Implementación y precisión de un nuevo método de cálculo biométrico basado en técnicas de inteligencia artificial

Abstract

A study is designed to estimate the refractive power of the intraocular lens, back-calculated the real power of the implanted intraocular lens retrospectively by distometry. Non-linear regression models will be implemented, using the retrospectively back-calculated power as the response variable and biometric inputs as predictors.A sample of 481 eyes undergoing uneventful cataract surgery by 4 surgeons with different types of intraocular implants was collected. All eyes were measured preoperatively with IOL Master® 700 (Carl Zeiss Meditec AG, Jena, Germany) and Pentacam® HR (Oculus Optikgeräte GmbH, Wetzlar, Germany) for corneal posterior curvature. The dataset was prepared and analyzed for variable selection by eliminating correlations that produced collinearity. The sample was randomized and subsequently split into two parts with a ratio 80 - 20: training and test.The regression models were implemented in raw form using Machine Learning techniques and trained with the training partition. Subsequently, they were optimized and hyperparameterized to improve and enhance predictability. Stacking techniques were used to assemble the best final models, obtaining a final model called Karmona®...