Analysis of Patient Education Guides Generated by ChatGPT and Gemini on Common Anti-diabetic Drugs: A Cross-Sectional Study
Abstract
Introduction Patient information guides are required, as they help to identify early diseases and complications and to prevent them. Artificial intelligence (AI) tools are being used to create patient education guides for easy accessibility to people. Methodology This was a cross-sectional study analyzing patient information guides regarding six anti-diabetic drugs created using ChatGPT (OpenAI, Inc., San Francisco, California, United States) and Gemini (Google LLC, Mountain View, California, United States), respectively. The patient information guides were on anti-diabetic drugs, including metformin, empagliflozin, liraglutide, glipizide, sitagliptin, and insulin glargine, and were created with the help of various prompts. Results There was no statistically significant difference found between any of the characteristics of the responses generated by the two AI tools, according to the P values obtained. Conclusion On comparing the two AI tools, there was not much difference noted in readability, reliability, and similarity.
How strong is the evidence?
Evidence Hub reads this as a cross-sectional, done in people. Its evidence level is 4 of 5 (Low · observational). Observational designs can show an association but not prove cause.
Read the paper
Related studies
- Metformin as an adjuvant in breast cancer treatment
- Metformin Lysosomal Targeting: A Novel Aspect to Be Investigated for Metformin Repurposing in Neurodegenerative Diseases?
- Aberrant HSF1 signaling activation underlies metformin amelioration of myocardial infarction in mice
- Metformin induces ZFP36 by mTORC1 inhibition in cervical cancer-derived cell lines
- Protein Interaction Network for Identifying Vascular Response of Metformin (Oral Antidiabetic)
- Preventing Long COVID With Metformin
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.