Improvement of Multiple Generations of Intraocular Lens Calculation Formulae with a Novel Approach Using Artificial...

Area of Science:

• Ophthalmology
• Artificial Intelligence
• Biomedical Engineering

Background:

• Cataract surgery is the most common ophthalmic procedure worldwide.
• Accurate intraocular lens (IOL) power calculation is crucial for achieving optimal visual outcomes.
• Existing IOL calculation formulas may require refinement to minimize refractive prediction errors.

Purpose of the Study:

• To present a novel methodology for optimizing existing IOL calculation formulas.
• To develop hybrid IOL formulas integrated with artificial intelligence (AI).
• To enhance the precision of refractive outcome predictions in cataract surgery.

Main Methods:

• Utilized preoperative biometric and postoperative outcome data from a single institution.
• Employed a numeric computing environment for data analysis and formula refinement.
• Applied supervised learning artificial intelligence (AI) algorithms to enhance existing IOL formulas.

Main Results:

• AI algorithms significantly improved the mean absolute error (MAE) of IOL formulas.
• Enhanced formulas demonstrated a higher number of eyes within 0.5 diopters of predicted refraction.
• Statistical analysis confirmed the significant improvement provided by AI enhancement (P < 0.05).

Conclusions:

• A novel AI-based methodology effectively optimizes existing IOL calculation formulas.
• This AI-driven approach holds significant potential for improving clinical outcomes in cataract surgery.
• The integration of AI offers a promising avenue for advancing ophthalmic surgical precision.