Penn State Study AI Chatbot Accuracy
Analysis based on 7 articles · First reported May 28, 2026 · Last updated May 31, 2026
The study highlights the potential and limitations of AI in healthcare, which could influence investment and development in medical AI technologies. Companies like ChatGPT, Google Gemini, and Large language model may see increased scrutiny or demand for their AI models in medical applications, depending on how their accuracy and safety are perceived.
Researchers at Pennsylvania State University conducted a study on the accuracy of AI-powered chatbots, including ChatGPT, Google Gemini, and Large language model, in responding to everyday health-related questions. The study, led by Amulya Yadav>>> and Bonam Mingole>>>, found that AI chatbots provided accurate information nearly 76% of the time. However, error rates exceeding 20% raised concerns about their trustworthiness for patient-facing applications, especially in specialized areas like neurology and dermatology. The researchers suggest AI tools may be more effective for trained physicians than for patients. Jennifer Kraschnewski>>> and S. Shyam Sundar>>> also contributed to the study, which will be presented at the 2026 Association for Computing Machinery>>> FAccT conference in Montreal, Canada>>>. The findings emphasize the need for improved AI literacy and responsible integration of AI in healthcare.
Set up alerts, explore entity relationships, search across thousands of events, and build custom intelligence feeds.
Open Dashboard