Does use of generative AI chatbots by patients introduce risk of adverse drug events? DOI
Roger S. McIntyre

Expert Opinion on Drug Safety, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

Language: Английский

Readability, reliability and quality of responses generated by ChatGPT, gemini, and perplexity for the most frequently asked questions about pain DOI Creative Commons
Erkan Özduran, İbrahim Akkoç, Sibel Büyükçoban

et al.

Medicine, Journal Year: 2025, Volume and Issue: 104(11), P. e41780 - e41780

Published: March 14, 2025

It is clear that artificial intelligence-based chatbots will be popular applications in the field of healthcare near future. known more than 30% world's population suffers from chronic pain and individuals try to access health information they need through online platforms before applying hospital. This study aimed examine readability, reliability quality responses given by 3 different intelligence (ChatGPT, Gemini Perplexity) frequently asked questions about pain. In this study, 25 most used keywords related were determined using Google Trend every chatbots. The readability response texts was Flesch Reading Ease Score (FRES), Simple Measure Gobbledygook, Gunning Fog Flesch-Kincaid Grade Level scoring. Reliability assessment Journal American Medical Association (JAMA), DISCERN scales. Global Quality Ensuring Information for Patients (EQIP) score assessment. As a result search, first as "back pain," "stomach "chest pain." answers all higher recommended 6th grade level (P < .001). evaluation, order easy difficult Gemini, ChatGPT Perplexity. Higher GQS scores = .008) detected compared other Perplexity had JAMA, EQIP chatbots, respectively .001, P .05). has been ChatGPT, pain-related are read their low. can stated these cannot replace comprehensive medical consultation. applications, it may facilitate text content, create containing reliable references, control them supervisory expert team.

Language: Английский

Citations

0

The digital dialogue on premature ejaculation: evaluating the efficacy of artificial intelligence-driven responses DOI
Hakan Anıl, Mehmet Vehbi Kayra

International Urology and Nephrology, Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Language: Английский

Citations

0

Does use of generative AI chatbots by patients introduce risk of adverse drug events? DOI
Roger S. McIntyre

Expert Opinion on Drug Safety, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

Language: Английский

Citations

0