Selecting a formula for calculating the optical power of an intraocular lens for short eyes using artificial intelligence

Objective: to conduct a comparative analysis of the accuracy of intraocular lens (IOL) selection in patients with an eye length of less than 22.0 mm using the Barrett Universal II, Kane, and Hoffer Q formulas, as well as via artificial intelligence (AI). Materials and Methods. We analyzed the outcomes of 88 phacoemulsification cataract surgeries with monofocal IOL implantation. Preoperative biometry and IOL calculations were performed on an IOL Master 700 (Zeiss, Germany). The accuracy of IOL selection was also determined via the LensCalc software based on AI (DecisionTreeClassifier). Results. The axial length of the eyes in patients ranged from 19.8 to 22.0 mm. The prediction of achieving the target refraction was most accurate when using the Barrett Universal II formula rather than Hoffer Q (Z=2.12; p=0.034). The mean error in achieving the target refraction when using the Barrett Universal II formula did not differ from the Kane formula (p>0.05). Using AI, we established that higher accuracy in the IOL power calculation was achieved when using the Barrett Universal II formula. Conclusion. Based on a comparative analysis of the study results and an assessment of the accuracy of IOL selection using AI, we established that the Barrett Universal II formula (4th generation) was more accurate in determining the optical power of the IOL in short eyes than the Hoffer Q formula (3rd generation). Our calculation results based on using the Barrett Universal II formula, unlike the Hoffer Q formula, were similar (p>0.05) to those calculated using the Kane formula (5th generation), which, according to the results of the majority of published studies, is currently the most accurate formula for IOL selection.