Predicting Melanoma Impact on the Swedish Healthcare System from the Adult Population Using Machine Learning on Registry Data
DOI:
https://doi.org/10.2340/actadv.v106.44610Keywords:
melanoma, machine learning, dermatology, healthcare register, predictionAbstract
Melanoma incidence has increased in Western countries over the past 50 years, leading to significant healthcare costs. In Sweden, comprehensive healthcare registries enable large-scale prediction studies using machine learning. Several machine learning models were evaluated to predict melanoma diagnoses using Swedish registry data, assessing the added value of diagnostic and medication data beyond demographics. The study included all adults in Sweden with continuous residency for 9.5 years (n = 6,036,186). The outcome was a melanoma diagnosis, including melanoma in situ, recorded within 5 years after the index date (31 December 2014). Predictors included age, sex, income, education, marital status, region of birth, diagnoses, and dispensed drugs. Models tested were logistic regression, gradient boosting, random forests, and a neural network. A total of 38,582 individuals (0.64%) developed melanoma. The gradient boosting model using all predictors performed best, with an area under the receiving operating characteristics curve (AUC) of 0.735 (95% confidence interval [CI], 0.725–0.746). When diagnosis and medication data were excluded, AUC dropped to 0.681 (95% CI: 0.670–0.691). The findings highlight that including healthcare codes improves predictive performance, and demonstrate the utility of Swedish registries for computational phenotyping. This approach may support early detection of melanoma and targeted follow-up.
Downloads
References
Claeson M, Gillstedt M, Whiteman DC, Paoli J. Lethal melanomas: a population-based registry study in Western Sweden from 1990 to 2014. Acta Derm Venereol 2017; 97: 1206–1211. DOI: https://doi.org/10.2340/00015555-2758
Godar DE. Worldwide increasing incidences of cutaneous malignant melanoma. J Skin Cancer 2011; 2011: 858425. DOI: https://doi.org/10.1155/2011/858425
Guy GP Jr, Thomas CC, Thompson T, Watson M, Massetti GM, Richardson LC, et al. Vital signs: melanoma incidence and mortality trends and projections – United States, 1982–2030. MMWR Morb Mortal Wkly Rep 2015; 64: 591–596.
Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022. CA Cancer J Clin2022; 72: 7–33. DOI: https://doi.org/10.3322/caac.21708
Whiteman DC, Green AC, Olsen CM. The growing burden of invasive melanoma: projections of incidence rates and numbers of new cases in six susceptible populations through 2031. J Invest Dermatol 2016; 136: 1161–1171. DOI: https://doi.org/10.1016/j.jid.2016.01.035
Pukkala E, Engholm G, Højsgaard Schmidt LK, Storm H, Khan S, Lambe M, et al. Nordic Cancer Registries: an overview of their procedures and data comparability. Acta Oncol 2018; 57: 440–455. DOI: https://doi.org/10.1080/0284186X.2017.1407039
Laugesen K, Ludvigsson JF, Schmidt M, Gissler M, Valdimarsdottir UA, Lunde A, et al. Nordic health registry-based research: a review of health care systems and key registries. Clin Epidemiol 2021; 13: 533–554. DOI: https://doi.org/10.2147/CLEP.S314959
Seedahmed MI, Mogilnicka I, Zeng S, Luo G, Whooley MA, McCulloch CE, et al. Performance of a computational phenotyping algorithm for sarcoidosis using diagnostic codes in electronic medical records: case validation study from 2 veterans Affairs Medical Centers. JMIR Form Res 2022; 6: e31615. DOI: https://doi.org/10.2196/31615
Katalinic A, Eisemann N, Waldmann A. Skin cancer screening in Germany: documenting melanoma incidence and mortality from 2008 to 2013. Dtsch Arztebl Int 2015; 112: 629–634. DOI: https://doi.org/10.3238/arztebl.2015.0629
Matsumoto M, Wack S, Weinstock MA, Geller A, Wang H, Solano FX, et al. Five-year outcomes of a melanoma screening initiative in a large health care system. JAMA Dermatol 2022; 158: 504–512. DOI: https://doi.org/10.1001/jamadermatol.2022.0253
Breiman L. Random forests. Machine Learning 2001; 45: 5–32. DOI: https://doi.org/10.1023/A:1010933404324
Mason L, Baxter J, Bartlett P, Frean M. Boosting algorithms as gradient descent. Advances in neural information processing systems, 1999; 12. https://papers.nips.cc/paper_files/paper/1999/file/96a93ba89a5b5c6c226e49b88973f46e-Paper.pdf
DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988; 44: 837–845. DOI: https://doi.org/10.2307/2531595
Benjamini Y, Yekutieli D. The control of the false discovery rate in multiple testing under dependency. Ann Statist 2001; 29: 1165–1188. DOI: https://doi.org/10.1214/aos/1013699998
Chauhan A, Walton M, Manias E, Walpola RL, Seale H, Latanik M, et al. The safety of health care for ethnic minority patients: a systematic review. Int J Equity Health 2020; 19: 118. DOI: https://doi.org/10.1186/s12939-020-01223-2
Hadziabdic E, Heikkila K, Albin B, Hjelm K. Problems and consequences in the use of professional interpreters: qualitative analysis of incidents from primary healthcare. Nurs Inq 2011; 18: 253–261. DOI: https://doi.org/10.1111/j.1440-1800.2011.00542.x
Ezenwa E, Buster K. Health disparities and skin cancer in people of color. Pract Dermatol 2019: 38–42.
