Polsky, Volpp Lead New Big Data Initiative to Improve Health in Pennsylvania

Polsky, Volpp Lead New Big Data Initiative to Improve Health in Pennsylvania

Amol Navathe, Mitesh Patel and Raina Merchant Head Up Project Teams

The potential of Big Data to significantly improve health requires Big Collaborations, across institutions, sectors, and disciplines. Can Big Data be used to anticipate and avoid adverse health events in hospitals, homes, and communities? The Pennsylvania Department of Health will find out in a new four-year, $5 million grant to the University of Pennsylvania, led by the Leonard Institute of Health Economics (LDI) and funded through the Commonwealth Universal Research Enhancement (CURE) program.

Caption

Dan Polsky, PhD, and Kevin Volpp, MD, PhD will lead the project.

The aptly-named project, Smarter Big Data for a Healthy Pennsylvania: Changing the Paradigm of Healthcare will develop and test algorithms that predict adverse health events in real time in the hospital, in the home, and in the community.  The results could help transform our health care delivery system from one focused on treating expensive clinical events after they occur to one more proactive in targeting disease, community health, and health care access to avoid common and high-risk events before they occur.

Innovative collaborations
The project is led by Dan Polsky, PhD, Executive Director of LDI, and Kevin Volpp, MD, PhD, Director of the LDI Center for Health Incentives and Behavioral Economics.  The work will be a product of an innovative set of collaborations that include researcher teams at both Temple and Carnegie Mellon.  Penn Medicine provides the big-data engine through its  Penn Signals  platform, which has already successfully produced real-time heart failure detection and sepsis alerts during its piloting phase, and will allow for the scaled processing of millions of patient records.  “Having the health system leadership support and the close collaboration of Penn Chief Data Scientist Michael Draugelis has been critical to building a big data research agenda,” said Volpp.

They will use state-of-the-art methods to integrate large datasets (claims, census, surveys), structured and free-text clinical data (from the electronic health record, Operating Room, and Intensive Care Unit), data from mobile devices, and social media data. “Our overall goal is to make new data assets smart and actionable, combining mathematical, statistical, and health economics perspectives to change the way health care is delivered,” said Polsky. He pointed to the unusual combination of institutions, expertise, practitioners, data, and hardware brought together in one project.

Developing predictive models
The research team exploring in-hospital prediction is led by Amol Navathe, MD, PhD, a physician, economist, and engineer with expertise in the use of advanced health data analytics and technology to improve health care. He will work closely with the Penn Signals team to develop prediction models of patients at risk for in-hospital complications of common surgical care, including gallbladder surgery, colorectal surgery, and total joint replacements. The model will be developed at Penn’s Health System and tested at Temple University Health System.

Mitesh Patel, MD, MBA leads the research team exploring at-home prediction.  The goal of this team is to develop models to dynamically predict changes in out-of-hospital risk for 30-day readmission by monitoring medication adherence and physical activity in the home and through the integration of these home data sources with the data from insurance claims and the electronic health record.  Patel’s research leverages concepts from behavioral economics to design connected health approaches to improve individual health behaviors.  This project builds upon his work using wearable devices and smartphone applications to track health behaviors.

To monitor community health, the third team will integrate social media data with statewide data to build and validate a tool to monitor and predict high-morbidity health conditions (heart disease, cancer, chronic lung disease, stroke, and unintentional injury) at a community level.  It will also build computational models to use Twitter data for monitoring and predicting dynamic public health events in the state (e.g., influenza, food-borne illness, infectious outbreaks, and acute environmental exposures). Raina Merchant, MD, MSHP, Director of Penn’s Social Media & Health Innovation Lab, builds upon her prior predictive work using Twitter data. She will lead this multidisciplinary team of physicians, computer scientists, demographers, and health disparities researchers to develop a base for understanding the health and health care uses and limitations of social media platforms.

Vulnerable populations
The potential health benefits for Pennsylvania’s most vulnerable populations are particularly great, given their prevalence of high-risk health events and longstanding barriers to care. The project can address health disparities because it moves our health care system health beyond the walls of the hospital and into homes and communities where the most vulnerable face the greatest challenges.

The project also has a training component to improve the pipeline of minorities entering science and public health careers who are equipped to use Big Data. It will provide opportunities for training in Big Data research through LDI’s Summer Undergraduate Minority Research (SUMR) program, now in its 17th year. Undergraduate scholars from Lincoln University, one of Pennsylvania’s historically black universities, will participate in this 12-week summer internship.