Digital Skin Health Insights Report 2026

This report presents a retrospective descriptive analysis of approved aggregate ScanSkinAI scan-history data generated through routine platform use between 1 January and 28 July 2026. The unit of analysis is a scan record, not a person. It is therefore essential to read every result as a distribution of platform outputs rather than a count of unique users or clinically confirmed conditions.

Two separate analysis datasets are described. The risk-band distribution included 50,265 scan records. The AI-output distribution included 45,270 medical skin-module scans. These datasets have different denominators and must not be combined. The AI-output distribution was available for a narrower eligible subset of medical skin-module scans; no further record-level breakdown is published.

Within the medical skin-module subset, the most frequent individually named AI-supported output category was benign naevus / mole, representing 13.9% of module scans. “Normal skin” represented 11.8%, followed by contact dermatitis at 7.3%, basal cell carcinoma indication at 6.5%, acne vulgaris at 5.9% and melanoma indication at 5.0%. The cancer-related categories retain the word “indication” because they are preliminary AI-supported outputs, not diagnoses.

Approximately 26% of medical skin-module scans were distributed across approximately 430 other lower-frequency labels. This broad long tail shows that the platform output distribution extends well beyond the most frequent named categories; it does not establish the prevalence of approximately 430 diseases.

Within the risk-band dataset, 52.8% of scan records fell in the 1–39 low band, 27.7% in the 40–69 moderate band and 18.6% received a 70–100 high-concern flag. A small proportion recorded a score of zero (0.7%) or had no reportable risk-band value (0.3%). A high-concern flag does not confirm cancer, while a low score does not rule out a medical condition.

The findings describe platform activity only. They cannot be used to estimate disease prevalence or incidence, evaluate diagnostic accuracy, count confirmed cancers, establish clinical outcomes, or describe risk in the general population. No individual user records, identifiers, images or row-level data are published.