Kamiya K, Ryu IH, Yoo TK, et al. - In a large cohort of eyes undergoing posterior chamber phakic intraocular lens (EVO ICL, STAAR Surgical) implantation, researchers sought to compare the achieved vault using the conventional manufacturer's nomogram and the predicted vault using machine learning. The research covered a total of 1,745 eyes of 1,745 consecutive patients (mean age ± standard deviation, 26.2 ± 6.8 years) undergoing ICL implantation. According to findings, machine learning of the preoperative anterior segment optical coherence tomography metrics, particularly the random forest regressor, provided significantly higher predictability of the ICL vault than the conventional nomogram of the manufacturer, indicating that it will become an aid for anticipating the ICL vault and subsequently choosing the proper ICL size in daily practice.