EyeModelHub
Home Subspecialties Oculoplastics Model card
§Model Card

KestyAI

Automated quantification of cosmetic improvement after periorbital laser surgery

Kesty C.E. · 2025 · USA · doi:10.1111/jocd.70022
Open DOI
Measurement/Regression Commercial API External photo Concept
More attributes
Anatomy · EyelidConditions · Upper eyelid dermatochalasisConditions · periorbital rhytidsConditions · lower eyelid skin laxitySingle-centern = 10 patients · 20 photos images
§01Overview

Brief overview

Kesty AI is a proprietary machine-learning system used to quantify cosmetic outcomes after combined CO2 laser blepharoplasty and Er:YAG resurfacing from standardized facial photographs. In this 10-patient single-center case series, the model generated Fitzpatrick Wrinkle Scale and Glogau Wrinkle Scale scores from pre- and post-procedure images, showing improved wrinkle severity after treatment. The authors report the algorithm was trained on thousands of dermatologist-labeled facial photographs, but no architectural details, performance metrics, calibration analyses, or external validation data were provided. Code, pretrained weights, and training datasets were not released. The system was used as an adjunctive cosmetic assessment tool rather than a clinical decision-making model and remains a closed commercial platform without independent reproducibility.

§02Performance
Headline performance

Reported cohort averages only (no statistical testing):

Full metrics — as reported
Reported cohort averages only (no statistical testing):
• FWS: 6.8 → 5.4
• Glogau: 3.5 → 3.0
No validation metrics (MAE, ICC, reliability) or human–AI comparisons provided.
Calibration · Uncertainty
Not reported.
Bias · Fairness
Not reported.
§03Data & Validation
Study designCase series
Center typeSingle-center
Patients10
Images / eyes20 photos
SplitNot reported
Reporting frameworks None stated
Age range40-73
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
Pretrained weights none
Live demo none
License Proprietary
§05Quality Review · APPRAISE-AI
Total score
29 /100 Low
ClinicalDataMethodRobust.Report.Repro.
Sub-domain scores
Clinical relevance 4/4 100%
Data quality 7/24 29%
Methodological conduct 4/20 20%
Robustness of results 0/20 0%
Reporting quality 10/12 83%
Reproducibility 4/20 20%
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_kesty_2025
Full author listKesty, K. R.
JournalJ Cosmet Dermatol
DOI10.1111/jocd.70022
ConditionsUpper eyelid dermatochalasis, periorbital rhytids, lower eyelid skin laxity
Architecture
Model internals
Architecture familyCommercial API
Architecture detailKesty AI-generated wrinkle severity scores (Fitzpatrick Wrinkle Scale, Glogau Scale) from pre–post facial photographs.
Funding & conflicts
Disclosures
FundingNot reported
Conflicts of interestK.R.K. is the Founder of Kesty AI
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