journal article·2022-12-07Open access

Clinical Risk Factor Prediction for Second Primary Skin Cancer: A Hospital-Based Cancer Registry Study

Hsi-Chieh Lee, Tsung-Chieh Lin, Chi-Chang Chang, Yen-Chiao Angel Lu, Chih-Min Lee, Bolormaa Purevdorj

Applied Sciences· Volume 12· Issue 24

Abstract

This study aimed to develop a risk-prediction model for second primary skin cancer (SPSC) survivors. We identified the clinical characteristics of SPSC and created awareness for physicians screening high-risk patients among skin cancer survivors. Using data from the 1248 skin cancer survivors extracted from five cancer registries, we benchmarked a random forest algorithm against MLP, C4.5, AdaBoost, and bagging algorithms for several metrics. Additionally, in this study, we leveraged the synthetic minority over-sampling technique (SMOTE) for the issue of the imbalanced dataset, cost-sensitive learning for risk assessment, and SHAP for the analysis of feature importance. The proposed random forest outperformed the other models, with an accuracy of 90.2%, a recall rate of 95.2%, a precision rate of 86.6%, and an F1 value of 90.7% in the SPSC category based on 10-fold cross-validation on a balanced dataset. Our results suggest that the four features, i.e., age, stage, gender, and involvement of regional lymph nodes, which significantly affect the output of the prediction model, need to be considered in the analysis of the next causal effect. In addition to causal analysis of specific primary sites, these clinical features allow further investigation of secondary cancers among skin cancer survivors.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Nonmelanoma Skin Cancer Studies · Cutaneous Melanoma Detection and Management · Cutaneous lymphoproliferative disorders research

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Computer Science and Information Engineering, National Quemoy University, Kinmen County 892, Taiwan

School of Medical Informatics, Chung Shan Medical University & IT Office, Chung Shan Medical University Hospital, Taichung City 40201, Taiwan

Department of Information Management, Ming Chuan University, Taoyuan City 33300, Taiwan

Department of Nursing, Chung Shan Medical University, Taichung City 40201, Taiwan

Department of Nursing, Chung Shan Medical University Hospital, Taichung City 40201, Taiwan

Department of Mathematics and Information Engineering, National Taipei University of Education, Taipei 106, Taiwan

School of Public Health, Mongolian National University of Medical Sciences, Ulaanbaatar 14210, Mongolia

Division of Environmental and Preventive Medicine, Tottori University, Tottori 680-8550, Japan

School of Public Health, Loma Linda University, Loma Linda, CA 92350, USA

Funding

Ministry of Science and Technology

References (32)

Show source-provided references
1. Risk factors for development of new skin neoplasms in patients with past history of skin cancer: A survival analysis10.1038/s41598-018-33763-7 ↗
2. Neural network diagnosis of malignant melanoma from color images10.1109/10.312091 ↗
3. Skin Cancer Classification Using Neural Networks and Fuzzy Systems
4. An ensemble classification approach for melanoma diagnosis10.1007/s12293-014-0144-8 ↗
5. Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., and Smith, J.R. (2015, January 5–9). Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images. Proceedings of the 6th International Workshop on Machine Learning in Medical Imaging, Munish, Germany.10.1007/978-3-319-24888-2_15 ↗
6. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
7. Convolutional neural networks for medical image analysis: “Full training or fine tuning?”10.1109/TMI.2016.2535302 ↗
8. A Prediction Tool to Facilitate Risk-Stratified Screening for Squamous Cell Skin Cancer10.1016/j.jid.2018.03.1528 ↗
10. C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 199310.1007/BF00993309 ↗
11. Freund, Y., and Schapire, R.E. (1996, January 3–6). Experiments with a New Boosting Algorithm. Proceedings of the International Conference on Machine Learning, Bari, Italy.
12. Bagging predictors10.1007/BF00058655 ↗
13. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗
14. Lundberg, S.M., and Lee, S. (2017). A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst., 30.
15. From local explanations to global understanding with explainable AI for trees10.1038/s42256-019-0138-9 ↗
16. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery10.1038/s41551-018-0304-0 ↗
17. Efron, B., and Tibshirani, R.J. (1993). An Introduction to the Bootstrap, Chapman and Hall.10.1007/978-1-4899-4541-9 ↗
18. Cost-sensitive decision tree ensembles for effective imbalanced classification10.1016/j.asoc.2013.08.014 ↗
19. Seiffert, C., Khoshgoftaar, T.M., Van Hulse, J., and Napolitano, A. (2008, January 15–19). A Comparative Study of Data Sampling and Cost Sensitive Learning. Proceedings of the 2008 IEEE International Conference on Data Mining Workshops, Pisa, Italy.10.1109/ICDMW.2008.119 ↗
20. Thai-Nghe, N., Gantner, Z., and Schmidt-Thieme, L. (2010, January 18–23). Cost-sensitive learning methods for imbalanced data. Proceedings of the 2010 International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain.10.1109/IJCNN.2010.5596486 ↗
21. Skin Cancer Epidemics in the Elderly as An Emerging Issue in Geriatric Oncology10.14336/AD.2017.0503 ↗
22. Outcomes and Risk Factors in Patients with Multiple Primary Melanomas10.1016/j.jid.2018.07.009 ↗
23. Non-Melanoma Skin Cancers in the Older Patient10.1007/s11912-019-0828-9 ↗
24. Alcohol intake and risk of nonmelanoma skin cancer: A systematic review and dose–response meta-analysis10.1111/bjd.15647 ↗
25. Adams, G.J., Goldstein, E.K., Goldstein, B.G., Jarman, K.L., and Goldstein, A.O. (2021). Attitudes and Behaviors That Impact Skin Cancer Risk among Men. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph18199989 ↗
26. Disease risk scores for skin cancers10.1038/s41467-020-20246-5 ↗
27. Chang, C.-C., Huang, T.-H., Shueng, P.-W., Chen, S.-H., Chen, C.-C., Lu, C.-J., and Tseng, Y.-J. (2021). Developing a Stacked Ensemble-Based Classification Scheme to Predict Second Primary Cancers in Head and Neck Cancer Survivors. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph182312499 ↗
28. Chang, C.C., Chen, C.-C., Cheewakriangkrai, C., Chen, Y.C., and Yang, S.F. (2021). Risk Prediction of Second Primary Endometrial Cancer in Obese Women: A Hospital-Based Cancer Registry Study. Int. J. Environ. Res. Public Health, 18.10.20944/preprints202107.0073.v1 ↗
29. Cigarette Smoking and the Risks of Basal Cell Carcinoma and Squamous Cell Carcinoma10.1016/j.jid.2017.03.027 ↗
30. Zavattaro, E., Fava, P., Veronese, F., Cavaliere, G., Ferrante, D., Cantaluppi, V., Ranghino, A., Biancone, L., Fierro, M.T., and Savoia, P. (2019). Identification of Risk Factors for Multiple Non-Melanoma Skin Cancers in Italian Kidney Transplant Recipients. Medicina, 55.10.3390/medicina55060279 ↗
31. Savoia, P., Veronese, F., Camillo, L., Tarantino, V., Cremona, O., and Zavattaro, E. (2022). Multiple Basal Cell Carcinomas in Immunocompetent Patients. Cancers, 14.10.3390/cancers14133211 ↗
32. Risk of Squamous Cell Carcinoma of the Skin in Relation to IgE: A Nested Case–Control Study10.1158/1055-9965.EPI-11-0668 ↗