Facial Aging in Thyroid Eye Disease: Quantification by Artificial Intelligence
Bibliographic record
Abstract
This study aims to elucidate the effect of thyroid eye disease on perceived facial aging. In this cross-sectional cohort study, an artificial intelligence (AI) model (previously trained to infer patient age from facial photographs) was used to analyze facial aging changes in 2 groups: (1) TED patients and (2) age-matched controls. Standardized photos were analyzed from initial and final visits of patients with more than 5 years of clinic follow-up. The performance of the AI model was compared to that of an expert group composed of oculoplastic surgeons. Chronological, AI-inferred, and expert-estimated ages were compared. AI initially estimated TED subjects to be 4.3 years older than their actual age, compared to 0.63 years older in control subjects (P=0.005). At the final timepoint, TED patients were estimated to be 5.0 years younger than their actual age, compared to 1.4 years younger in controls (P=0.004). The mean difference between actual and AI-inferred change in age was 9.3 years for TED patients and 2.0 years for controls (P<0.001). Human experts tended to underestimate age across all groups and time points. The AI model was significantly more accurate than human experts in estimating the age of controls at the final time point. AI estimated that TED patients were older than their chronological age initially and younger than their chronological age at the final follow-up. This may be due to initial pathologic soft tissue volume expansion in TED, which may compensate for age-related soft tissue deflation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".