Clinical Report: The Scleral Lens Vault: Dive Into the Future Without Forgetting the Past

Overview

This report discusses the challenges of fitting contact lenses for keratoconus patients and highlights the potential of artificial intelligence (AI) in improving fitting accuracy. Recent studies indicate that deep learning techniques, particularly convolutional neural networks (CNNs), outperform traditional methods in predicting optimal lens parameters.

Background

Fitting contact lenses for keratoconus patients is often complicated due to corneal irregularities, making accurate fitting essential for patient comfort and visual acuity. Traditional fitting methods can be time-consuming and may require multiple attempts. The integration of AI into the fitting process represents a significant advancement, potentially reducing the trial-and-error nature of lens fitting and enhancing patient outcomes.

Data Highlights

No numerical data available in the source material.

Key Findings

• AI techniques, particularly CNNs, have shown superior accuracy in predicting rigid lens parameters for keratoconus patients compared to traditional methods.
• A retrospective study analyzed 197 keratoconic eyes, demonstrating the effectiveness of AI in lens fitting.
• Combining multiple topographic maps in AI analysis resulted in better fitting predictions than using single methods.
• Practitioners are encouraged to incorporate advanced technologies, including AI, in their fitting processes to improve efficiency.
• Future research is needed to explore the application of AI in scleral lens fittings specifically.

Clinical Implications

The findings suggest that incorporating AI into the lens fitting process can streamline patient care and reduce the number of fitting attempts required. Practitioners should consider utilizing AI tools to enhance fitting accuracy and patient satisfaction.

Conclusion

The integration of AI into the fitting of contact lenses for keratoconus patients represents a promising advancement in optometry. Continued research and development in this area are essential for optimizing patient outcomes.

References

1. Abadou J, Dahan S, Knoeri J, et al., Cont Lens Anterior Eye, 2025 -- Artificial intelligence versus conventional methods for RGP lens fitting in keratoconus
2. Ortiz-Toquero S, Rodriguez G, et al., Indian J Ophthalmol, 2019 -- Gas permeable contact lens fitting in keratoconus: Comparison of different guidelines to back optic zone radius calculations
3. Ting DSW, Pasquale LR, et al., Br J Ophthalmol, 2019 -- Artificial intelligence and deep learning in ophthalmology
4. Kamiya K, Ayatsuka Y, et al., BMJ Open, 2019 -- Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study
5. Hashemi S, Veisi H, et al., Med Biol Eng Comput, 2020 -- Multi-view deep learning for rigid gas permeable lens base curve fitting based on Pentacam images
6. Contact Lens Spectrum — The Scleral Lens Vault
7. Contact Lens Spectrum — THE SCLERAL LENS VAULT
8. Contact Lens Spectrum — The Scleral Lens Vault
9. Contact Lens Spectrum — THE SCLERAL LENS VAULT
10. The Second Global Consensus on Keratoconus
11. Visual Improvement With Wavefront-Guided Scleral Lenses for Irregular Corneal Astigmatism
12. Compare of the scleral morphology between healthy populations and keratoconus patients using optical coherence tomography - ScienceDirect