Abstract
This study introduced a new approach for the calculation of personalized intraocular lens power, which used an ensemble of regression models to devise a more accurate and robust prediction of the effective lens position. The concept of cross-validation is used to rigorously assess the performance of the devised formula against the most commonly used published formulae. The results from this study show that overall, the proposed approach outperforms the most commonly used modern formulae (namely, SRK/T, Hoffer Q, Holladay I, and Haigis) in terms of mean absolute prediction errors and prediction accuracy i.e., the percentage of eyes within ± 0.5D and ± 1 D ranges of prediction, for various ranges of axial lengths of the eyes. The results are obtained using three models of lens (two monofocal and one multifocal). Furthermore, the proposed formula exhibited some promising features in terms of robustness. This particular characteristic enables the new formula to cope with the variations in the axial length, the pre-operative anterior chamber depth as well as the keratometric readings of the corneal power; hence mitigating the impact of measurement accuracy for these parameters.
An Ensemble-Based Approach for Estimating Personalized Intraocular Lens Power