International Journal of Medical and All Body Health Research  |  e-ISSN: 2582-8940  |  Double-Blind Peer Review  |  Open Access  |  CC BY-NC-SA 4.0

Current Issues
     2026:7/4

International Journal of Medical and All Body Health Research

e-ISSN: 2582-8940 | Open Access

Breast Cancer Classification and Identification of Important Risk Factors with Bagged Cart

İpek Balikçi Çiçek, Zeynep Küçükakçali

Inonu University, Faculty of Medicine, Department of Biostatistics and Medical Informatics, Malatya, Turkey

Article Information

Volume / Issue5 / 4 (October-December 2024)
Pages138-143
AccessOpen Access

Publication Timeline

  • Received25 September 2024
  • Accepted29 October 2024

Full Text (PDF)

Open Access - Free to Download

Download Full Article (PDF) JATS XML

Abstract

Objective: The objective of this study is to classify breast cancer using the Bagged Classification and Regression Trees (CART) method and identify possible risk factors that play a role in the development of the disease. By evaluating the classification performance of the model, this study aims to contribute to the development of early detection and preventive strategies.

Materials and Methods: The study used an open-access dataset that includes variables such as menopausal status, tumor grade, lymph nodes, progesterone and estrogen receptors, age, and tumor size. The dataset was divided into training (80%) and testing (20%) subsets, and a 10-fold cross-validation approach was used to improve generalization. Bagged CART was employed for classification, and model performance was evaluated using metrics like accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score.

Results: The Bagged CART model achieved high classification performance, with an accuracy of 99.6%, sensitivity of 100%, and specificity of 99.2%. Variable importance analysis revealed that recurrence-free survival time was the most critical factor in the classification process, followed by progesterone and estrogen receptors, lymph nodes, tumor size, and age. Variables such as tumor grade and hormonal treatment status had lower importance.

Conclusion: The findings indicate that Bagged CART is highly effective in breast cancer classification, with a strong emphasis on factors such as recurrence-free survival time, hormone receptor status, and tumor characteristics. The model's high accuracy and reliability suggest that it could contribute to enhancing early detection and preventive strategies, ultimately improving patient outcome.

Keywords

Breast cancerBagged CARTmachine learningclassificationrecurrence-free survival timehormone receptorsearly detectionrisk factorspredictive modeling

