Oxford Study Suggests AI Presents “Inaccurate” Medical Advice
The investigation, spearheaded by the Oxford Internet Institute and Nuffield Department of Primary Care Health Sciences at the University of Oxford, revealed that depending on AI systems for clinical decision-making endangers patient safety due to a "tendency to provide inaccurate and inconsistent information."
Study co-author Rebecca Payne, who practices as a general practitioner, stated: "Despite all the hype, AI just isn't ready to take on the role of the physician."
"Patients need to be aware that asking a large language model about their symptoms can be dangerous, giving wrong diagnoses and failing to recognize when urgent help is needed," she added.
The research enlisted nearly 1,300 participants to diagnose potential medical conditions and suggest appropriate actions across various clinical scenarios.
Certain participants utilized large language model technology to generate diagnostic assessments, while others employed conventional approaches including general practitioner consultations.
Investigators discovered that AI platforms frequently generated a "mix of good and bad information," leaving users unable to differentiate between reliable and problematic guidance.
Although the chatbots "excel at standardized tests of medical knowledge," researchers concluded their practical application as diagnostic instruments "would pose risks to real users seeking help with their own medical symptoms."
Principal researcher Andrew Bean noted that human interaction remains "a challenge" for even the most advanced AI platforms, expressing optimism that these findings will inform safer technological development.
Legal Disclaimer:
MENAFN provides the
information “as is” without warranty of any kind. We do not accept
any responsibility or liability for the accuracy, content, images,
videos, licenses, completeness, legality, or reliability of the information
contained in this article. If you have any complaints or copyright
issues related to this article, kindly contact the provider above.
Legal Disclaimer:
EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.
