Facial Aging in Thyroid Eye Disease: Quantification by Artificial Intelligence.

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.