EyeModelHub
Home Subspecialties Oculoplastics Model card
§Model Card

Post-Blepharoplasty Age Prediction AI (FaceAge)

Assessment of postoperative rejuvenation using AI-estimated facial age

Chiou T.W. · 2024 · Taiwan · doi:10.1093/asj/sjae182
Open DOI
Measurement/Regression CNN External photo Internally validated
More attributes
Anatomy · Periorbital soft tissueConditions · BlepharoptosisSingle-centern = 150 patients · NR images
§01Overview

Brief overview

This study aggregates four commercial facial age-estimation CNN APIs — Amazon Rekognition, Microsoft Azure Face, Face++, and Inferdo — to quantify perceived age reduction after lower blepharoplasty from standard facial photographs. In a single-centre retrospective cohort of 150 Asian patients, the platform estimated a mean postoperative rejuvenation effect of roughly 2 years, with Face++ showing the strongest standalone accuracy (ICC 0.78; MAE 4.8 years). The software was implemented as a Python/Qt graphical interface and tested only on pre/postoperative images acquired at one institution. No code repository, pretrained weights, external validation cohort, or clinical deployment workflow were reported.

§02Performance
Headline performance

Best individual model: Face++ (ICC 0.78; MAE 4.82 yrs).

Full metrics — as reported
Best individual model: Face++ (ICC 0.78; MAE 4.82 yrs).
Ensemble (average of four): ICC 0.71; MAE 5.94 yrs.
Mean perceived age reduction across all patients: −1.68 years (p < .0001).
Men showed greater reduction than women; combined upper+lower procedures produced the largest effect.
Calibration · Uncertainty
Not reported.
Bias · Fairness
Not reported.
§03Data & Validation
Study designRetrospective cohort
Center typeSingle-center
Patients150
Images / eyesNot reported
SplitNot reported
Reporting frameworks None stated
Age range>18
Sex (% female)Not reported
Race / ethnicity reportedN
Subgroup performanceN
§04Deployment
Deployment maturity
  1. Concept
  2. Prototype
  3. Internal val.
  4. External val.
  5. Regulator
  6. Clinical
Regulatory status
None No FDA / Health Canada / CE clearance.
Artifacts & license
Code repository none
Pretrained weights none
Live demo
License Proprietary
§05Quality Review · APPRAISE-AI
Total score
56 /100 Moderate
ClinicalDataMethodRobust.Report.Repro.
Sub-domain scores
Clinical relevance 4/4 100%
Data quality 17/24 71%
Methodological conduct 8/20 40%
Robustness of results 11/20 55%
Reporting quality 11/12 92%
Reproducibility 5/20 25%
Why this score?

The APPRAISE-AI tool grades AI/ML medical studies across 24 items in 6 subdomains, scored independently by two reviewers. The total reflects the methodological transparency of the publication — not the underlying clinical value of the model.

How to read this: high scores in clinical relevance and reporting with low scores in methodological conduct, robustness, or reproducibility is the dominant pattern in ophthalmic AI today.

Quality bands: Low <40 · Moderate 40–59 · High 60–79 · Very High 80+. Most published ophthalmic AI sits in the Low–Moderate band; studies that break into High typically combine multi-center datasets, prospective evaluation, and open-source release.

§06Full Metadata
Citation & identification
Bibliographic record
Model IDoculoplastics_chiou_2024
Full author listYen, C. I., Hsiao, Y. C., & Chen, H. C.
JournalAesthet Surg J
DOI10.1093/asj/sjae182
ConditionsBlepharoptosis
Architecture
Model internals
Architecture familyCNN
Architecture detailFour commercial age-estimation CNN APIs, wrapped in a custom application (“FaceAge”).
Funding & conflicts
Disclosures
FundingNot reported
Conflicts of interestNo conflicts
Card lifecycle
Status, version, reviewers
Card statusPublished
Card versionv1.0.0
First added2026-04-28
Last reviewed2026-04-28
Reviewersattribution opt-in pending
Update history
Card changelog
  • 2026-04-28 initial publication (v1.0.0)
← Back to Oculoplastics