Academic Journal
Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus.
| Τίτλος: | Machine Learning Model for Predicting Visual Acuity Improvement After Intrastromal Corneal Ring Surgery in Patients With Keratoconus. |
|---|---|
| Συγγραφείς: | Perez E; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Louissi N; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Kallel S; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Hays Q; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Bouheraoua N; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Hamrani M; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and., Chessel A; Laboratory for Optics and Biosciences (LOB), École Polytechnique, CNRS, Inserm, Institut Polytechnique de Paris, Palaiseau, France ., Borderie V; GRC 32, Transplantation et Thérapies Innovantes de La Cornée, TTIC, Hôpital National des 15-20, Sorbonne Université, Paris, France ; and. |
| Πηγή: | Cornea [Cornea] 2026 Jul 01; Vol. 45 (7), pp. 840-850. Date of Electronic Publication: 2025 Jul 23. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Lippincott Williams & Wilkins Country of Publication: United States NLM ID: 8216186 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1536-4798 (Electronic) Linking ISSN: 02773740 NLM ISO Abbreviation: Cornea Subsets: MEDLINE |
| Imprint Name(s): | Publication: Hagerstown, MD : Lippincott Williams & Wilkins Original Publication: New York, N.Y. : Masson Pub. USA, c1982- |
| Ιατρικοί όροι (MeSH): | Corneal Stroma*/surgery , Keratoconus*/surgery , Keratoconus*/physiopathology , Visual Acuity*/physiology , Boosting Machine Learning Algorithms* , Prostheses and Implants* , Prosthesis Implantation*, Refraction, Ocular/physiology ; Adolescent ; Adult ; Female ; Humans ; Male ; Young Adult ; Corneal Topography ; Predictive Learning Models ; Retrospective Studies |
| Περίληψη: | Background: Keratoconus is a progressive, degenerative corneal disease that can lead to significant visual impairment. The intrastromal ring segment implantation procedure is effective in reshaping the cornea and improving vision. However, vision does not improve postoperatively in all operated eyes, and the results vary widely among patients, making it challenging to predict postoperative visual gain. Purpose: This study investigated the potential of machine learning in predicting postoperative visual acuity in keratoconus patients undergoing intrastromal ring segment implantation with the aim of enhancing surgical decision-making. Methods: This retrospective study analyzed 120 eyes of 102 patients with keratoconus who underwent ring segment implantation (1 symmetric or asymmetric segment, 150-300 μm thick, 150 degrees, or 160 degrees-arc). Preoperative and postoperative refraction, corneal topography, and tomographic data were collected. Various models were trained to predict postoperative visual acuity improvements. Results: The models demonstrated excellent performance, with XGBoost achieving perfect results in predicting whether vision will improve after surgery (R 2 = 1.0, Youden Index = 1.0; all test observations being correctly classified). The CatBoost model achieved an R 2 of 0.59 [0.7-line mean absolute error (MAE)] for predicting postoperative visual acuity, an R 2 of 0.76 (MAE, 1.08 D) for predicting keratometry, and an R 2 of 0.54 (MAE, 0.29) for predicting corneal asphericity. Key features for accurate predictions included preoperative keratometry values (K1, K2, Kmax), corneal asphericity, and visual acuity, whereas segment characteristics featured low importance. Conclusions: This study shows the strong potential of machine learning for selecting candidates for surgery and predicting postoperative visual improvements after ring segment implantation in keratoconus eyes. (Copyright © 2025 The Author(s). Published by Wolters Kluwer Health, Inc.) |
| References: | Curr Opin Ophthalmol. 2020 Jul;31(4):253-260. (PMID: 32487811) Ophthalmology. 2012 Nov;119(11):2231-8. (PMID: 22892148) J Clin Med. 2021 Mar 06;10(5):. (PMID: 33800825) Am J Ophthalmol. 2003 May;135(5):620-7. (PMID: 12719068) PLoS One. 2024 Feb 6;19(2):e0288181. (PMID: 38319899) J Fr Ophtalmol. 2016 May;39(5):428-36. (PMID: 27133136) JMIR Med Inform. 2021 Dec 13;9(12):e27363. (PMID: 34898463) J Biomed Inform. 2002 Jun;35(3):151-9. (PMID: 12669978) Evol Intell. 2022;15(1):1-22. (PMID: 33425040) J Refract Surg. 2024 Nov;40(11):e863-e876. (PMID: 39530978) J Taibah Univ Med Sci. 2024 Jan 01;19(2):296-303. (PMID: 38283379) Curr Eye Res. 2019 Jul;44(7):707-715. (PMID: 30868919) Biomed Res Int. 2015;2015:795738. (PMID: 26075261) J Cataract Refract Surg. 2007 Jul;33(7):1303-14. (PMID: 17586391) J Refract Surg. 2018 Aug 1;34(8):547-550. (PMID: 30089185) Am J Ophthalmol. 2013 Mar;155(3):575-584.e1. (PMID: 23218702) Invest Ophthalmol Vis Sci. 1994 May;35(6):2749-57. (PMID: 8188468) J Clin Med. 2023 Feb 20;12(4):. (PMID: 36836208) J Cataract Refract Surg. 2009 Oct;35(10):1768-73. (PMID: 19781474) Surv Ophthalmol. 1998 Jan-Feb;42(4):297-319. (PMID: 9493273) Br J Ophthalmol. 2021 Feb;105(2):158-168. (PMID: 32532762) J Fr Ophtalmol. 2021 Jun;44(6):882-898. (PMID: 33895029) J Cataract Refract Surg. 2004 Apr;30(4):812-20. (PMID: 15093643) Comput Methods Programs Biomed. 2014 Aug;116(1):39-47. (PMID: 24857632) Surv Ophthalmol. 1984 Jan-Feb;28(4):293-322. (PMID: 6230745) Comput Math Methods Med. 2021 Nov 16;2021:9979560. (PMID: 34824602) BMJ Open. 2019 Sep 27;9(9):e031313. (PMID: 31562158) J Fr Ophtalmol. 2011 Oct;34(8):513-20. (PMID: 21632148) Comput Intell Neurosci. 2019 Jan 23;2019:8162567. (PMID: 30809255) Ophthalmology. 2017 Dec;124(12):1726-1728. (PMID: 29157423) Br J Ophthalmol. 2019 Feb;103(2):167-175. (PMID: 30361278) |
| Grant Information: | ANR-21-CE19-0010-02 Agence Nationale de la Recherche |
| Contributed Indexing: | Keywords: artificial intelligence; corneal topography; intrastromal corneal ring segments; keratoconus; machine learning |
| Entry Date(s): | Date Created: 20250723 Date Completed: 20260610 Latest Revision: 20260813 |
| Update Code: | 20260813 |
| PubMed Central ID: | PMC13241183 |
| DOI: | 10.1097/ICO.0000000000003933 |
| PMID: | 40698829 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1536-4798 |
|---|---|
| DOI: | 10.1097/ICO.0000000000003933 |