References

  1. Shen L, Margolies LR, Rothstein JH, Fluder E, McBride R, Sieh W. Deep learning to improve breast cancer detection on screening mammography. Scientific Reports. 2019;9(1):12495. [Google Scholar][Crossref]
  2. Houssami N, Kirkpatrick-Jones G, Noguchi N, Lee CI. Artificial Intelligence (AI) for the early detection of breast cancer: A scoping review to assess AI’s potential in breast screening practice. Expert Review of Medical Devices. 2019;16(5):351–62. [Google Scholar][Crossref]
  3. Kim H-E, Kim HH, Han B-K, Kim KH, Han K, Nam H, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: A retrospective, multireader study. The Lancet Digital Health. 2020;2(3):e138–48. [Google Scholar][Crossref]
  4. Freeman K, Geppert J, Stinton C, Todkill D, Johnson S, Clarke A, et al. Use of artificial intelligence for image analysis in breast cancer screening programmes: Systematic review of test accuracy. BMJ. 2021;374:n1872. [Google Scholar][Crossref]
  5. Salim M, Wåhlin E, Dembrower K, Azavedo E, Foukakis T, Liu Y, et al. External evaluation of 3 commercial artificial intelligence algorithms for independent assessment of screening mammograms. JAMA Oncology. 2020;6(10):1581–8. [Google Scholar][Crossref]
  6. Riveira-Martin M, Rodríguez-Ruiz A, Martí R, Chevalier M. Multi-vendor robustness analysis of a commercial artificial intelligence system for breast cancer detection. Journal of Medical Imaging. 2023;10(5):051807. [Google Scholar][Crossref]
  7. Yala A, Schuster T, Miles R, Barzilay R, Lehman C. A deep learning model to triage screening mammograms: A simulation study. Radiology. 2019;293(1):38–46. [Google Scholar][Crossref]
  8. Aboutalib SS, Mohamed AA, Berg WA, Zuley ML, Sumkin JH, Wu S. Deep learning to distinguish recalled but benign mammography images in breast cancer screening. Clinical Cancer Research. 2018;24(23):5902– [Google Scholar][Crossref]
  9. Elhakim MT, Stougaard SW, Graumann O, Nielsen M, Lång K, Gerke O, et al. Breast cancer detection accuracy of AI in an entire screening population: A retrospective, multicentre study. Cancer Imaging. 2023;23(1):127. [Google Scholar][Crossref]
  10. Hong W, Xu Q, Zhou L. Large unbalanced credit scoring using Lasso-logistic regression ensemble. PLOS One. 2015;10(2):e0117844. International Journal of Medical and All Body Health Research www.allmedicaljournal.com [Google Scholar][Crossref]
  11. Ramosaj B, Pauly M. Who wins the Miss contest for imputation methods? Our vote for Miss BooPF. [Conference paper]. 2017. [Google Scholar][Crossref]
  12. Жебко ОО, Калініна І, Hannichenko T. Intelligent classification system based on ensemble methods. System Technologies. 2023;3(146):61–75. [Google Scholar][Crossref]
  13. Amroussia M, Viedma O, Achour H, Abbes C. Predicting spatially explicit composite burn index (CBI) from different spectral indices derived from Sentinel 2A: A case of study in Tunisia. Remote Sensing. 2023;15(2):335. [Google Scholar][Crossref]
  14. Sone K, Taguchi A, Kawata A, Eguchi S, Miyamoto Y, Tanikawa M, et al. Transiently elevated D-dimer levels post-concentrated ascites reinfusion therapy cannot be used to predict deep vein thrombosis-pulmonary embolism. Journal of Obstetrics and Gynaecology Research. 2022;48(3):817–23. [Google Scholar][Crossref]
  15. Yang Z, Zhang S. Financial risk analysis of enterprises based on random forest algorithm. Applied Machine Learning. 2023. [Google Scholar][Crossref]
  16. Farrell AV, Wang G, Rush SA, Martin JA, Belant JL, Butler A, et al. Machine learning of large-scale spatial distributions of wild turkeys with high-dimensional environmental data. Ecology and Evolution. 2019;9(10):5938–49. [Google Scholar][Crossref]
  17. Zhu Y, Tao T, Yu K, Qu X, Li S, Wickert J, et al. Machine learning-aided sea ice monitoring using feature sequences extracted from spaceborne GNSS-reflectometry data. Remote Sensing. 2020;12(22):3751. [Google Scholar][Crossref]
  18. Miyazaki Y, Kawakami M, Kondo K, Tsujikawa M, Honaga K, Suzuki K, et al. Improvement of predictive accuracies of functional outcomes after subacute stroke inpatient rehabilitation by machine learning models. PLOS One. 2023;18(5):e0286269. [Google Scholar][Crossref]
  19. Jing X, Jing Z, editors. Feature extraction and classification method of electrooculogram based on variational modal decomposition. 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022); 2022: SPIE. [Google Scholar][Crossref]
