Abstract
Purpose :
To analyze the accuracy of artificial intelligence (AI)-driven intraocular (IOL) calculation formulae, together with the established formulae available in the European Society of Cataract and Refractive Surgeons (ESCRS) calculator, using the heteroscedastic methodology and the Eyetemis Analysis Tool.
Methods :
Consecutive patients undergoing phacoemulsification and implantation of the Acrysof IQ SN60WF IOL were retrospectively reviewed. IOL power calculations were performed using the Barrett Universal II (BUII), EVO 2.0, Hoffer QST, K6, Ladas Super Formula (LSF), Nallasamy, PEARL-DGS and RBF 3.0 formulae. Formulae's distribution, denoted by the standard deviation (SD) of the prediction error (PE), served as the primary metric for accuracy. The heteroscedastic statistical method was employed for formulae comparisons. The mean absolute deviation (MAD) of the PEs and the predictability rates within intervals from ±0.25 D to ±1.50 D were also evaluated. The Eyetemis Analysis Tool was used for further validation.
Results :
Four hundred and four eyes of 404 patients were included. The SD ranged from 0.468 (Nallasamy) to 0.510 (LSF). The Nallasamy formula had a significantly lower SD than BUII (0.505, p=0.025) and K6 (0.489, p=0.022) formulae. The Nallasamy formula also exhibited the lowest MAD (0.358) with a significant difference compared with the Hoffer QST formula (0.384, p<0.001). Finally, a significantly higher percentage of eyes achieving ±0.50 D of the target refraction was seen using the Nallasamy formula (77.19%) compared with the Hoffer QST (71.04%, p=0.019) and LSF (70.79%, p=0.030) formulae.
Conclusions :
The Nallasamy formula, incorporating AI technology, demonstrated superior accuracy according to the analysis guidelines for PE statistics for non-gaussian datasets recommended by Holladay et al. and the online Eyetemis Analysis Tool.
This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.