Optimizing keratoconus treatment with AI‐driven lenticule matching using pentacam indices

Aims/Purpose: The aim of this study is to develop an advanced artificial intelligence (AI) methodology to optimize the matching of donor and recipient lenticules for the treatment of keratoconus. This approach leverages Pentacam indices related to corneal thickness and topography to minimize the preparatory modifications required for stromal lenticule implantation. Methods : We will construct a comprehensive database of donor and recipient lenticules by systematically collecting Pentacam‐derived indices, including central corneal thickness (CCT), anterior and posterior corneal elevation, and corneal curvature, at preoperative, intraoperative, and postoperative stages. Using these datasets, an AI algorithm capable of identifying the most compatible lenticule pairs will be trained and validated. The algorithm's performance will be assessed based on its accuracy in predicting optimal matches and the practical effectiveness of the process. Results: As this project is in its preliminary phase, no results are currently available. However, we hypothesize that the AI‐assisted matching system will significantly enhance the compatibility of donor and recipient lenticules. Expected outcomes include increased postoperative central corneal thickness, improved corrected distance visual acuity (CDVA), and reduced corneal irregularity. Conclusions: This study aims to validate the potential of AI‐assisted matching of donor and recipient lenticules using Pentacam indices as a transformative approach in the treatment of keratoconus. By refining the customization process, we anticipate improvements in surgical efficiency and patient outcomes.