Please consider downloading the latest version of Internet Explorer
to experience this site as intended.
Skip to content

In Review: Artificial Intelligence

Helping Doctors with Hard ConversationsA friendly virtual patient aims to teach physicians how to talk about the end of life.By Bob Marcotte
University of Rochester MEET SOPHIE: Appearing as a real-life human face, the AI-generated avatar is designed to help physicians have difficult conversations. (Photograph: Courtesy of Ehsan Hoque Lab)

It’s a hard pill for doctors to swallow: Studies show that as many as 68 percent of late-stage cancer patients leave their doctor’s offices either underestimating the severity of their disease, overestimating their life expectancy—or both.

Such misunderstandings can hinder the ability of patients and their families to make realistic decisions about whether to continue aggressive treatments or instead turn to palliative care.

To address the problem, a team of Rochester computer scientists, palliative care specialists, and oncologists have created SOPHIE (Standardized Online Patient for Healthcare Interaction Education)—an online virtual “patient” that helps physicians practice how to communicate effectively with late-stage cancer patients about their disease. SOPHIE appears as a real-life—albeit AI-derived—human face and voice on the user’s screen.

“During difficult conversations about facing the potential of one’s own death, patients are frightened and don’t know how to ask the right questions, and clinicians may oversimplify, omit, or sugarcoat information, or feel too pressed for time to address patients’ emotions,” says Ehsan Hoque, an associate professor of computer science.

SOPHIE was made possible by a body of nearly 400 conversations that were recorded between late-stage cancer patients and their oncologists, and initially analyzed by Medical Center palliative care expert Ronald Epstein, a professor of family medicine, psychiatry and oncology, and his colleagues.

Mohammad Rayafet Ali, a postdoctoral researcher, and PhD student Taylan Sen, both members of Hoque’s Human-Computer Interaction Lab, created algorithms that could be applied to the transcripts of the conversations so the researchers could develop metrics to assess a physician’s ability to communicate clearly with patients.

The metrics focus specifically on the extent to which physicians engage in lecturing—delivering a lot of information without giving the patient a chance to ask questions or to respond—or, on the plus side, how well they employ positive words and phrases in ways associated with increased patient understanding.

While doctors may also work with human actors, SOPHIE “can provide training at a fraction of the cost and be available to physicians worldwide,” says Epstein.