AI Points the Way to Better Doctor-Patient Communication

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

Experts on health literacy, as well as leading health care organizations, have advised that doctors always use simple language when explaining things to their patients, to avoid confusing those with the least health literacy.

But the study found that most doctors did not do this. Only about 40 percent of patients with low health literacy had doctors who used simple language with them.

Effective electronic communication is becoming increasingly important, as doctors and patients rely more on secure messaging, an innovation that has rapidly expanded during the COVID-19 pandemic. The study found that the doctors who performed best in surveys of how well patients understood their care tended to tailor their electronic messages to their patients’ level, wherever it was on the spectrum of health literacy.

"There's a combination of attitudes and skills that we discovered is critical to physician-patient communication," said Dean Schillinger, MD, professor of medicine and a primary care doctor at UC San Francisco (UCSF) and co-first author of the paper, published in Science Advances on Dec. 17, 2021. "We were able to prove that this kind of ‘precision communication’ is important to all patients in terms of their understanding."

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

Using data from over 250,000 secure messages exchanged between diabetes patients and their doctors through Kaiser Permanente's secure email portal, the study sets a new bar for the scale of research on doctor-patient communication, which is usually done with much smaller data sets and often does not use objective metrics.

The algorithms evaluated whether patients were cared for by doctors whose language matched theirs. Then, the research team analyzed the individual doctors' overall patterns, to see if they tended to tailor their communications to their patients’ different levels of health literacy.

"Our computer algorithms extracted dozens of linguistic features beyond the literal meaning of words, looking at how words were arranged, their psychological and linguistic characteristics, what part of speech they were, how frequently they were used and their emotional saliency," said Nicholas Duran, PhD, a cognitive scientist and associate professor at the School of Social and Behavioral Sciences at Arizona State University and co-first author of the paper.

Patients' assessments of how well they understood their doctors most likely reflected how they felt about their doctor's verbal and written communications. But the ratings nevertheless strongly correlated with the doctor's written communication style.

"Unlike a clinic encounter, where a doctor can use visual cues or verbal feedback from each patient to verify understanding, in an email exchange, a doctor can never be sure that their patient understood the written message," said the study’s senior author Andrew Karter, PhD, senior research scientist at the Kaiser Permanente Northern California Division of Research. "Our findings suggest that patients benefit when doctors tailor their email messages to match the complexity of language the patient uses."

Schillinger D, Duran ND, McNamara DS, Crossley SA, Balyan R, Karter AJ.
Precision communication: Physicians' linguistic adaptation to patients' health literacy.
Sci Adv. 2021 Dec 17;7(51):eabj2836. doi: 10.1126/sciadv.abj2836

Most Popular Now

Research Shows AI Technology Improves Pa…

Existing research indicates that the accuracy of a Parkinson's disease diagnosis hovers between 55% and 78% in the first five years of assessment. That's partly because Parkinson's sibling movement disorders...

Who's to Blame When AI Makes a Medi…

Assistive artificial intelligence technologies hold significant promise for transforming health care by aiding physicians in diagnosing, managing, and treating patients. However, the current trend of assistive AI implementation could actually...

First Therapy Chatbot Trial Shows AI can…

Dartmouth researchers conducted the first clinical trial of a therapy chatbot powered by generative AI and found that the software resulted in significant improvements in participants' symptoms, according to results...

DMEA sparks: The Future of Digital Healt…

8 - 10 April 2025, Berlin, Germany. Digitalization is considered one of the key strategies for addressing the shortage of skilled workers - but the digital health sector also needs qualified...

DeepSeek: The "Watson" to Doct…

DeepSeek is an artificial intelligence (AI) platform built on deep learning and natural language processing (NLP) technologies. Its core products include the DeepSeek-R1 and DeepSeek-V3 models. Leveraging an efficient Mixture...

Stepping Hill Hospital Announced as SPAR…

Stepping Hill Hospital, part of Stockport NHS Foundation Trust, has replaced its bedside units with state-of-the art devices running a full range of information, engagement, communications and productivity apps, to...

DMEA 2025: Digital Health Worldwide in B…

8 - 10 April 2025, Berlin, Germany. From the AI Act, to the potential of the European Health Data Space, to the power of patient data in Scandinavia - DMEA 2025...