An Efficient Machine Learning Pipeline for Distinguishing Cancer and Non‐Cancer Patients in Systemic Lupus Erythematosus
International Journal of Rheumatic Diseases · 2025
DOI: 10.1111/1756-185x.70455 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Rheumatic Diseases, 2025. Verfasst von You-Yue Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Evidence-Based Medicine, School of Public Health, Southwest Medical University, Luzhou, Sichuan, China. Hauptthemen laut MEDLINE: Lupus Erythematosus, Systemic, Machine Learning, Neoplasms. Die Arbeit nennt 40 Literaturangaben. Gefördert von: Natural Science Foundation of Sichuan Province, Luzhou Municipal People's Government-Southwest Medical University Science and Technology Strategic Cooperation Project Fund.
Themen: Künstliche Intelligenz in der Pflege, Onkologische Pflege
Abstract (Originalsprache)
Background
The objective is to develop a machine learning model that is capable of effectively distinguishing between cancer and non‐cancer patients among systemic lupus erythematosus (SLE).
Methods
A total of 2811 patients with SLE were included in this study, among which 208 had concurrent cancers. Age, gender, and 95 clinical and laboratory indicators were included. Initially, data preprocessing and feature transformation were conducted. After evaluating feature importance, selected features were included in the subsequent steps for establishing the machine learning model. The optimal model chosen was assessed using a series of metrics to obtain a comprehensive performance evaluation of the model.
Results
Through integrated feature selection, features such as Age, C4, WBC (urine), BASO_R, ALP, AST, and C3 were screened out for model construction. Among the various machine learning (ML) models established after parameter optimization, the logistic regression model performed the best. Furthermore, the logistic regression model still showed the best predictive capability by evaluating metrics such as receiver operating characteristic (ROC) curves, precision‐recall curve (PRC) plots, as well as model prediction accuracy, F1 score, and recall.
Conclusion
We have developed a convenient and straightforward machine learning model for SLE patients, which can easily and usefully distinguish cancer from non‐cancer patients within the SLE patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Evidence-Based Medicine, School of Public Health, Southwest Medical University, Luzhou, Sichuan, China.
- Department of Rheumatology and Immunology, the Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan, China.
- Center for Public Experimental Technology, Southwest Medical University, Luzhou, Sichuan, China.
- Laboratory Animal Center, Southwest Medical University, Luzhou, Sichuan, China.
ORCID-Profile: An-Fang Huang, Wang-Dong Xu
Förderung
- Natural Science Foundation of Sichuan Province
- Luzhou Municipal People's Government-Southwest Medical University Science and Technology Strategic Cooperation Project Fund
Zitieren
APA
Chen, Y. Y., Huang, A. F., Yang, J., Fu, L., & Xu, W. D. (2025). An Efficient Machine Learning Pipeline for Distinguishing Cancer and Non‐Cancer Patients in Systemic Lupus Erythematosus. International Journal of Rheumatic Diseases. https://doi.org/10.1111/1756-185x.70455
Vancouver
Chen YY, Huang AF, Yang J, Fu L, Xu WD. An Efficient Machine Learning Pipeline for Distinguishing Cancer and Non‐Cancer Patients in Systemic Lupus Erythematosus. International Journal of Rheumatic Diseases. 2025. doi:10.1111/1756-185x.70455
BibTeX
@article{Chen2025,
author = {Chen, You-Yue and Huang, An-Fang and Yang, Jing and Fu, Lu and Xu, Wang-Dong},
title = {An Efficient Machine Learning Pipeline for Distinguishing Cancer and Non‐Cancer Patients in Systemic Lupus Erythematosus},
journal = {International Journal of Rheumatic Diseases},
year = {2025},
doi = {10.1111/1756-185x.70455}
}
EUVIMED