A systematic review evaluates the accuracy of artificial intelligence (AI)-based intraocular lens (IOL) power calculation formulas. The study analyzed 25 peer-reviewed articles published between 2017 and July 2023, focusing on the performance of AI-based formulas such as Kane, PEARL-DGS, Hill-RBF, Karmona, Hoffer QST, and Nallasamy. The accuracy of these formulas was assessed using mean absolute error (MAE) and the percentage of patients within ±0.5 D and ±1.0 D of the predicted refraction. The Kane formula consistently showed the lowest MAE and highest percentage of patients within ±0.5 D and ±1.0 D across most studies, making it the most accurate AI-based formula. The PEARL-DGS formula also performed very well, while Hoffer QST, Karmona, and Nallasamy are newer formulas that require further evaluation. The study highlights the potential of AI-based formulas to improve the accuracy of IOL power calculations, particularly in cases with extreme axial lengths. However, the review also notes limitations, including the need for more extensive studies and the heterogeneity of data across different studies. Overall, AI-based formulas show promise in enhancing the accuracy of postoperative refraction in cataract surgery.A systematic review evaluates the accuracy of artificial intelligence (AI)-based intraocular lens (IOL) power calculation formulas. The study analyzed 25 peer-reviewed articles published between 2017 and July 2023, focusing on the performance of AI-based formulas such as Kane, PEARL-DGS, Hill-RBF, Karmona, Hoffer QST, and Nallasamy. The accuracy of these formulas was assessed using mean absolute error (MAE) and the percentage of patients within ±0.5 D and ±1.0 D of the predicted refraction. The Kane formula consistently showed the lowest MAE and highest percentage of patients within ±0.5 D and ±1.0 D across most studies, making it the most accurate AI-based formula. The PEARL-DGS formula also performed very well, while Hoffer QST, Karmona, and Nallasamy are newer formulas that require further evaluation. The study highlights the potential of AI-based formulas to improve the accuracy of IOL power calculations, particularly in cases with extreme axial lengths. However, the review also notes limitations, including the need for more extensive studies and the heterogeneity of data across different studies. Overall, AI-based formulas show promise in enhancing the accuracy of postoperative refraction in cataract surgery.