By using this site, you agree to our Privacy Policy and Terms of Use.
Accept
VellaTimesVellaTimesVellaTimes
  • News
    NewsShow More
    A large Cerebras artificial intelligence processor resting in front of illuminated server racks in a modern data center.
    OpenAI Strikes $20B Cerebras Chips Deal for AI Power
    April 17, 2026
    A sleek corporate boardroom overlooking Silicon Valley at dusk, featuring a glowing holographic projection of a data tree and the text $7 Billion hovering over a conference table.
    Sequoia Capital AI Fund: Firm Secures $7 Billion for Growth
    April 17, 2026
    Oncology specialists review digital cancer scans and biomarker data on large screens in a modern hospital setting.
    Precision Medicine in Cancer Care Gains Pace in 2026
    April 16, 2026
    Wide view of a modern data center next to power transmission infrastructure in an industrial setting.
    AI Infrastructure Spending Surges as Power Costs Rise
    April 16, 2026
    A glowing artificial intelligence microchip resting on a server rack inside a modern, brightly lit data center.
    Meta Broadcom AI Chip Deal Expands Through 2029
    April 16, 2026
  • Technology
    TechnologyShow More
    A sleek corporate boardroom overlooking Silicon Valley at dusk, featuring a glowing holographic projection of a data tree and the text $7 Billion hovering over a conference table.
    Sequoia Capital AI Fund: Firm Secures $7 Billion for Growth
    April 17, 2026
    A glowing artificial intelligence microchip resting on a server rack inside a modern, brightly lit data center.
    Meta Broadcom AI Chip Deal Expands Through 2029
    April 16, 2026
    A sleek Amazon-branded satellite orbiting Earth against the deep black of space and the glowing blue curvature of the planet.
    Amazon Globalstar Acquisition: $11.57 Billion Deal Challenges Starlink
    April 16, 2026
    A glowing holographic shield with digital code and the text GPT-5.4-Cyber floating in a modern, neon-lit server room.
    OpenAI Unveils GPT-5.4-Cyber to Counter Anthropic in Escalating AI Security Race
    April 16, 2026
    A futuristic data center showing an intricate gold quantum computer connected to modern AI server racks with glowing blue and green cables.
    Nvidia Launches Open-Source Ising AI Models to Accelerate Quantum Computing
    April 15, 2026
  • AI
    AIShow More
    A large Cerebras artificial intelligence processor resting in front of illuminated server racks in a modern data center.
    OpenAI Strikes $20B Cerebras Chips Deal for AI Power
    April 17, 2026
    Wide view of a modern data center next to power transmission infrastructure in an industrial setting.
    AI Infrastructure Spending Surges as Power Costs Rise
    April 16, 2026
    A person sits at a desk looking at a laptop with a chatbot error message on screen, with a phone nearby in a modern office setting.
    ChatGPT Outage Hits Users Again in Global Disruption
    April 16, 2026
    Wide header image of a modern tech conference stage showing AI developer tools, code visuals and smartphone interface graphics on large presentation screens.
    Apple AI Developers Gain New On-Device Tools at WWDC
    April 16, 2026
    A glowing tablet displaying futuristic financial charts on a modern glass desk, symbolizing the intersection of artificial intelligence and personal finance technology.
    OpenAI Acquires AI Personal Finance Startup Hiro Finance
    April 15, 2026
  • Science
    ScienceShow More
    Oncology specialists review digital cancer scans and biomarker data on large screens in a modern hospital setting.
    Precision Medicine in Cancer Care Gains Pace in 2026
    April 16, 2026
    A clear glass being filled with tap water from a kitchen faucet, with a blurred paper in the background suggesting a scientific study.
    Fluoride and IQ Study Finds No Harm in Drinking Water
    April 16, 2026
    A vibrant network of galaxies and stars in deep space, illustrating the measurement of cosmic distances and the expansion of the universe.
    Hubble Tension Deepens With New Universe Expansion Rate
    April 15, 2026
    A medical researcher in protective gear examining samples under a microscope with a softly blurred dairy farm in the background, representing the study of H5N1 bird flu.
    H5N1 Bird Flu Threat: Viral Mutations and Rising Mammal Infections
    April 15, 2026
    The sunlit Orion spacecraft travels through deep space as a darkened Moon fully eclipses the Sun, revealing a glowing solar corona against a star-filled background.
    Artemis II Lunar Flyby Success Shifts Focus to Moon Landers
    April 15, 2026
  • World
    WorldShow More
    Allu Arjun Commitment to Ethical Brand Partnerships
    Exploring Allu Arjun’s Commitment to Ethical Brand Partnerships
    December 18, 2023
    Orry aka Orhan Awatramani
    Orhan Awatramani ‘Orry’ Biography, Lifestyle and Rise to Fame
    December 8, 2023
    Alia Bhatt Latest Deepake Video Victim
    Alia Bhatt becomes latest victim of Deepfake Videos, Obscene Video goes Viral
    November 28, 2023
    Napoleon Movie Review
    Napoleon Movie Review: A Historical Epic by Ridley Scott Reviewed
    November 25, 2023
  • Bookmarks
Search
Category
  • News
  • Technology
  • AI
  • Science
  • World
Company
  • About Us
  • Contact Us
  • Fact Checking Policy
  • Terms & Conditions
  • Privacy Policy
  • Copyright Policy
Resources
  • Home
  • Web Stories
  • Bookmarks
  • Interests
  • Disclaimer
  • Sitemap
© 2022 VellaTimes • All Rights Reserved.
Reading: AI Medical Advice Study Finds Chatbots Wrong Half the Time
Share
Notification Show More
Font ResizerAa
VellaTimesVellaTimes
Font ResizerAa
  • News
  • Technology
  • AI
  • Science
  • World
Search
  • Explore
    • News
    • Technology
    • AI
    • Science
    • World
  • Useful Links
    • About Us
    • Contact Us
    • Fact Checking Policy
    • Terms & Conditions
    • Privacy Policy
    • Copyright Policy
  • Home
  • Web Stories
  • Bookmarks
  • Interests
  • Disclaimer
  • Sitemap
© 2022 VellaTimes • All Rights Reserved.
News

