• AI models demonstrate high diagnostic accuracy for COPD with pooled sensitivity of 0.89 and specificity of 0.87, and an AUC of 0.94.
• Prognostic models show good performance with a pooled C-index of 0.82, indicating effective risk stratification.
• Deep learning and imaging-based models outperform traditional machine learning and clinical data models.
• High risk of bias and lack of external validation in most studies highlight the need for standardized reporting and validation.