Study uses computer algorithms to understand doctor-patient communication

A computer analysis of hundreds of thousands of secure e-mail messages between physicians and patients revealed that most physicians use language that is too complex for their patients to understand. The study also revealed strategies some doctors use to overcome communication barriers.

Health literacy experts, as well as major healthcare organizations, have advised physicians to always use plain language when explaining things to their patients, to avoid confusing those with the least amount of disease. health literacy.

But the study found that most doctors didn’t do this. Only about 40% of patients with low health literacy had doctors who used plain language with them.

Effective electronic communication is becoming increasingly important as physicians and patients rely more on secure messaging, an innovation that rapidly developed during the COVID-19 pandemic. The study found that physicians who performed best in surveys of patient understanding of their care tended to tailor their email messages to their patients’ level, regardless of their level of health literacy. .

“We discovered a combination of attitudes and skills essential to physician-patient communication,” said Dean Schillinger, MD, professor of medicine and primary care physician at UC San Francisco (UCSF) and co-lead author of the article, Posted in Scientists progress on December 17, 2021. “We were able to prove that this type of ‘precision communication’ is important for all patients in terms of understanding.”

The study used computer algorithms and machine learning to measure the linguistic complexity of physicians’ messages and the health literacy of their patients.

Using data from more than 250,000 secure messages exchanged between diabetic patients and their physicians through Kaiser Permanente’s secure messaging portal, the study sets a new bar for the research scale on physician-patient communication, which is typically done with much smaller data sets and often does not use objective metrics.

The algorithms assessed whether patients were being treated by doctors whose language matched theirs. Next, the research team analyzed the general trends of each physician, to see if they tended to tailor their communications to the different levels of health literacy of their patients.

“Our computer algorithms extracted dozens of linguistic features beyond the literal meaning of words, examining how words were arranged, their psychological and linguistic characteristics, what part of speech they were, how often they were used and their salience. emotional, ”said Nicholas Duran. , PhD, cognitive scientist and associate professor in the School of Social and Behavioral Sciences at Arizona State University and co-first author of the article.

Patients’ ratings of how they understood their physicians most likely reflected what they thought of their physician’s verbal and written communications. But the grades were nonetheless strongly correlated with the physician’s written communication style.

“Unlike a clinic encounter, where a doctor can use visual cues or verbal comments from each patient to verify understanding, in an email exchange a doctor can never be sure their patient has understood. the written message, ”said Andrew Karter, lead author of the study. , PhD, Principal Investigator at the Kaiser Permanente Northern California Division of Research. “Our results suggest that patients benefit when physicians tailor their email messages to the complexity of the language used by the patient.”

Source link

Comments are closed.