Information School Professor Wanda Pratt is part of a research team that has won funding to analyze patient-doctor communication to detect and provide feedback on implicit biases.

The National Library of Medicine announced $2.8 million to fund the work over the next five years. The "UnBIASED" project is led by Andrea Hartzler, a former doctoral student of Pratt’s who is now an associate professor and co-director of the UW’s Clinical Informatics and Patient-Centered Technologies program. Others on the team include Janice Sabin, an associate professor in Biomedical Informatics and Medical Education at the UW; and Nadir Weibel, an associate professor at the University of California, San Diego.

The project will use “social signal processing,” a computational approach that detects subtle forms of bias that are typically invisible. For example, talk time, interruptions and body movements from health-care providers might differ based on a patient’s race, gender or socioeconomic status.

“These hidden biases can undermine many patient-doctor interactions and they make a difference in the care people receive and the trust they have in the entire health-care establishment,” Pratt said.

By using technology to detect such biases, the researchers hope to provide feedback to clinicians and reduce the disparities as a result. They aim to lay the foundation for training resources that will ultimately improve the quality of care by improving communication between patients and doctors.

“I’ve heard physicians express frustration about poor interactions, and they really want to do what they can to make the relationship as effective as possible,” Pratt said. “Everyone could benefit from identifying and highlighting these hidden biases.”