Project Summary

One of PCORI’s goals is to improve the methods that researchers use for patient-centered outcomes research. PCORI funds methods projects like this one to better understand and advance the use of research methods that improve the strength and quality of comparative effectiveness research.

What is the project about?

Researchers can use electronic health record, or EHR, data from multiple clinics to compare treatments. But these data may include personal information, like names or social security numbers, that could identify patients. Also, patients receiving care at clinics may differ in ways that are important for research. For example, patients at one clinic may be older or sicker than patients at another clinic.

In this study, the research team is creating methods for combining EHR data from multiple clinics. The new methods account for differences across clinics but don’t require sharing personal health data.

How can this project help improve research methods?

Results may help researchers protect patients’ privacy when combining EHR data from multiple clinics. Also, results may help researchers identify patients at high risk for specific health problems.

What is the research team doing?

The research team is developing methods to combine and analyze EHR data from multiple health clinics. The team is testing the methods using data from a national children’s research network. Then, the team is looking to see if the methods can predict which children are at high risk of adverse health events, such as infections from Crohn’s disease.

Research methods at a glance

Design Element Description
  • Develop regression methods for combining and analyzing EHR data from multiple healthcare providers without sharing patient-level information
  • Develop methods to predict risk of having a specific health problem
  • Evaluate the effectiveness of the proposed methods in predicting risk of adverse health events from pediatric Crohn’s disease
Approach Distributed algorithms for regression models

Project Information

Yong Chen, PhD, MA
University of Pennsylvania
An Efficient Distributed Learning Framework for Integrating Evidence in Clinical Research Networks

Key Dates

June 2020
January 2024


Award Type
State State The state where the project originates, or where the primary institution or organization is located. View Glossary
Last updated: January 24, 2024