COMPARISON OF INTRAOCULAR-LENS COMPUTATIONS USING A NEURAL-NETWORK VERSUS THE HOLLADAY-FORMULA

Purpose: To compare the accuracy of intraocular lens (IOL) calculation s using Holladay personalized calculations and a new method of trained neural networks. Setting: A private ophthalmic practice. Methods: We developed and trained a neural network to predict IOL powers using a p ersonalized Holladay program and clinical data from 200 consecutive ca ses of one surgeon's results with one IOL. Clinical data included preo perative axial length, both keratometry values, anterior chamber depth , and human lens thickness. The neural network was trained to produce the actual postoperative refractive error, and the Holladay surgeon fa ctor was continuously refined using the same results. After the networ k was successfully trained against the clinical data, it was used to c ompute IOL power in a double-masked study. Ninety-five patients were r andomized between the Holladay personalized calculation and the neural network computation. There were no significant differences in age or preoperative refractive errors between the two groups. Manifest refrac tions were obtained during the masked period at least 6 weeks after su rgery. Results: Mean postoperative error from predicted refraction was +0.271 diopters (D) for the neural network group and -0.217 D for the Holladay personal group. Mean absolute error from predicted refractio n was +0.63 D for the neural network group and +0.93 D for the Hollada y personal group. There was a significant difference in postoperative refractive errors and mean absolute error between the two groups (P < .022; nonparametric Mann-Whitney test). An error of less than +/-0.75 D was obtained by 72.5% of the neural network group and 50.0% of the H olladay group. Conclusions: The neural network prediction formula can improve IOL implantation calculations by tightening the variance of er rors.