Comparative Evaluation of Traditional and AI-Based Intraocular Lens Power Calculation Formulas in Highly Myopic Eyes

Purpose: To assess the accuracy of artificial intelligence (AI)-based intraocular lens (IOL) power calculation formulas compared with traditional methods in highly myopic eyes, and to evaluate their performance across varying axial lengths and corneal curvatures. Methods: This retrospective case series included 115 highly myopic eyes that underwent phacoemulsification with IOL implantation. IOL power was calculated using four conventional formulas (SRK/T, Haigis, Holladay 2, Barrett Universal II) and seven AI-based formulas (Hill-RBF 3.0, Karmona, Hoffer QST, PEARL-DGS, Ladas Super Formula, Kane, HM-ZL). The outcomes were evaluated using mean error (ME), mean absolute error (MAE), median absolute error (MedAE), and the percentage of eyes within ±0.25 D to ±1.00 D of the prediction error. Subgroup analyses were conducted based on axial length (AL) and corneal curvature (Kmean). Results: AI-based formulas—especially Hill-RBF 3.0, Hoffer QST, and PEARL-DGS—demonstrated significantly higher accuracy than traditional formulas. Hill-RBF 3.0 achieved the lowest MAE (0.50 D) and MedAE (0.33 D) and the highest percentage of eyes within ±0.50 D (67.83%）and ±1.00 D (89.57%). Subgroup analyses showed that AI formulas maintained consistent performance across various AL and Kmean categories. Significant differences were noted between AI-based and traditional formulas, particularly in eyes with extreme biometric values. Conclusion: AI-based formulas provide superior refractive prediction in highly myopic eyes compared with traditional methods, particularly in cases of long axial length or steep corneal curvature. Tailored formula selection based on biometric profiles may enhance refractive outcomes in cataract surgery.