Gonzalez-Cruces, Timoteo , Aguilar-Salazar, Francisco Javier , Marfany Tort, Jordi , Sanchez-Ventosa, Alvaro , Villarrubia, Alberto , Mateu, Jose Lamarca , Barraquer, Rafael I. , Pardina, Sergio , Cerdan Palacios, David , Cano-Ortiz, Antonio
No
J Cataract Refract Surg
Article
Científica
01/05/2025
001569141600006
2-s2.0-85217263212
Purpose: To develop a prediction model based on machine learning to calculate the postoperative vault and the ideal implantable collamer lens (ICL) size, considering for the first time the implantation orientation in a White population. Setting: Arruzafa Ophthalmological Hospital (Cordoba, Spain) and Barraquer Ophthalmology Center (Barcelona, Spain). Design:Multicenter, randomized, retrospective study. Methods: Anterior segment biometric data from 235 eyes of patients who underwent ICL lens implantation surgery were collected using the anterior segment optical coherence tomography CASIA II to train and validate 5 types of multiple regression models based on advanced machine learning techniques. To perform an external validation, a dataset of 45 observations was used. Results: The Pearson correlation coefficient between observed and predicted values was similar in the 5 models in the external validation, with least absolute shrinkage and selection operator regression being the highest (r = 0.62, P < .001), followed by random forest regression model (r = 0.60, P < .001) and backward stepwise regression (r = 0.58, rho < 0.001). In addition, the predictions generated by the different models showed closer agreement with the actual vault compared with the Nakamura formulas. Using the new methods, about 70% of the observations had a prediction error below 150 mu m. Conclusions: Advanced forms of regressions models based on machine learning allow satisfactory calculation of the ideal lens size, offering greater precision to surgeons customizing surgery according to implant orientation.
adult; anterior eye chamber depth; anterior eye segment; Article; astigmatism; Caucasian; controlled study; corneal diameter; corneal tomography; decision tree; female; follow up; human; intraocular pressure; keratometry; least absolute shrinkage and selection operator; lens implantation; machine learning; major clinical study; male; myopia; optical coherence tomography; prediction; prediction error; preoperative evaluation; pupillometry; random forest; retrospective study; spherical equivalent; trabecular-iris angle; biometry; clinical trial; diagnostic imaging; middle aged; multicenter study; pathology; phakic intraocular lens; procedures; randomized controlled trial; surgery; visual acuity; young adult; Adult; Anterior Eye Segment; Biometry; Female; Humans; Lens Implantation, Intraocular; Machine Learning; Male; Middle Aged; Myopia; Phakic Intraocular Lenses; Retrospective Studies; Tomography, Optical Coherence; Visual Acuity; Young Adult