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?

Many doctors and patients communicate with each other using online messages in patient portals. Patient portals are secure websites where patients can view their health records, see test results, and ask for prescription refills. Patients can also use these portals to send messages to and receive responses from their doctor.

Little research has explored whether and how doctors help patients make treatment decisions through online messaging. Before researchers can study these messages, they must first have a way to remove personally identifiable information, or PII, from the messages.

In this study, the research team is first developing a new way to remove PII from messages in patient portals. The team is then looking at messages to see if doctors share research evidence with patients to help patients make treatment decisions.

How can this project help improve research methods?

Results may help researchers study how patients and doctors communicate through patient portals to help patients make informed decisions.

What is the research team doing?

The research team is using natural language processing, or NLP, to study messages sent between doctors and patients in patient portals. In NLP, computer programs interpret written language. NLP methods use a process called machine learning, where computer programs use data to learn how to perform different tasks with little or no human input.

First, the research team is developing new methods for removing PII from messages. Then, the team is creating a computer program that checks if messages include discussions about treatment options. The team is sharing the new method and program with other researchers at no cost.

Research methods at a glance

Design ElementDescription
GoalTo advance research methods to study whether clinicians and patients communicate about the comparative effectiveness of clinical interventions in real-world clinical care
ApproachNatural language processing, machine learning, computational linguistics

Project Information

Dean Schillinger, M.D.
Mary Reed, Ph.D.
The Regents of the University of California, San Francisco
Employing Computational Linguistics In Patient-Provider Secure Exchanges for Comparative Effectiveness Research (ECLIPPSE-CER)

Key Dates

36 months
March 2023


Award Type
State State The state where the project originates, or where the primary institution or organization is located. View Glossary
Last updated: March 26, 2024