Healthcare registry data can show early risk patterns for melanoma skin cancer, according to a study from the University of Gothenburg. Using AI, it is possible to identify small groups within the population that have a significantly higher risk of developing melanoma within five years.
The study was based on registry data that is routinely collected on the whole of Sweden's adult population. The analyzed data included age, sex, diagnoses, use of medications and socioeconomic status. Of the 6,036,186 individuals included, 38,582 (0.64%) developed melanoma during the five years of the study.
Martin Gillstedt was responsible for much of the analysis:
"Our study shows that data which is already available within healthcare systems can be used to identify individuals at higher risk of melanoma," says Martin Gillstedt, a doctoral student at the University of Gothenburg's Sahlgrenska Academy and a statistician at Sahlgrenska University Hospital's Department of Dermatology and Venereology. "This is not a form of decision support that is currently available in routine healthcare, but our results give a clear signal that registry data can be used more strategically in the future."
33% probability of melanoma
When the researchers compared different AI models, the differences became clear. The most advanced model was able to distinguish individuals who subsequently developed melanoma from those who did not in about 73% of cases, compared with about 64% when only age and sex were used. The combination of diagnoses, medications and sociodemographic data made it possible to identify small, high-risk groups for whom the risk of developing melanoma within five years was around 33%.
![[none]](https://www.gu.se/sites/default/files/styles/50_10_6_xmedium_1x/public/2026-04/duobild%2016x9%20Martin%20Gillstedt%20o%20Sam%20Polesie.jpg?h=e6d74438&itok=yQdAKtx4)
The study was led by Sam Polesie, Associate Professor of Dermatology and Venereology at the University of Gothenburg and a dermatologist at Sahlgrenska University Hospital:
"Our analyses suggest that selective screening of small, high-risk groups could lead to both more accurate monitoring and more efficient use of healthcare resources. This would involve bringing population data into precision medicine and supplementing clinical assessments."
The researchers emphasize that more research and policy decisions are needed before the method can be introduced in healthcare. However, the results show that AI models trained on large amounts of registry data can become an important source of support for more personalized risk assessments and future screening strategies for melanoma.
The study was carried out in collaboration between the University of Gothenburg and Chalmers University of Technology.
Article:: Predicting melanoma impact on the Swedish healthcare system from the adult population using machine learning on registry data, Acta Dermato-Venereologica. DOI: https://doi.org/10.2340/actadv.v106.44610
