94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Med.
Sec. Ophthalmology
Volume 12 - 2025 | doi: 10.3389/fmed.2025.1462653
Digital Transformation of Care for Keratoconus Patients: ML Modelling Structural Outcomes of Corneal Collagen Cross-Linking
Provisionally accepted
Yauhen Statsenko 1,2,3*
Darya Smetanina 1
Roman Voitetskii 2
Gillian Simiyu 1
Mikalai Pazniak 1
Elena Likhorad 1 Aleh Pazniak 1 Pavel Beliakouski 1 Dmitriy Abelskyi 1
Klaus Neidl-Van Gorkom 1
Milos R Ljubisavljevic 1,4- 1 Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, AlAin, Abu Dhabi, United Arab Emirates
- 2 Medical Imaging Platform, ASPIRE Precision Medicine Research Institute, United Arab Emirates University, Al-Ain, Abu Dhabi, United Arab Emirates
- 3 Big Data Analytics Center (BIDAC), United Arab Emirates University, Al Ain, United Arab Emirates
- 4 Neuroscience Platform, ASPIRE Precision Medicine Research Institute, United Arab Emirates University, Al-Ain, Abu Dhabi, United Arab Emirates
Background: Structural outcomes of corneal collagen cross-linking (CXL) have not been thoroughly investigated. Clinical risk assessment would benefit from a reliable prognosis of postoperative minimal (MCT) and central corneal thickness (CCT). Objective: to find a combination of diagnostic modalities and measurements that reliably reflect CXL efficiency in terms of corneal thickness. Methods: We retrospectively reviewed the medical histories of 107 patients (131 eyes) who underwent CXL. The dataset included preoperative examinations and follow-up results, which totalled 796 observations. Results: The postoperative changes in MCT are more pronounced, clinically relevant, and meaningful than in CCT. MCT should serve as the major clinical marker of corneal thinning after CXL. The cornea's potential to recover reduces in advanced keratoconus. A polynomial curve demonstrates the natural course of corneal remodelling. It includes thinning immediately after CXL and stabilisation with partial recovery of corneal thickness over time. Baseline pachymetry data can adequately reflect the outcomes. Preoperative BAD and topography indices strongly correlate with the outcomes. Keratometry and refractometry data exhibit moderate associations with postoperative corneal thickness. The models trained on a combination of top correlating features, clinical data and time after intervention provide the most reliable prognosis. Conclusion: Risk assessment is accurate with multimodal 1 Statsenko et al. 1 preoperative diagnostics. A stratification system should take into account findings in different diagnostic modalities.
Keywords: Keratoconus, corneal collagen cross-linking, CXL outcomes, machine learning models, predictive models, Keratometry readings, corneal thickness, precision medicine
Received: 10 Jul 2024; Accepted: 10 Mar 2025.
Copyright: © 2025 Statsenko, Smetanina, Voitetskii, Simiyu, Pazniak, Likhorad, Pazniak, Beliakouski, Abelskyi, Neidl-Van Gorkom and Ljubisavljevic. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Yauhen Statsenko, Radiology Department, College of Medicine and Health Sciences, United Arab Emirates University, AlAin, 15551, Abu Dhabi, United Arab Emirates
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.