2014 to 2020
Learning from real doctor-patient conversations
SOPHIE began in 2014 with a conversation with Ronald Epstein at the University of Rochester Medical Center. We analyzed 386 conversations between oncologists and patients with late-stage cancer. Two patterns stood out: lecturing (long one-sided stretches) was linked to patients misunderstanding their prognosis, while delivering technical information and ending on positive language was linked to better understanding. We also found differences in communication styles by gender.
-
Modeling Doctor-Patient Communication with Affective Text Analysis
Analyzing the emotional content of doctor-patient conversations to model communication in cancer care.
-
What Computers Can Teach Us About Doctor-Patient Communication: Leveraging Gender Differences in Cancer Care
Computational analysis of cancer-care conversations reveals gender differences in doctor-patient communication.
-
Using Artificial Intelligence to Analyze and Teach Communication in Healthcare
How AI can analyze and help teach communication between clinicians and patients.





