Search

The article discusses the use of artificial intelligence (AI) tools, specifically ChatGPT, in providing statistical advice for scientific research. While AI can be helpful in solving narrow problems, there are concerns about relying too heavily on AI for health advice, as it can lead to misinformation and risks to our health. The article presents a study that analyzed ChatGPT's statistical skills in the field of allergology and found limitations in its ability to provide accurate and reliable answers. The authors emphasize the importance of human oversight and the need for researchers to familiarize themselves with statistical recommendations. They also suggest increasing the use of statistical reviewers by biomedical journal editors to improve the quality of published research. [Extracted from the article]