AI Medical Advice Study Finds Chatbots Wrong Half the Time

Nisha Pradhan
Last updated: 16/04/2026
Nisha Pradhan
Share
6 Min Read
Smartphone displaying a generic AI health chatbot next to a doctor’s desk with medical items in a modern clinic office.

AI medical advice from major chatbots, including ChatGPT, Gemini, Meta AI, Grok, and DeepSeek, was problematic in about half of the tested responses in a study published in BMJ Open, adding to concerns about how people use these tools for health questions. The researchers found that 49.6% of answers were problematic, including 19.6% that were rated highly problematic.

Contents
What the researchers testedWhere chatbots struggled mostReference problems deepen concernsPublic use is growing

The findings arrive as more Americans say they are already using artificial intelligence for health information and advice. A West Health-Gallup Center on Healthcare in America poll published Wednesday found that roughly one-quarter of U.S. adults had used an AI tool for health information or advice in the previous 30 days.

What the researchers tested

The BMJ Open audit was led by a researcher from the University of California at Los Angeles and involved researchers from the United States, Canada and the United Kingdom. The team asked five publicly available chatbots 10 questions across five categories: cancer, vaccines, stem cells, nutrition and athletic performance.

According to the study summary, the questions included both closed-ended prompts with a defined correct answer and open-ended prompts that asked the systems to generate several responses. The prompts were designed to resemble common health questions and online misinformation tropes, while also testing how the models handled advice that could run against medical standards.

Two experts in each category rated the responses as non-problematic, somewhat problematic, highly problematic or potentially harmful. Researchers also examined whether the scientific references offered by the chatbots were accurate and complete, and they measured how easy the answers were to read.

Where chatbots struggled most

The study found that the chatbots generally performed better on closed-ended questions and on topics such as vaccines and cancer. They performed worse on open-ended prompts and in areas such as stem cells, athletic performance, and nutrition.

Researchers also said the chatbots answered with confidence and certainty even when the information was flawed or incomplete. Out of 250 total questions, only two were refused, and both refusals came from Meta AI on questions about anabolic steroids and non-traditional cancer therapies.

Another issue was readability. The study said the responses were scored as difficult, meaning a reader would need at least some college education to understand them comfortably.

Reference problems deepen concerns

The researchers said poor sourcing made the problem harder to spot. The BMJ Open audit found a median reference completeness score of 40%, and it said hallucinations and made-up citations meant none of the chatbots could provide a fully accurate reference list.

