**1. Introduction**

The primary purpose of cataract surgery is visual rehabilitation; however, refractive correction is also an important aspect of the surgery to achieve better vision and quality of life postoperatively. With modern surgical techniques, patients' expectations for better vision postoperatively are increasing day by day. Accurately predicting the postoperative refraction in myopic eyes is challenging [1,2]. The prevalence of myopia is growing, especially in Asia [3–5]. While many methods are being used to overcome this issue [6–11], the challenge still remains.

The recent advances in artificial intelligence (AI) are outstanding and the application of AI in clinical medicine is a current hot topic. AI is used not only for classification or anomaly detection, but also for regression. The Hill-RBF refractive formula uses pattern recognition and data interpolation to predict postoperative refraction [12,13], whereas the Kane formula is based on theoretical optics and also incorporates regression and AI components to further refine its predictions [14]. Several studies have reported good refractive outcomes obtained with these formulas [15–17].

The Hill-RBF formula has been updated recently to version 3.0, which was reported to show better prediction accuracy than the previous version in a recent study; however, that study did not focus on myopic eyes (axial length [AL], 24.10 ± 1.47 mm) [13] and, to our knowledge, no other study has investigated the accuracy of the new version of the formula

**Citation:** Omoto, M.; Sugawara, K.; Torii, H.; Yotsukura, E.; Masui, S.; Shigeno, Y.; Nishi, Y.; Negishi, K. Investigating the Prediction Accuracy of Recently Updated Intraocular Lens Power Formulas with Artificial Intelligence for High Myopia. *J. Clin. Med.* **2022**, *11*, 4848. https://doi.org/ 10.3390/jcm11164848

Academic Editor: Nobuyuki Shoji

Received: 11 June 2022 Accepted: 13 August 2022 Published: 18 August 2022

**Publisher's Note:** MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

**Copyright:** © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).

in myopic eyes. Therefore, we investigated the prediction accuracy of the recently updated intraocular lens (IOL) power formulas with AI for high myopia.

#### **2. Materials and Methods**

#### *2.1. Study Institutions and Institutional Review Board Approval*

The Research Ethics Committee of the Graduate School of Medicine and the Faculty of Medicine at Keio University approved this retrospective, observational study. All patients provided written consent for the surgeries. Patient consent to participate in this study was waived, and an opt-out approach was used according to the Ethical Guidelines for Medical and Health Research Involving Human Subjects presented by the Ministry of Education, Culture, Sports, Science, and Technology in Japan. The patients and public were not involved in the design, conduct, reporting, or dissemination plans of our research. This study was performed according to the tenets of the Declaration of Helsinki.
