IJSDIP | International Journal of System Design & Info Processing

Multiclass Classification of Breast Cancer using Machine learning techniques

Paper ID:

IJSDIP_2019_VOLUME 7_ISSUE 3_31-36

Author's Name:

Deeba Khan, Seema Shedole

Volume:

Issue:

Issue 3

Year:

2019

Pages:

31-36

Abstract

Highly available genomic data has led to enriched analysis of various genetic disorders including breast cancer. This has significantly improved the treatment strategies leading to reduced mortality rates. Literature has identified seven breast cancer subtypes based on molecular profiles; this molecular data can be leveraged to build models to classify tumour subtypes of the patients. Identifying the right subtype of breast cancer results in better prognosis and therapeutics. Machine learning techniques like Logistic Regression (LR) and Support Vector Machines (SVM) were used to build multiclass classification models. One vs One and One vs Rest scheme were adopted with these techniques to support multiple classes. This study demonstrates and compares the models for classifying breast cancer subtypes using ma-chine learning. It was observed that LR was better choice for multiclass classifications

Keywords

Support Vector Machine, Logistic Regression, Multiclass Classification, Breast cancer subtypes, Gene expression.

References

[1] H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries.,” CA. Cancer J. Clin., vol. 71, no. 3, pp. 209–249, May 2019, doi: 10.3322/caac.21660. [2] L. He, Y. Lv, Y. Song, and B. Zhang, “The prognosis comparison of different molecular subtypes of breast tumors after radiotherapy and the intrinsic reasons for their distinct radiosensitivity.,” Cancer Manag. Res., vol. 11, pp. 5765–5775, 2019, doi: 10.2147/CMAR.S213663. [3] M. Kittaneh, A. J. Montero, and S. Glück, “Molecular profiling for breast cancer: a comprehensive review.,” Biomark. Cancer, vol. 5, pp. 61–70, Oct. 2013, doi: 10.4137/BIC.S9455. [4] M. Tao et al., “Classifying Breast Cancer Subtypes Using Multiple Kernel Learning Based on Omics Data,” Genes (Basel)., vol. 10, no. 3, p. 200, Mar. 2019, doi: 10.3390/genes10030200. [5] “TCGA.” https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga. [6] B. J. Caan et al., “Intrinsic subtypes from the PAM50 gene expression assay in a population-based breast cancer survivor cohort: prognostication of short- and long-term outcomes.,” Cancer Epidemiol. biomarkers Prev. a Publ. Am. Assoc. Cancer Res. cosponsored by Am. Soc. Prev. Oncol., vol. 23, no. 5, pp. 725–734, May 2014, doi: 10.1158/1055-9965.EPI-13-1017. [7] “Comprehensive molecular portraits of human breast tumours.,” Nature, vol. 490, no. 7418, pp. 61–70, Oct. 2012, doi: 10.1038/nature11412. [8] M. Aitkin and R. J. Foxall, “Statistical modelling of artificial neural networks using the multi-layer perceptron,” Stat. Comput., vol. 13, pp. 227–239, 2003. [9] A. Athar et al., “ArrayExpress update - from bulk to single-cell expression data.,” Nucleic Acids Res., vol. 47, no. D1, pp. D711–D715, Jan. 2019, doi: 10.1093/nar/gky964. [10] T. Kopinski, S. Magand, U. Handmann, and A. R. T. Gepperth, “A pragmatic approach to multi-class classification,” 2015 Int. Jt. Conf. Neural Networks, pp. 1–8, 2015. [11] L. Yin, J.-J. Duan, X.-W. Bian, and S. Yu, “Triple-negative breast cancer molecular subtyping and treatment progress,” Breast Cancer Res., vol. 22, no. 1, p. 61, 2019, doi: 10.1186/s13058-020-01296-5. [12] L. Chen, C. Chu, J. Lu, X. Kong, T. Huang, and Y.-D. Cai, “Gene Ontology and KEGG Pathway Enrichment Analysis of a Drug Target-Based Classification System,” PLoS One, vol. 10, no. 5, pp. 1–12, 2015, doi: 10.1371/journal.pone.0126492.

DOI: https://doi.org/10.64971/j.cph.ijsdip.v7.i3.1.2019