Copyright
©The Author(s) 2025.
World J Methodol. Dec 20, 2025; 15(4): 102290
Published online Dec 20, 2025. doi: 10.5662/wjm.v15.i4.102290
Published online Dec 20, 2025. doi: 10.5662/wjm.v15.i4.102290
Table 1 Comparison of effect measures and P values between original studies and ChatGPT
Ref. | Journal | Software used for analysis | Outcome measures | Type of effect measure | Effect measure (original) | P value (original) | Effect measure (ChatGPT) | P value (ChatGPT) |
Sreenivasan et al[10] | Journal of American Heart Association | R studio | MACE | Risk ratio (95%CI) | 0.67 (0.55 -0.82) | < 0.001 | 0.67 (0.56-0.81) | < 0.001 |
Cardiac death | Risk ratio (95%CI) | 0.49 (0.34 -0.71) | < 0.001 | 0.46 (0.29-0.72) | < 0.001 | |||
All-cause death | Risk ratio (95%CI) | 0.81 (0.61 -1.07) | 0.135 | 0.80 (0.60-1.06) | 0.124 | |||
Myocardial infarction | Risk ratio (95%CI) | 0.82 (0.62-1.07) | 0.144 | 0.84 (0.64-1.10) | 0.197 | |||
Target vessel MI | Risk ratio (95%CI) | 0.61 (0.42-0.89) | 0.011 | 0.61 (0.42-0.90) | 0.011 | |||
Target lesion revascularization | Risk ratio (95%CI) | 0.67 (0.49-0.91) | 0.011 | 0.66 (0.48-0.91) | 0.010 | |||
Target vessel revascularization | Risk ratio (95%CI) | 0.60 (0.45-0.80) | < 0.001 | 0.60 (0.45-0.80) | < 0.001 | |||
Stent thrombosis | Risk ratio (95%CI) | 0.63 (0.40-0.99) | 0.046 | 0.67 (0.42-1.06) | 0.090 | |||
Patel et al[11] | Circulation | R studio | MACE | Hazard ratio (95%CI) | 0.91 (0.87-0.96) | < 0.0001 | 0.94 (0.90-0.98) | 0.005 |
Cardiovascular death | Hazard ratio (95%CI) | 0.86 (0.81-0.92) | < 0.0001 | 0.88 (0.81-0.96) | 0.0037 | |||
Myocardial infarction | Hazard ratio (95%CI) | 0.95 (0.87-1.04) | 0.29 | 0.97 (0.90-1.05) | 0.429 | |||
Stroke | Hazard ratio (95%CI) | 0.99 (0.91-1.07) | 0.77 | 0.87 (0.65-1.18) | 0.380 | |||
Sacoransky et al[12] | American Journal of Cardiology | RevMan | LV thrombus formation | Odds ratio (95%CI) | 0.28 (0.11-0.73) | < 0.01 | 0.37 (0.16-0.86) | 0.021 |
Major bleeding events | Odds ratio (95%CI) | 2.85 (1.13-7.24) | 0.03 | 2.82 (1.30-6.13) | 0.009 | |||
Systemic embolism | Odds ratio (95%CI) | 0.37 (0.12-1.13) | 0.08 | 0.42 (0.13-1.29) | 0.130 | |||
Paolucci et al[13] | European Heart Journal | RevMan | Relationship between PMI (UDMI and UDMI-like definitions) and mortality | Hazard ratio (95%CI) | 1.61(1.32- 1.97) | < 0.00001 | 1.61 (1.32-1.97) | < 0.00001 |
Relationship between PMI (ARC-2 definition) and mortality | Hazard ratio (95%CI) | 2.07 (1.40-3.08) | 0.0003 | 2.07 (1.40-3.08) | 0.0003 | |||
Relationship between PMI (SCAI and SCAI-like definitions) and mortality | Hazard ratio (95%CI) | 3.24 (2.36-4.44) | < 0.00001 | 3.24 (2.36-4.44) | < 0.00001 | |||
Ang et al[14] | International Journal of Surgery | Stata | Major vascular complications | Risk ratio (95%CI) | 2.32 (1.73-3.11) | < 0.001 | 2.30 (1.72-3.09) | < 0.001 |
Major bleeding | Risk ratio (95%CI) | 1.61 (1.27-2.05) | < 0.001 | 1.61 (1.27-2.05) | < 0.001 | |||
Aortic annulus rupture | Risk ratio (95%CI) | 4.66 (1.67-13.01) | < 0.001 | 4.66 (1.67-13.01) | 0.0033 | |||
Cardiac tamponade | Risk ratio (95%CI) | 3.0 (1.31-6.89) | 0.01 | 3.0 (1.31-6.89) | 0.0095 | |||
Minor vascular complications | Risk ratio (95%CI) | 1.43 (1.00-2.04) | 0.05 | 1.43 (1.00-2.04) | 0.052 | |||
Stroke | Risk ratio (95%CI) | 1.37 (0.81-2.32) | 0.24 | 1.41 (0.82-2.40) | 0.210 | |||
In-hospital mortality | Risk ratio (95%CI) | 1.86 (0.74-4.70) | 0.19 | 1.86 (0.74-4.70) | 0.187 | |||
30 days mortality | Risk ratio (95%CI) | 1.14 (0.532.46) | 0.74 | 1.22 (0.55-2.71) | 0.628 | |||
Pacemaker implantation | Risk ratio (95%CI) | 0.91 (0.70-1.18) | 0.47 | 0.98 (0.75-1.26) | 0.848 |
- Citation: Goyal A, Tariq MD, Ahsan A, Khan MH, Zaheer A, Jain H, Maheshwari S, Brateanu A. Accuracy of artificial intelligence in meta-analysis: A comparative study of ChatGPT 4.0 and traditional methods in data synthesis. World J Methodol 2025; 15(4): 102290
- URL: https://www.wjgnet.com/2222-0682/full/v15/i4/102290.htm
- DOI: https://dx.doi.org/10.5662/wjm.v15.i4.102290