Predicting Age-Related Facial Hyperpigmentation via Dermatologist Knowledge Elicitation and Generative Modeling

Facial hyperpigmentation is a primary marker of skin aging in Asian populations. While many artificial intelligence (AI)-based aging simulators exist on social media, they often lack scientific transparency and dermatological validation. This study introduces and validates a novel facial aging simulator specifically engineered to provide personalized, evidence-based predictions of pigmentary spot progression according to varying levels of ultraviolet (UV) exposure and photoprotection. The simulator utilizes a dual-tool framework: Elicitation Based Aging Simulator (EBAS) and AgingMapGAN (AMGAN). EBAS leverages the collective expertise of 28 dermatologists via a structured Delphi process and causal Bayesian belief networks (BBNs) to model skin aging trajectories. AMGAN, a conditional generative adversarial network, provides high-resolution visual representations of these trajectories. The model was trained on a standardized dataset of 600 individuals and focused on the density of pigmentary spots (DPS) on the cheek. Model performance was benchmarked against expert clinical grading using correlation metrics. The simulator demonstrated high accuracy in replicating expert logic (Pearson’s correlation 0.96). In a case study of a 38-year-old female of Chinese descent, the model predicted the 15-year probability of a clinically significant progression (a two-grade increase in DPS). In the absence of photoprotection, the probability of reaching this elevated grade by age 53 was 71.35%, whereas regular daily application of SPF 50+ sunscreen reduced this probability to 39.24%. This framework represents the application of a scientifically validated image-generation tool for predicting age-related hyperpigmentation based on individual exposome factors. By integrating dermatological knowledge, this simulator provides a robust educational and research resource for personalized skincare strategies. The findings confirm that consistent photoprotection significantly mitigates the 15-year trajectory of premature facial aging, offering a scientifically validated foundation for public health communication on prevention. Facial hyperpigmentation is a well-established marker of skin aging and photoaging; it represents both a significant indicator of premature aging and a major esthetic concern, particularly in Asian populations. Many smartphone and social media applications claim to predict facial aging, but most lack scientific validation. This work presents a scientifically rigorous facial aging simulator that generates personalized probabilities and visual predictions of age-related pigmentation changes. The tool integrates two previously published and validated works: first, the elicitation of 28 dermatologists’ intrinsic knowledge across the world, and second, an AI-powered image generation system. The simulator enables users to visualize realistic 15-year projections of their facial hyperpigmentation, such as solar lentigo, incorporating both visual representations and probabilistic data, under varying degrees of sun exposure and photoprotection scenarios. Beyond the Asian skin model illustrated in this study, which evaluated scenarios ranging from no protection to daily high-SPF (50+) use, occasional application, and combined chemical/physical barriers, the simulator can be adapted to explore various levels of sun exposure, photoprotective behaviors, genetic factors, and environmental influences across diverse skin tones. This simulator, developed with dermatological expertise, is useful for scientifically and rigorously addressing the expectations of consumers concerned with specific markers of premature facial aging, such as facial hyperpigmentation. Furthermore, this tool enables public health initiatives focused on photoprotection and skin longevity, given their intrinsic link to premature aging.