Academic Journal
Machine learning-based prediction of keratoconus progression after accelerated corneal cross-linking using the thinnest corneal thickness-to-maximum keratometry ratio.
| Τίτλος: | Machine learning-based prediction of keratoconus progression after accelerated corneal cross-linking using the thinnest corneal thickness-to-maximum keratometry ratio. |
|---|---|
| Συγγραφείς: | Wu T; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: wuti_kiki@163.com., Liu Y; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: liuyang-7708@163.com., Cao X; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: cao_xueqian@163.com., Gong Y; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: gytnjmu@163.com., Jiang Y; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: 18914999538@163.com., Huang J; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: huangjin@njmu.edu.cn., Li Z; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: lizhongguo@njmu.edu.cn., Ma J; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: majunxin@njmu.edu.cn., Wang J; Department of Ophthalmology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China. Electronic address: wangjing0218@njmu.edu.cn. |
| Πηγή: | Photodiagnosis and photodynamic therapy [Photodiagnosis Photodyn Ther] 2026 Oct; Vol. 61, pp. 105663. Date of Electronic Publication: 2026 Sep 24. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Elsevier Country of Publication: Netherlands NLM ID: 101226123 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1873-1597 (Electronic) Linking ISSN: 15721000 NLM ISO Abbreviation: Photodiagnosis Photodyn Ther Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Amsterdam ; Boston : Elsevier, c2004- |
| Ιατρικοί όροι (MeSH): | Keratoconus*/drug therapy , Keratoconus*/pathology , Corneal Cross-Linking*/methods , Cornea*/pathology , Photochemotherapy*/methods , Machine Learning*, Photosensitizing Agents/therapeutic use ; Cross-Linking Reagents/therapeutic use ; Humans ; Retrospective Studies ; Disease Progression ; Female ; Corneal Topography ; Prediction Algorithms ; Adult ; Predictive Learning Models ; Algorithms ; Corneal Pachymetry |
| Περίληψη: | Purpose: To develop and internally validate an interpretable model of keratoconus progression after accelerated corneal cross-linking (A-CXL), emphasizing the thinnest corneal thickness-to-maximum keratometry ratio (TCT/Kmax). Methods: This retrospective cohort included 170 eyes treated with A-CXL; progression was an increase in maximum keratometry of at least 1.00 D within 1 year. Twenty-six baseline clinical, treatment, and Pentacam-derived tomographic predictors were evaluated using fully nested stratified cross-validation with 10 outer and five inner folds. Scaling, categorical one-hot encoding, 1-SE LASSO selection, hyperparameter tuning, and fitting were confined to each outer training set. Eight algorithms were compared using pooled out-of-fold (OOF) predictions. Discrimination, calibration, clinical utility, and OOF SHAP explanations were assessed. Results: Of 170 eyes, 42 (24.7%) progressed. TCT/Kmax was selected in all 10 outer folds, whereas Km front and BAD-D were each selected in seven. The fold-specific logistic regression (LR) pipeline had the highest candidate-specific OOF AUC (0.772; 95% CI, 0.692-0.844), with an AUPRC of 0.528 and a Brier score of 0.156. Its calibration intercept was -0.19 (95% CI, -0.51 - 0.20) and slope was 1.15 (95% CI, 0.74-1.65). Confidence intervals overlapped across algorithms. TCT/Kmax had the largest mean absolute OOF SHAP value. A separate post-validation three-factor LR model was fitted after validation for interpretation and a research-only calculator prototype. Conclusions: Leakage-controlled internal validation identified TCT/Kmax as the most stable predictor and supported LR as a parsimonious candidate pipeline. The fixed three-factor model and accompanying calculator are exploratory research tools and require independent external validation before use in clinical decision-making. (Copyright © 2026 The Authors. Published by Elsevier B.V. All rights reserved.) |
| Competing Interests: | Declaration of competing interest The authors declare no conflict of interest. |
| Contributed Indexing: | Keywords: Accelerated corneal cross-linking; Keratoconus progression; Logistic regression; Nested cross-validation; Thinnest corneal thickness-to-maximum keratometry ratio |
| Substance Nomenclature: | 0 (Photosensitizing Agents) 0 (Cross-Linking Reagents) |
| Entry Date(s): | Date Created: 20260924 Date Completed: 20261003 Latest Revision: 20261003 |
| Update Code: | 20261004 |
| DOI: | 10.1016/j.pdpdt.2026.105663 |
| PMID: | 42785496 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!