AI Points the Way to Better Doctor-Patient Communication

Medical doctors commonly use language that patients cannot understand, according to an analysis of more than 250,000 secure emails conducted by researchers at the University of California, San Francisco, Arizona State University, and insurer Kaiser Permanente.

The researchers used computer algorithms and machine learning to quantify the linguistic complexity of doctors' communications and the health literacy of patients. Algorithms analyzed word arrangement, psychological and linguistic properties, frequency, and emotional saliency, says Arizona State's Nicholas Duran. Patients' ratings of their doctors strongly corresponded with doctors' written communication style.

"Our findings suggest that patients benefit when doctors tailor their email messages to match the complexity of language the patient uses," says senior research scientist Andrew Karter at Kaiser Permanente.

From University of California, San Francisco
View Full Article

Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA