Post

New research · Ophthalmology
Current eye research · 3d
Cohort studyCurrent eye research · 2026

The Quest to Predict Surgically Induced Astigmatism After Cataract Surgery: Lessons for Toric IOL Planning.

Amanda C Pan, Klemens P Kaiser, Stefan Raidl … Jascha A Wendelstein
Read paper
OphthalmologyCohort study

Linear regression best predicted post-cataract corneal power changes, beating machine learning models.

The Quest to Predict Surgically Induced Astigmatism After Cataract Surgery: Lessons for Toric IOL Planning.

Amanda C Pan … Jascha A Wendelstein
Current eye research · 2026
Purpose

This study compared traditional statistical models with machine learning algorithms for predicting surgically induced astigmatism after cataract surgery, aiming to identify the most accurate and generalizable method among linear regression, regression trees, random forests, and neural networks.

Methods

Retrospective analysis was performed on 321 eyes (321 patients) undergoing phacoemulsification at a tertiary center.

n = 321 eyes
0.043
Results
0.043
linear regression's prediction error for corneal power change - lower is more accurate
n = 321 eyes
More results

Tree-based models performed slightly worse, while neural networks showed substantial overfitting with markedly higher test errors.

Preoperative astigmatism and corneal radii were the strongest predictors.

“
Conclusion · 1 of 3

KAST0 and KAST45 were not predictably modeled, whereas changes in KEQ.post were.

Conclusion · 2 of 3

Multivariable linear regression provided the most accurate and reliable predictions, while more complex machine-learning models (especially neural networks) overfit the limited dataset and offered no clinical advantage.

Conclusion · 3 of 3

The relationship between preoperative biometrics and postoperative equivalent power appears predominantly linear, though larger datasets may enhance machine-learning performance.

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving