Periorbital Rejuvenation Analysis AI Platform
Quantification of postoperative rejuvenation using AI-estimated facial age
▸ More attributes
Brief overview
This study evaluated four pretrained convolutional neural network (CNN) facial-analysis platforms — Face++, Betaface, Facelytics, and Everypixel — to quantify perceived age reduction after brow lift and blepharoplasty using standardized pre- and postoperative facial photographs from 153 patients at a single cosmetic surgery practice. Across all platforms, mean age-estimation error was 10.6%, with algorithms generally underestimating true age. AI analysis found an average perceived age reduction of 1.03 years after periorbital rejuvenation surgery, with brow lift independently associated with the greatest reduction (1.43 years). The study used proprietary third-party CNN systems rather than a newly trained model. No code, weights, external validation, regulatory clearance, or clinical deployment were reported.
Platforms generally underestimated true age; preoperative percentage errors ranged 4–18%.
Platforms generally underestimated true age; preoperative percentage errors ranged 4–18%. Overall AI-estimated age reduction: −1.03 years (P < .001). Brow lift independently associated with −1.43 years (P = .031); blepharoplasty alone not significant.
| Study design | Retrospective cohort |
|---|---|
| Center type | Single-center |
| Patients | 153 |
| Images / eyes | Not reported |
| Split | Not reported |
| Reporting frameworks | None stated |
| Age range | >18 |
|---|---|
| Sex (% female) | Not reported |
| Race / ethnicity reported | N |
| Subgroup performance | N |
- Concept
- Prototype
- Internal val.
- External val.
- Regulator
- Clinical
▸ 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.
Bibliographic record ▸
| Model ID | oculoplastics_kreh_2025 |
|---|---|
| Full author list | Roider, L., Firouzbakht, P. K., Nathan, C., Prada, C. A., Lund, H. G., Jr, Sarhaddi, D., & Chen, K. |
| Journal | Aesthet Surg J |
| DOI | 10.1093/asj/sjae201 |
| Conditions | Periorbital aging, brow ptosis, blepharochalasis |
Model internals ▸
| Architecture family | Commercial API |
|---|---|
| Architecture detail | Four off-the-shelf age-estimation CNN platforms (Face++, Betaface, Facelytics, Everypixel), averaged into a mean estimated age (MEA). |
Disclosures ▸
| Funding | Not reported |
|---|---|
| Conflicts of interest | No conflicts |
Status, version, reviewers ▸
| Card status | Published |
|---|---|
| Card version | v1.0.0 |
| First added | 2026-04-28 |
| Last reviewed | 2026-04-28 |
| Reviewers | attribution opt-in pending |
Card changelog ▸
- 2026-04-28 initial publication (v1.0.0)