Accuracy of 8 intraocular lens calculation formulas in relation to anterior chamber depth in patients with normal axial lengths

Purpose: To determine the effect of anterior chamber depth (ACD) on the accuracy of 8 intraocular lens calculation formulas in patients with normal axial lengths (ALs). Setting: Baylor College of Medicine, Alkek Eye center, Houston, Texas, USA. Design: Retrospective case series. Methods: Patients having cataract surgery with ALs between 22.0 mm and 25.0 mm were divided into 3 groups based on their preoperative ACD measurement. The mean prediction errors, mean absolute errors (MAEs), and median absolute errors for each group were calculated. Results: For the ACD of 3.0 mm or less group and the ACD of 3.5 mm or more group, the Barrett Universal II, Holladay 2, Haigis, and Olsen ray-tracing formulas had mean prediction error values that were not significantly different from zero. For the ACD of 3.01 to 3.49 mm group, all formulas had mean prediction error values that were not significantly different from zero. For the ACD of 3.0 mm or less group, the Barrett Universal II formula had a smaller median absolute error than the Haigis, Hoffer Q, and Olsen optical low-coherence reflectometry (OLCR) (Lenstar) formulas and a smaller MAE than the Hoffer Q, Hill-RBF, and Olsen OLCR (P < .05). In the ACD of 3.5 mm or more group, the Barrett MAE was smaller than the Hoffer Q (P < .05); however, there were no significant differences between median absolute errors. Conclusion: in eyes with normal ALs, taking preoperative ACD values into consideration might improve refractive outcomes. (C) 2018 ASCRS and ESCRS