Abstract
The objective is to evaluate the parameters significantly related to calculating the power of the implanted lens and to determine the importance of different biometric, retina, and corneal aberrations variables. A retrospective cross-sectional observational study used a database of 422 patients who underwent cataract surgery at the Oftalvist Center in Almeria between January 2021 and December 2022. A random forest based on machine learning techniques was proposed to classify the importance of preoperative variables for calculating IOL power. Correlations were explored between implanted IOL power and the most important variables in random forests. The importance of each variable was analyzed using the random forest technique, which established a ranking of feature selections based on different criteria. A positive correlation was found with the random forest variables. Selection: axial length (AL), keratometry preoperative, anterior chamber depth (ACD), measured from corneal epithelium to lens, corneal diameter, lens constant, and astigmatism aberration. The variables coma aberration (p-value = 0,12) and macular thickness (p-value = 0,10) were almost slightly significant. In cataract surgery, the implanted IOL power is mainly correlated with axial length, anterior chamber depth, corneal diameter, lens constant, and preoperative keratometry. New variables such as astigmatism and anterior coma aberration and retina variables such as the preoperative central macular thickness could be included in the new generation of biometric formulas based on artificial intelligence techniques.