Artificial intelligence driven intraocular lens power calculation in extreme axial myopia
Yudai Suzuki1,2, Koju Kamoi3, Kengo Uramoto1
1Department of Ophthalmology & Visual Science Graduate school of Medical and Dental Sciences , Institute of Science Tokyo , Tokyo, Japan.
Accurate intraocular lens (IOL) power calculations for extreme myopia are improved by AI formulas like Kane and Hill-RBF. These advanced methods offer better refractive accuracy than traditional formulas, enhancing visual outcomes after cataract surgery.
Area of Science:
- Ophthalmology
- Biomedical Engineering
- Artificial Intelligence in Medicine
Background:
- Accurate intraocular lens (IOL) power calculation is crucial for successful cataract surgery.
- Traditional formulas often show inaccuracies in patients with extreme axial myopia (axial length ≥ 30.0 mm).
- This necessitates exploring advanced calculation methods for improved refractive outcomes in this challenging patient group.
Purpose of the Study:
- To retrospectively evaluate and compare the accuracy of two AI-driven IOL formulas (Hill-RBF, Kane) against the Barrett Universal II and traditional SRK/T formulas.
- To assess the refractive predictability of these formulas in eyes with extreme axial myopia.
- To determine if AI-driven formulas offer superior accuracy in this specific patient cohort.
Main Methods:
- Retrospective analysis of data from 80 eyes of 51 patients with axial lengths ≥ 30.0 mm.
- Comparison of postoperative refractive errors calculated using Hill-RBF, Kane, Barrett Universal II, and SRK/T formulas.
- Accuracy assessment using mean error (ME), mean absolute error (MAE), and median absolute error (MedAE), with statistical analysis including Wilcoxon signed-rank and chi-square tests.
Main Results:
- The Kane and Hill-RBF formulas demonstrated significantly lower MAE (0.51 D and 0.52 D) compared to SRK/T (P < 0.05).
- Barrett Universal II showed an MAE of 0.66 D, not significantly different from SRK/T.
- In eyes with axial lengths ≥ 32.0 mm, Kane achieved the lowest MAE (0.44 D) and MedAE (0.40 D).
- Kane and Hill-RBF resulted in fewer eyes with refractive errors > ±1.0 D (7.5%) compared to SRK/T (42.5%).
Conclusions:
- AI-driven IOL formulas, specifically Kane and Hill-RBF, significantly enhance refractive accuracy in patients with extreme axial myopia.
- These advanced formulas show potential to improve postoperative visual outcomes.
- Clinical adoption of AI-driven formulas may reduce the need for subsequent refractive interventions in this population.
More Related Videos
06:55Scanning Light Scattering Profiler SLPS Based Methodology to Quantitatively Evaluate Forward and Backward Light Scattering from Intraocular Lenses
Published on: June 6, 2017
05:46Author Spotlight: Advancements in Refractive Surgical Correction for Presbyopia and Exploring Postoperative Visual Acuity
Published on: September 20, 2024
Related Concept Videos
Focusing of Light in the Eye
Glaucoma: Overview
Angle Closure Glaucoma: Treatment
Open Angle Glaucoma: Treatment
Drugs such as carbonic anhydrase inhibitors, α2- and...
