OpenAI's ChatGPT is Eng Subno closer to replacing your family physicians, as the increasingly advanced chatbot failed to accurately diagnose the vast majority of hypothetical pediatric cases.
The findings were part of a new study published in JAMA Pediatrics on Jan. 2, conducted by researchers from Cohen Children's Medical Center in New York. The researchers analyzed the bot's responses to requests for medical diagnosis of child illnesses and found that the bot had an 83 percent error rate across tests.
SEE ALSO: 5 ways AI changed the internet in 2023The study used what are known as pediatric case challenges, or medical cases originally posted to groups of physicians as learning opportunities (or diagnostic challenges) involving unusual or limited information. Researchers sampled 100 challenges published on JAMA Pediatrics and NEJM between the years 2013 and 2023.
ChatGPT provided incorrect diagnoses for 72 out of 100 of the experimental cases provided, and generated 11 answers that were deemed "clinically related" to the correct diagnosis but considered too broad to be correct.
This Tweet is currently unavailable. It might be loading or has been removed.
The researchers attribute part of this failure to the generative AI's inability to recognize relationships between certain conditions and external or preexisting circumstances, often used to help diagnose patients in a clinical setting. For example, ChatGPT did not connect "neuropsychiatric conditions" (such as autism) to commonly seen cases of vitamin deficiency and other restrictive-diet-based conditions.
The study concludes that ChatGPT needs continued training and involvement of medical professionals that feeds the AI not with an internet-generated well of information, which can often cycle in misinformation, but on vetted medical literature and expertise.
AI-based chatbots relying on Large Language Models (LLMs) have been previously studied for their efficacy in diagnosing medical cases and in accomplishing the daily tasks of physicians. Last year, researchers tested generative AI's ability to pass the three-part United States Medical Licensing Exam — It passed.
But while it's still highly criticized for its training limits and potential to exacerbate medical bias, many medical groups, including the American Medical Association, don't view the advancement of AI in the field just as a threat of replacement. Instead, better trained AI's are considered ripe for their administrative and communicative potential, like generating patient-side text, explaining diagnoses in common terms, or in generating instructions. Clinical uses, like diagnostics, remain a controversial, and hard to research, topic.
To that extent, the new report represents the first analysis of a chatbot's diagnostic potential in a purely pediatric setting — acknowledging the specialized medical training undertaken by medical professionals. Its current limitations show that even the most advanced chatbot on the public market can't yet compete with the full range of human expertise.
Topics Artificial Intelligence Social Good
John Oliver calls out his boss AT&T for its stance on Texas abortion banMary Elizabeth Winstead kills it in Netflix's 'Kate': ReviewTwitter has started showing which accounts are run by botsEpic Games scores partial victory in legal battle royale with AppleApple Store goes down ahead of 'California Streaming' eventMoonPie Twitter has evolved to making dad jokesThe truly insidious 'WandaVision' bop picked up a wellHow to access Instagram's 'On This Day' featureTrump just defended Rob Porter again and it is extremely problematicWhat the Apple vs. Epic ruling means for the rest of Big TechApple Store goes down ahead of 'California Streaming' eventInternet nostalgia: Revisiting the memeNo, Walmart will not be accepting Litecoin. Here's how people were duped.A guide to restricting creeps from your Instagram profileApple Watch 8 might have a temperature sensor14 best tweets of the week, including frong, floor poisoning, and wings dinnerThis mouse riding on a cop's windshield is public enemy no. 1How to access Instagram's 'On This Day' featureHow to set a song as your ringtone on iPhoneThis teen slept through his alarm because of Netflix and still won gold at the Olympics 'Leave no trace' isn't just for Burning Man. Let's all declare war on MOOP. Netflix's 'Daybreak' sinks an ambitious premise with misguided dark comedy Greta Gerwig's 'Little Women' first reactions: An original take on a beloved classic You can’t lurk on Instagram anymore unless you’re logged in Norton Secure VPN will help secure your connection Snapchat is still growing where it matters most 1 key moment from the new 'Star Wars' trailer has fans seriously panicking Dads, like moms, are at risk of depression after a child’s birth, researchers report Instagram adds 'false information' labels to prevent fake news from going viral This model of Donald Trump's awful handshake is hilariously on Lizzo credits viral tweet for the most iconic line in 'Truth Hurts' Now you can get magically stupefied in a 'Harry Potter' Trump decries 'tremendous increase' in U.S. autism cases. But it's not so simple. Play of the day: Under Armour CEO publicly wallows in regret for Trump comments Yes, Twitter was down Chance the Rapper didn't buy that Eric Andre was dating Rosario Dawson Huawei's foldable Mate X phone goes on sale on November 15 at a staggering price 'Arrow' tackles the gun debate to 'start a conversation' How to cope when your best friend falls in love and pulls away from you 'Watchmen': Everything you need to know from the comic after Episode 1
2.3177s , 10134.4765625 kb
Copyright © 2025 Powered by 【Eng Sub】,Openness Information Network