Publication: Implementación y precisión de un nuevo método de cálculo biométrico basado en técnicas de inteligencia artificial
Loading...
Files
Official URL
Full text at PDC
Publication Date
2022-02-16
Authors
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Complutense de Madrid
Citations
Exportar
Abstract
Se diseña un estudio para estimar la potencia emetropizante de la lente intraocular, modificando por distometría y de forma retrospectiva la potencia real de la lente intraocular implantada. Se implementarán unos modelos regresivos no lineales, que utilicen como variable respuesta la potencia recalculada retrospectivamente y como predictores una serie de inputs biométricos.Se recopiló una muestra de 481 ojos intervenidos de cataratas por 4 cirujanos con distintos tipos de implantes intraoculares. Todos los ojos fueron medidos preoperatoriamente con IOL Master® 700 (Carl Zeiss Meditec AG, Jena, Alemania) y Pentacam® HR (Oculus Optikgeräte GmbH, Wetzlar, Alemania) para la curvatura posterior corneal. Se preparó y se analizó el dataset para la selección de las variables eliminando correlaciones que produjeran colinealidad. La muestra se aleatorizó y posteriormente se dividió en dos partes con una ratio 80/20: entrenamiento (training) y validación (test) respectivamente.Se implementaron en crudo modelos regresivos mediante técnicas de Machine Learning y se entrenaron con la partición training. Posteriormente se optimizaron e hiperparametrizaron para mejorar y potenciar la predictibilidad. Se utilizaron técnicas de mejora (stacking) para ensamblar los mejores modelos finales, obteniendo un modelo definitivo al que se llamó Karmona®...
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®...
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®...
Description
Tesis inédita de la Universidad Complutense de Madrid, Facultad de Óptica y Optometría, Departamento de Optometría y Visión, leída el 12-11-2021