ChatGPT fails to reliably assess heart risk in patients with chest pain, according to a PLOS ONE study.
ChatGPT fails to reliably assess heart risk in patients with chest pain, according to a study published in the journal PLOS ONE. Researchers from Washington State University and Washington University in St. Louis found that ChatGPT provided inconsistent conclusions and different heart risk assessment levels for the same patient data, making it unreliable for high-stakes clinical situations. The generative AI system also failed to match the traditional methods physicians use to judge a patient's cardiac risk.
May 01, 2024
11 Articles