Machine learning for toric IOL power calculations
Research type
Research Study
Full title
The use of machine learning to improve toric intraocular lens power prediction for cataract surgery.
IRAS ID
322993
Contact name
Jonathan Moore
Contact email
Sponsor organisation
Cathedral Eye Clinic
Duration of Study in the UK
1 years, 0 months, 1 days
Research summary
Cataract surgery is the most commonly performed elective surgery in the UK, and more than 11 million eyes undergoing intraocular lens (IOL) implantation globally each year. Historically, the primary aim of cataract surgery was to remove the opacified crystalline lens and improve visual potential by implanting an artificial intraocular lens. Postoperative refractive error could then be corrected with spectacles. However, cataract surgery is increasingly becoming a refractive procedure, with the aim of minimising postoperative refractive error and therefore improving unaided visual acuity reducing the need for spectacles. Optimal refractive outcomes are achieved by accurately selecting the appropriate IOL power.
In addition to myopia (short-sightedness) and hyperopia (long-sightedness), astigmatism is a type of refractive error. The curvature of the front surface of the eye means that light rays are not brought to a single focal point, causing blurred vision. Corneal astigmatism can limited unaided visual acuity following cataract surgery. A study of patients undergoing cataract surgery in Northern Ireland found that 41% of eyes had significant (greater than 1 dioptre) corneal astigmatism preoperatively. The use of toric intraocular lenses can greatly reduce postoperative refractive astigmatism and improve visual outcomes. The correct strength of toric IOL is determined using mathematical formulas. However, current toric IOL calculations have limitations. The use of machine learning to enhance the accuracy of toric IOL power prediction is likely to improve refractive outcomes for patients with significant corneal astigmatism.
REC name
HSC REC B
REC reference
23/NI/0074
Date of REC Opinion
21 Jul 2023
REC opinion
Further Information Favourable Opinion