American Academy of Ophthalmology Meeting

American Academy of Ophthalmology Meeting

Issue: January 2022
Source:

Gupta S, et al. AcuSimX, a predictive tool based on inverse finite element method (iFEM) and artificial intelligence (AI), for planning refractive surgery. Presented at: American Academy of Ophthalmology meeting; Nov. 12-15, 2021; New Orleans.


Disclosures: The authors report no relevant financial disclosures.

December 29, 2021
1 min read
Save

AI-based predictive software helps choose refractive procedure for each patient

Issue: January 2022
Source:

Gupta S, et al. AcuSimX, a predictive tool based on inverse finite element method (iFEM) and artificial intelligence (AI), for planning refractive surgery. Presented at: American Academy of Ophthalmology meeting; Nov. 12-15, 2021; New Orleans.


Disclosures: The authors report no relevant financial disclosures.

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

An AI-based predictive tool helps selecting the most appropriate procedure for refractive surgery, minimizing the risk of postoperative ectasia.

A study presented in a poster at the American Academy of Ophthalmology meeting showed correspondence between predicted outcomes and in-vivo postoperative outcomes.

“Decision making for refractive surgery is based on the evaluation of corneal structure by corneal topography and corneal biomechanics by measurement of corneal strength. However, clinicians are often challenged by confusing scenarios,” Sneha Gupta, MBBS, said.

Cases with normal biomechanics but suspicious topography, or vice versa, often make the choice between the three options of LASIK, SMILE and PRK difficult.

The AcuSimX software is based on the finite element method (FEM), a numerical technique that subdivides a large complex system into smaller simpler parts called finite elements.

“We can study a simulated reaction to any action involving these parts,” Gupta said. “Patient-specific inverse FEM model is generated using preoperative Corvis-ST deformation, Pentacam-HR tomography (Oculus) and intended aspheric ablation profile. AcuSimX is then able to estimate postoperative corneal stiffness and the risk of ectasia after LASIK, SMILE and PRK.”

In a study, this method was used in 529 eyes from multiple centers around the world of which 280 had LASIK, 150 had SMILE and 99 had PRK. Preoperative data were run through the simulation program and postoperative validation was done using again Pentacam and Corvis. The results showed accuracy of postop CS predictions, with a mean absolute error of 6.24 and 6.47 N/m in the training and test cohorts The software successfully predicted the postoperative biomechanics of 7 eyes that developed ectasia.

“Currently there is no tool to predict the postoperative outcomes of refractive surgery. AcuSimX is the first software for choosing the right procedure including patient-specific data,” Gupta said.