A separate study highlighted by the Royal College of Surgeons of England pointed to similar problems in AI-generated surgical information. That analysis reviewed 108 chatbot responses containing 1,249 references and found that in the worst-performing models, 34% of references were fabricated or unverifiable, while several other platforms produced no hallucinated references at all.

The Royal College study also found that some fabricated citations closely resembled real scientific literature and sometimes included invented URLs or attributions to well-known institutions. It said many cited sources were behind academic paywalls, which could make it harder for users to verify medical claims for themselves.

Public use is growing

Polls suggest that people are not waiting for perfect systems before turning to AI for health help. In the Gallup survey, about 7 in 10 recent users said they wanted quick answers, more information, or were simply curious, and majorities said they used AI for research before or after seeing a doctor.

The same report said some people used AI because health care was too expensive or inconvenient to access. About 4 in 10 wanted help outside normal business hours, about 3 in 10 did not want to pay for a doctor visit, and roughly 2 in 10 said they did not have time to make an appointment, had felt ignored in the past, or were too embarrassed to talk to a person.

Trust, however, remains divided. About one-third of adults who had recently used AI for health information said they somewhat or strongly trusted the advice, 34% distrusted it, and 33% said they neither trusted nor distrusted it. The KFF survey also found that about three-quarters of U.S. adults were very or somewhat concerned about the privacy of health information shared with AI tools or chatbots.

Both studies point to the same basic message: AI tools may help people start a health search, but they can still produce unsafe answers or unreliable references. The BMJ Open authors warned that continued deployment without public education and oversight risks amplifying misinformation.

TAGGED: AI medical advice, BMJ Open, ChatGPT, DeepSeek, Gemini, Grok, Health Technology, healthcare AI, medical misinformation, Meta AI
Share This Article
Facebook Twitter Whatsapp Whatsapp Telegram Copy Link
By Nisha Pradhan
I am a passionate content creator with a deep love for travel, music, and food. Using my unique blend of these interests, I genuinely enjoy crafting high-quality travel, lifestyle, and entertainment-related news content.
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *


Most Read

Ola CEO Bhavish Aggarwal unveils new Indian AI Chat App ‘Krutrim’

November 28, 2023

Gemini 3.1 Pro: Google touts new AI reasoning gains

February 21, 2026

Tesla CarPlay delay tied to iOS 26 Maps issue: Report

February 17, 2026

Amazon MGM Studios Launches AI Tools to Speed Up Film and TV Production

February 5, 2026

OpenAI Pentagon Deal Outlines Strict AI Guardrails

March 2, 2026

PixVerse real-time AI video tool adds live control feature

January 15, 2026

Related News

A large Cerebras artificial intelligence processor resting in front of illuminated server racks in a modern data center.
News

OpenAI Strikes $20B Cerebras Chips Deal for AI Power

Sameer Katoch Sameer Katoch April 17, 2026
A sleek corporate boardroom overlooking Silicon Valley at dusk, featuring a glowing holographic projection of a data tree and the text $7 Billion hovering over a conference table.
News

Sequoia Capital AI Fund: Firm Secures $7 Billion for Growth

Rakesh Paul Rakesh Paul April 17, 2026
Oncology specialists review digital cancer scans and biomarker data on large screens in a modern hospital setting.
News

Precision Medicine in Cancer Care Gains Pace in 2026

Nisha Pradhan Nisha Pradhan April 16, 2026

About Us

VellaTimesVellaTimesVellaTimes

VellaTimes is a leading news portal that covers the latest trending news in technology, lifestyle, entertainment, automobiles, travel, and sports.

Explore

  • News
  • Technology
  • AI
  • Science
  • World

Useful Links

  • About Us
  • Contact Us
  • Fact Checking Policy
  • Terms & Conditions
  • Privacy Policy
  • Copyright Policy

Subscribe Us

Subscribe to our newsletter for the Latest News and Top Stories!

© 2022 VellaTimes • All Rights Reserved.
  • Home
  • Web Stories
  • Bookmarks
  • Interests
  • Disclaimer
  • Sitemap
adbanner
AdBlocker Detected
Our site is an advertising supported site. Please whitelist us to support our work.
Okay, I'll Whitelist