Wang HH, Wang YH, Liang CW, Li YC. Assessment of deep learning using nonimaging information and sequential medical records to develop a prediction model for nonmelanoma skin cancer. JAMA Dermatol 2019; 155: 1277–1283. DOI: https://doi.org/10.1001/jamadermatol.2019.2335
Gillstedt M, Polesie S. Ability to predict melanoma within 5 years using registry data and a convolutional neural network: a proof of concept study. Acta Derm Venereol 2022; 102: adv00750. DOI: https://doi.org/10.2340/actadv.v102.2028
Philonenko P, Kokh V, Blinov P. Combining survival analysis and machine learning for mass cancer risk prediction using EHR data. arXiv preprint arXiv:230915039, 2023. DOI: https://doi.org/10.21203/rs.3.rs-3611680/v1
Li L, Pu C, Jin N, Zhu L, Hu Y, Cascone P, et al. Prediction of 5-year overall survival of tongue cancer based machine learning. BMC Oral Health 2023; 23: 567. DOI: https://doi.org/10.1186/s12903-023-03255-w
Baltzer N, Sundstrom K, Nygard JF, Dillner J, Komorowski J. Risk stratification in cervical cancer screening by complete screening history: applying bioinformatics to a general screening population. Int J Cancer 2017; 141: 200–209. DOI: https://doi.org/10.1002/ijc.30725
Cui Y, Shi X, Wang S, Qin Y, Wang B, Che X, et al. Machine learning approaches for prediction of early death among lung cancer patients with bone metastases using routine clinical characteristics: an analysis of 19,887 patients. Front Public Health 2022; 10: 1019168. DOI: https://doi.org/10.3389/fpubh.2022.1019168
Tang J, Wang X, Wan H, Lin C, Shao Z, Chang Y, et al. Joint modeling strategy for using electronic medical records data to build machine learning models: an example of intracerebral hemorrhage. BMC Med Inform Decis Mak 2022; 22: 278. DOI: https://doi.org/10.1186/s12911-022-02018-x
Liljendahl MS, Ibler K, Vestergaard C, Skov L, Jain P,Rudolfsen JH, et al. Identifying mild-to-moderate atopic dermatitis using a generic machine learning approach: a Danish National Health Register Study. Acta Derm Venereol 2025; 105: adv42250. DOI: https://doi.org/10.2340/actadv.v105.42250
Dullerud N, Roth K, Hamidieh K, Papernot N, Ghassemi M. Is fairness only metric deep? evaluating and addressing subgroup gaps in deep metric learning. arXiv preprint arXiv:220312748, 2022.
Additional Files
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Martin Gillstedt, Lena Stempfle, John Paoli, Fredrik D. Johansson, Sam Polesie
This work is licensed under a Creative Commons Attribution 4.0 International License.
All digitalized ActaDV contents is available freely online. The Society for Publication of Acta Dermato-Venereologica owns the copyright for all material published until volume 88 (2008) and as from volume 89 (2009) the journal has been published fully Open Access, meaning the authors retain copyright to their work.
Unless otherwise specified, all Open Access articles are published under CC-BY-NC licences, allowing third parties to copy and redistribute the material in any medium or format and to remix, transform, and build upon the material for non-commercial purposes, provided proper attribution to the original work.
