Skip to main content

Can AI answer medical questions better than your doctor?

 A second look at a study rating quality and empathy when answering patient questions.

By , Senior Faculty Editor, Harvard Health Publishing; Editorial Advisory Board Member, Harvard Health Publishing

Illustration of woman with brown hair looking at computer screen with healthcare symbol and chatbot robot; concept is AI in healthcare

Last year, headlines describing a study about artificial intelligence (AI) were eye-catching, to say the least:

At first glance, the idea that a chatbot using AI might be able to generate good answers to patient questions isn't surprising. After all, ChatGPT boasts that it passed a final exam for a Wharton MBA, wrote a book in a few hours, and composed original music.

But showing more empathy than your doctor? Ouch. Before assigning final honors on quality and empathy to either side, let's take a second look.

What tasks is AI taking on in health care?

Already, a rapidly growing list of medical applications of AI includes drafting doctor's notes, suggesting diagnoses, helping to read x-rays and MRI scans, and monitoring real-time health data such as heart rate or oxygen level.

But the idea that AI-generated answers might be more empathetic than actual physicians struck me as amazing — and sad. How could even the most advanced machine outperform a physician in demonstrating this important and particularly human virtue?



Can AI deliver good answers to patient questions?

It's an intriguing question.

Imagine you've called your doctor's office with a question about one of your medications. Later in the day, a clinician on your health team calls you back to discuss it.

Now, imagine a different scenario: you ask your question by email or text, and within minutes receive an answer generated by a computer using AI. How would the medical answers in these two situations compare in terms of quality? And how might they compare in terms of empathy?

To answer these questions, researchers collected 195 questions and answers from anonymous users of an online social media site that were posed to doctors who volunteer to answer. The questions were later submitted to ChatGPT and the chatbot's answers were collected.

A panel of three physicians or nurses then rated both sets of answers for quality and empathy. Panelists were asked "which answer was better?" on a five-point scale. The rating options for quality were: very poor, poor, acceptable, good, or very good. The rating options for empathy were: not empathetic, slightly empathetic, moderately empathetic, empathetic, and very empathetic.

What did the study find?

The results weren't even close. For nearly 80% of answers, ChatGPT was considered better than the physicians.

  • Good or very good quality answers: ChatGPT received these ratings for 78% of responses, while physicians only did so on 22% of responses.
  • Empathetic or very empathetic answers: ChatGPT scored 45% and physicians 4.6%.

Notably, the length of the answers was much shorter for physicians (average of 52 words) than for ChatGPT (average of 211 words).

Like I said, not even close. So, were all those breathless headlines appropriate after all?

Not so fast: Important limitations of this AI research

The study wasn't designed to answer two key questions:

  • Do AI responses offer accurate medical information and improve patient health while avoiding confusion or harm?
  • Will patients accept the idea that questions they pose to their doctor might be answered by a bot?

And it had some serious limitations:

  • Evaluating and comparing answers: The evaluators applied untested, subjective criteria for quality and empathy. Importantly, they did not assess actual accuracy of the answers. Nor were answers assessed for fabrication, a problem that has been noted with ChatGPT.
  • The difference in length of answers: More detailed answers might seem to reflect patience or concern. So, higher ratings for empathy might be related more to the number of words than true empathy.
  • Incomplete blinding: To minimize bias, the evaluators weren't supposed to know whether an answer came from a physician or ChatGPT. This is a common research technique called "blinding." But AI-generated communication does not always sound exactly like a human, and the AI answers were significantly longer. So, it's likely that for at least some answers, the evaluators were not blinded.

The bottom line

Could physicians learn something about expressions of empathy from AI-generated answers? Possibly. Might AI work well as a collaborative tool, generating responses that a physician reviews and revises? Actually, some medical systems already use AI in this way.

But it seems premature to rely on AI answers to patient questions without solid proof of their accuracy and actual supervision by healthcare professionals. This study wasn't designed to provide either.

And by the way, ChatGPT agrees: I asked it if it could answer medical questions better than a doctor. Its answer was no.

We'll need more research to know when it's time to set the AI genie free to answer patients' questions. We may not be there yet — but we're getting closer.

Want more information about the research? Read responses composed by doctors and a chatbot, such as answers to a concern about consequences after swallowing a toothpick.

About the Author

photo of Robert H. Shmerling, MD

Robert H. Shmerling, MD, Senior Faculty Editor, Harvard Health Publishing; Editorial Advisory Board Member, Harvard Health Publishing

Dr. Robert H. Shmerling is the former clinical chief of the division of rheumatology at Beth Israel Deaconess Medical Center (BIDMC), and is a current member of the corresponding faculty in medicine at Harvard Medical School. … See Full Bio
View all posts by Robert H. Shmerling, MD
Labels:

Comments

Post a Comment

Popular posts from this blog

Ramadan 2024 Series: Ramadan Reflection

  As a first-year one of the many things I thought about was what Ramadan would be like on campus and how I would manage my workload.  After observing Ramadan on campus for three years on Harvard’s campus, here is my reflection on how to make the most out of Ramadan while doing school work: Sleep early, wake up, stay up As a student, it is typical to stay up late at night to submit assignments on time and catch up on work, but during Ramadan, this can be difficult because we are typically not getting as much sleep due to taraweeh and tahajjud prayers, or other reasons. I have found that I am the most productive when I go to sleep and wake up for suhoor and then stay up. I usually have a suhoor buddy where we ensure both of us are awake to eat before we start fasting at dawn. Remember to take naps in between! Don’t miss Suhoor/Sehri It can be difficult to wake up at 3 or 4 am to eat suhoor, so set up those 10-15 alarms and have a friend who will call or text to ensure you are a...
Post a Comment
Read more

Harvard Housing Day

  Harvard Housing Day is more than just an event; it's a rite of passage, a moment that transcends the ordinary and marks the beginning of a unique chapter in every freshman's life. As a first year to the vibrant Harvard community, your housing day experience will be nothing short of magical, filled with anticipation, excitement, and the thrill of discovering your new home. (Disclaimer, my housing day was on Zoom due to the COVID pandemic so yours is 100% going to be much better than what I went through). In the days leading up to Housing Day, there's an electrifying buzz on campus. Rumors swirl, speculations abound, and there's an air of mystery as students eagerly await the revelation of their assigned house. It's a time of camaraderie and unity as everyone shares the anticipation of discovering where they'll spend the next three years of their college journey.  Of course though, some students will be filled with existential dread as they pray to their gods to...
Post a Comment
Read more