Artificial Intelligence in Cornea, Refractive, and Cataract Surgery

Aazim A. Siddiqui; John G. Ladas; Jimmy K. Lee


Curr Opin Ophthalmol. 2020;31(4):253-260. 

In This Article

Artificial Intelligence and Cataract Surgery: The use of Objective Postoperative Data

Artificial intelligence is dependent on a large volume of accurate postoperative outcome data. Generally, this data is composed of a postoperative manifest refraction (MRx). However, MRx measurements are often suboptimal because of technique variability, room length, patient's subjective participation, and time taken to perform measurements. Currently, this data is supplied by a few high-volume surgeons with standardized refraction protocols.

The limitations of obtaining high-quality postoperative outcomes data may be addressed by using automated refractors or wavefront analyzers to supply this data. At present, automated refractors function as a device to provide refractive and sometimes biometric analyses for a given eye. Although automated refraction (ARx) serves as a useful tool, it may evolve into a method of integrating preoperative biometry data and postoperative refractive outcomes.

The use of ARx outcome data can potentially help eliminate most issues that occur with MRx acquisition. However, the substitution of MRx with ARx data for the purposes of IOL formula optimization is still unclear and is currently being investigated in ongoing studies. If this substitution is shown to be valid, this will allow for collection of 'big data' and lead to development of artificial intelligence-based IOL formulas.

There are many potential benefits of artificial intelligence integration with automated postoperative data. Customized artificial intelligence-IOL calculation formulas may be developed for a given surgeon with their own postoperative data. This could help reduce surgeon-to-surgeon variation, which is responsible for a significant portion of error in current IOL calculation methodologies. Further, this could allow for ongoing optimization that continually improves in perpetuity. The 'big data' stored within an automated refractor would be able to characterize an eye as one with 'standard' parameters or one with 'unusual' parameters. Thus, artificial intelligence could preoperatively highlight eyes that are 'at-risk' for a postoperative refractive surprise.