Accuracy of artificial intelligence in meta-analysis: A comparative study of ChatGPT 4.0 and traditional methods in data synthesis
Our findings suggest the potential of ChatGPT in conducting meta-analyses in interventional cardiology. However, further research is needed to address the limitations of transparency and potential data quality issues, ensuring that AI-generated analyses are robust and trustworthy for clinical decision-making.
Authors
- Hritvik Jain (ORCID: https://orcid.org/0000-0001-5608-4299)
- Amna Zaheer (ORCID: https://orcid.org/0000-0002-2355-911X)
- Areeba Ahsan (ORCID: https://orcid.org/0000-0003-2390-7775)
- Andrei Brateanu (ORCID: https://orcid.org/0000-0003-1339-3934)
- Surabhi Maheshwari
- Aman Goyal (ORCID: https://orcid.org/0000-0002-7526-7071)
- Muhammad Hamza Khan (ORCID: https://orcid.org/0000-0001-8279-5430)
- Muhammad Daoud Tariq (ORCID: https://orcid.org/0009-0003-7769-5592)
Institutions
- Karachi Medical and Dental College (PK)
- Cleveland Clinic (US)
Publication Details
- Journal
- World Journal of Methodology
- Published
- 2025-08-03
- DOI
- https://doi.org/10.5662/wjm.v15.i4.102290
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00