Comparison of IOL power formulas in eyes with a flat cornea <42 D

Purpose

To assess and compare accuracy of intraocular lens (IOL) power calculation performed with old generation, new generation and artificial intelligence (AI)-based formulas in eyes with flat corneas.

Design

Patients with a tomography-derived mean keratometry <42 D were retrospectively recruited among those who underwent uncomplicated phacoemulsification with intracapsular IOL implantation in two different tertiary care centers. Mean prediction error (ME), mean absolute prediction error (MAE) and incidence of MAE>0.25D were calculated for Barrett Universal II (BUII),EVO 2.0, Hoffer QST, Kane, Olsen-C, Pearl-DGS and SRK/T formulas. Linear correlation between MAE and axial length was also calculated for each formula.

Results

Eighty (80) eyes with a mean keratometry of 41.4 ± 0.6 D (range 40.6–41.9 D) were recruited. The SRK/T significantly differed from both the Olsen-C (p = 0.022) and the BUII (p = 0.048) in ME. The EVO 2.0, the Hoffer QST, the Kane and the PEARL-DGS showed a significantly lower MAE compared to all other formulas (p < 0.001) and a significant lower incidence of MAE>0.25D (p < 0.001), MAE>0.50 D (p < 0.001) and MAE>1.0 D (0.002).

Conclusion

Formulas based on AI and on the theory of vergence show superior accuracy in IOL power calculation in corneas with low mean keratometry; their MAE is not correlated to axial length.