Prediction of Early Visual Outcome of Small-Incision Lenticule Extraction (SMILE) Based on Deep Learning.
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: ResNet50 and XGBoost models predicted early visual recovery from SMILE surgical videos, with prospective cohorts used for testing. The article reports 318 eyes but inconsistent patient totals (159 in the abstract versus 164 across results cohorts), and the eye-level split may leave paired-eye dependence.
Technology: ResNet50 classifies scanning images from SMILE surgical videos; PCA-compressed image probabilities feed an XGBoost video-level visual-recovery classifier; Grad-CAM shows image regions.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- ResNet50 classifies scanning images from SMILE surgical videos; PCA-compressed image probabilities feed an XGBoost video-level visual-recovery classifier; Grad-CAM shows image regions.
- Limitation / still unknown
- ResNet50 and XGBoost models predicted early visual recovery from SMILE surgical videos, with prospective cohorts used for testing. The article reports 318 eyes but inconsistent patient totals (159 in the abstract versus 164 across results cohorts), and the eye-level split may leave paired-eye dependence. The result is limited to the reported cohort, data or experimental conditions and does not establish broader clinical or field benefit.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC10011351/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.