor, respectively, in Pitt’s Department of Biomedical Informatics.  

• Fall Sentinel, an automated system that will enable clinical pharmacists to continuously monitor patients in nursing homes, especially for potential drug interactions that might lead to falls. The project is led by Richard D. Boyce, a Pitt assistant professor in biomedical informatics.

• PUMP, a monitoring and alert system aimed at reducing hospital-acquired pressure ulcers, which affect an estimated 3 million patients annually. J. Peter Rubin, UPMC Endowed Professor and Chair of Plastic Surgery, Pitt School of Medicine, is spearheading this effort.

• ComPACD, or Computational Pathology for Accurate Cancer Diagnosis, a software to help pathologists provide more accurate diagnoses from complex tumor images. The initial focus will be on breast cancer. The principal investigators are D. Lansing Taylor, the Allegheny Foundation Professor of Computational and Systems Biology, and Chakra Chennubhotla, an associate professor in Pitt’s Department of Computational and Systems Biology.  

As the project leaders develop these technologies and assess their broader market potential, it is possible that UPMC Enterprises may provide additional funding and development, Heppenstall said.