In a new study published online today in Open JAMA Networkresearchers used artificial intelligence to analyze more than 1.4 million electronic health record (HER) emails sent to doctors — and the results aren’t pretty.
Of the emails, 43% were from patients; the rest were mostly from other physicians or clinicians, or were automated. The content of the messages was not associated with physician burnout, as the researchers had assumed. And only about 5% of posts had negative sentiment.
But the researchers were struck by the hostility of that sentiment, displayed in posts like these that would surely be painful for doctors to read:
“I hope and expect you to spend eternity in him**. You are an abusive, mean and cheap person.”
“Your office is full of liars, hypocrites and I will do everything in my power to prevent anyone from visiting your bullshit office again.”
About 5% of emails had an overall negative sentiment, with frequent words like “cancel”, “pain” or “problem”. Of the patient messages, 3% were negative and contained words and swear words suggesting hatred, hostility or violence.
“F***” was the most common expletive used by patients.
Researchers provided examples of posts containing profanity, including one patient who said, “I’m so upset I was told the blood work would include the sex of the baby. I’ve been waiting for 5 years. [days] to find it, and it hasn’t even been tested!!!! What a disappointment in your office and the bullshit I’ve been told. I’m going to change plans because it’s shit!”
The researchers also noted some high-frequency words associated with violence, such as “shoot”, “fight” and “kill”.
“This is concerning, especially given the literature on patient abuse of physicians. Healthcare systems should be proactive in ensuring that the front desk does not become a site of physician abuse and of cyberbullying,” the researchers wrote.
“Posting reminders in EHR patient portals to use kind language when messaging, applying filters for swear words or threatening words, and creating frameworks to identify patients who frequently send negative messages are potential strategies to mitigate this risk.”
Using a form of artificial intelligence technology called natural language processing (NLP), researchers at the University of California, San Diego analyzed the characteristics of more than 1.4 million emails received by university doctors, 43% of whom are patients. They specifically looked at message volume, word count, and overall sentiment.
While other studies have looked at the growing burden of EHR messaging on physicians, this kind of email sentiment analysis could help create solutions. Researchers say such a solution could involve applying filters for swear words or threatening words. It could also help identify fixable health system problems that make patients so angry, the researchers say.
Among doctor-to-doctor emails, just over half mentioned burnout, which corresponded to the following phrases: “I’m starting to burn out and I have one or more symptoms of burnout” and ” I feel completely exhausted”. [and] I’m at the point where maybe I need to ask for help.”
On average, physicians who reported burnout received a higher volume of patient messages. Burnout risks were significantly higher among Hispanic/Latin doctors and women. Physicians with more than 15 years of clinical practice had significantly lower burnout.
Although physicians now spend more time on EHR basket tasks than before the pandemic, the study found no significant association between message characteristics and burnout.
Data for the cross-sectional study was collected from multiple specialties from April to September 2020. Physicians then completed a survey and rated their burnout on a 5-point scale. Of the 609 physician responses, about 49% of participants were female, 56% were Caucasian, and 64% worked as outpatients. About 70% of physicians had been in practice for 15 years or less.
The sentiment score was based on word content as well as the use of negation, punctuation, degree modifiers, capitalization, emoticons, emoticons, and acronyms. Positive messages from patients were more likely to convey gratitude and thanks, as well as casual expressions, such as “fyi” and “lol.”
Steph Weber is a Midwest-based freelance journalist specializing in health care and law.
For more news, follow Medscape on Facebook, TwitterInstagram, YouTube and LinkedIn
#Doctors #email #study #finds #infrequent #noticeable #hostility