  20. Yamamoto K, Nagao S, Tsu T, Matsushima T, Ishido Y, Narita M, et al. Quality of life assessment of cell-free and concentrated ascites reinfusion therapy during initial treatment for advanced ovarian cancer: A prospective cohort study. Journal of Obstetrics and Gynaecology Research. 2021;47(4):1536–43. [Google Scholar][Crossref]
  21. Zhao Y, Dong X, Li R, Ma X, Song J, Li Y, et al. Evaluation of the pathological response and prognosis following neoadjuvant chemotherapy in molecular subtypes of breast cancer. OncoTargets and Therapy. 2015;8:1511–21. [Google Scholar][Crossref]
  22. Kheradmand AA, Ranjbarnovin N, Khazaeipour Z. Postmastectomy locoregional recurrence and recurrence-free survival in breast cancer patients. World Journal of Surgical Oncology. 2010;8:1–7. [Google Scholar][Crossref]
  23. Zdravković KZ, Zdravković J, Stošić M, Stojanović I, Popović RM, Zlatković M. Prognostic significance of estrogen receptor, progesterone receptor and human epidermal growth factor receptor 2 in patients with breast cancer. Medicinski Pregled. 2017;70(1–2):5–11. [Google Scholar][Crossref]
  24. Liu X-Y, Ma D, Xu X-E, Jin X, Yu K-D, Jiang Y-Z, et al. Genomic landscape and endocrine-resistant subgroup in estrogen receptor-positive, progesterone receptor-negative, and HER2-negative breast cancer. Theranostics. 2018;8(22):6386–98. [Google Scholar][Crossref]
  25. Erić I, Petek Erić A, Kristek J, Koprivčić I, Babić M. Rak dojke u mladih žena: Patološka i imunohistokemijska obilježja. Acta Clinica Croatica. 2018;57(3):497–501. [Google Scholar][Crossref]
  26. Yang H, Wang R, Zeng F, Zhao J, Peng S, Ma Y, et al. Impact of molecular subtypes on metastatic behavior and overall survival in patients with metastatic breast cancer: A single-center study combined with a large cohort study based on the Surveillance, Epidemiology, and End Results database. Oncology Letters. 2020;20(4):1–11. [Google Scholar][Crossref]
  27. Wan J, Gao Y, Zeng K, Yin Y, Zhao M, Wei J, et al. The levels of the sex hormones are not different between type 1 and type 2 endometrial cancer. Scientific Reports. 2016;6(1):39744. [Google Scholar][Crossref]
  28. Vetter M, Stadlmann S, Bischof E, Georgescu Margarint EL, Schötzau A, Singer G, et al. Hormone receptor expression in primary and recurrent high-grade serous ovarian cancer and its implications in early maintenance treatment. International Journal of Molecular Sciences. 2022;23(22):14242. [Google Scholar][Crossref]
  29. Need EF, Selth LA, Trotta AP, Leach DA, Giorgio L, O’Loughlin MA, et al. The unique transcriptional response produced by concurrent estrogen and progesterone treatment in breast cancer cells results in upregulation of growth factor pathways and switching from a luminal A to a basal-like subtype. BMC Cancer. 2015;15:1–17. [Google Scholar][Crossref]
  30. Luo Y, Li Q, Fang J, Pan C, Zhang L, Xu X, et al. The loss of progesterone receptor predicts more aggressive biological features and worse outcomes in estrogen receptor-positive and HER2-negative inflammatory breast cancer. [Unpublished study]. 2023. Copyright and License © The Author(s). Authors retain the copyright of their published articles. This is an open access journal, and articles are distributed under the terms of the Creative Commons Attribution Non Commercial-Share A like 4.0 International (CC BY-NC-SA 4.0) License, which allows others to remix, tweak, and build upon the work non-commercially, as long as appropriate credit is given and the new creations are licensed under the identical terms. [Google Scholar][Crossref]

How to Cite

Çiçek, İ. B., & Küçükakçali, Z. (2024). Breast Cancer Classification and Identification of Important Risk Factors with Bagged Cart. International Journal of Medical and All Body Health Research, 5(4), 138-143.

Çiçek, İpek Balikçi, and Zeynep Küçükakçali. "Breast Cancer Classification and Identification of Important Risk Factors with Bagged Cart." International Journal of Medical and All Body Health Research, vol. 5, no. 4, 2024, pp. 138-143.

Çiçek, İ. B. and Küçükakçali, Z. (2024) 'Breast Cancer Classification and Identification of Important Risk Factors with Bagged Cart', International Journal of Medical and All Body Health Research, 5(4), pp. 138-143.

Çiçek İB, Küçükakçali Z. Breast Cancer Classification and Identification of Important Risk Factors with Bagged Cart. International Journal of Medical and All Body Health Research. 2024;5(4):138-143.

Similar Articles

Share

Find this Article on

Google Scholar Semantic Scholar OpenAlex ResearchGate BASE

A newly published article may take a few days to appear on these services.