The science behind AI skin analysis.
Peer-reviewed research on AI reading skin from photos, summarised in plain language.
A Dermatology AI Trained on 2 Million Skin Images
PanDerm, published in Nature Medicine in 2025, learned from over 2 million real skin images and helped non-specialists read skin photos 16.5% more accurately.
Read the summary →ResearchAI Reads Wrinkles, Pigmentation and Redness From a Face Photo
A 2025 study in the Journal of Cosmetic Dermatology: one AI model graded skin type, pigmentation, redness and wrinkle severity from ordinary face photos with 85% accuracy.
Read the summary →ResearchSelfie AI Compared With 50 Dermatologists
1,041 women took selfies. An AI graded seven facial signs and was compared with 50 US dermatologists: strong agreement on five of the seven signs.
Read the summary →ResearchAI Now Matches Dermatologists in Skin Diagnosis
Large-scale studies show that deep learning systems can diagnose skin conditions as accurately as board-certified dermatologists - and more accurately than general practitioners.
Read the summary →ResearchAI Can Read Your Skin from a Single Selfie
Researchers have trained AI models to predict skin type, pigmentation, wrinkles, and redness from standard facial photographs with over 85% accuracy.
Read the summary →ResearchDeep Learning Hits 94% Accuracy Across 144 Skin Conditions
A comprehensive review of 64 AI models shows consistently high accuracy for acne, rosacea, eczema, and dozens of other conditions - with 92% of doctors finding AI assistance useful.
Read the summary →IndustryYour Phone Camera Is Good Enough for Skin Analysis
Meta-analyses confirm that smartphone-based AI achieves clinically viable accuracy for skin diagnosis, even outside clinical settings.
Read the summary →ResearchAI Can Detect and Grade Acne Severity from Phone Photos
Computer vision systems can now identify individual acne lesions and grade severity from smartphone images, outperforming previous benchmarks by 18 percentage points.
Read the summary →IndustryAI Is Replacing Subjective Skin Grading with Data
New AI frameworks enable objective, reproducible measurement of skin quality - transforming how aesthetic practices evaluate and track treatment outcomes.
Read the summary →Independent studies of AI skin analysis in general, not tests of DiemSkin.
See it on your own face.
One selfie, a full skin report in under a minute.