Analysis of breast cancer classification using machine learning techniques and hyper parameter tuning

被引:3
作者
Talukder, Pratik [1 ]
Ray, Rajarshi [1 ]
机构
[1] Univ Engn & Management, Kolkata, India
关键词
Breast cancer; BRCA gene; Machine learning; Detection; Mutation; Hyper parameters; FAMILY-HISTORY; RISK-FACTORS; FEATURES; DISEASE;
D O I
10.1016/j.bcab.2024.103195
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Breast cancer remains an important public health issue, emphasizing the need for accurate and timely diagnostic methods. It is mainly characterised by BRCA gene mutations due to genetic alterations specifically BRCA1 and BRCA2 genes which maintains healthy state responsible for DNA repair in the cells. When these genes undergo mutation, they lose the ability in cellular repair mechanisms thus leading to cancer development in the target cells which is observed biologically by differential gene expression analysis or by studying the cellular morphology differences between normal and cancerous cells. In this research project, we propose a machine learning classification (ML) method to detect breast cancer based on nuclear measurements from biopsy samples due to its predictive capability to detect patterns from a given dataset and categorise types of data based on their distribution. Based on a comprehensive set of ten nuclear features, we aim to distinguish malignant mass from benign mass, providing a reliable tool for early detection and improving patient outcomes between malignant and benign tumor stages. Early detection of malignancies leads to timely intervention, potentially reducing disease progression and improving patient survival rates. In addition, the non-invasive nature of biopsy sampling coupled with the efficiency of our ML model allows for simple and accessible breast cancer screening in a variety of clinical settings. In summary, our study demonstrates the capability of ML techniques to revolutionize breast cancer detection. The potency of nuclear measurements into our classification model provides a powerful and reliable tool for early diagnosis, improving patient outcomes and enhancing breast cancer screening methods. Ultimately, we envision this technology contributing to a proactive, data-driven approach to the diagnose against breast cancer, providing contribution to be proactive for a future with detection, treatment and care.
引用
收藏
页数:8
相关论文
共 34 条
[1]   Is iodine a gatekeeper of the integrity of the mammary gland? [J].
Aceves, C ;
Anguiano, B ;
Delgado, G .
JOURNAL OF MAMMARY GLAND BIOLOGY AND NEOPLASIA, 2005, 10 (02) :189-196
[2]  
[Anonymous], Breast Cancer Wisconsin (Original) Data Set
[3]   Risk Factors of Breast Cancer: A Systematic Review and Meta-Analysis [J].
Anothaisintawee, Thunyarat ;
Wiratkapun, Cholatip ;
Lerdsitthichai, Panuwat ;
Kasamesup, Vijj ;
Wongwaisayawan, Sansanee ;
Srinakarin, Jiraporn ;
Hirunpat, Siriporn ;
Woodtichartpreecha, Piyanoot ;
Boonlikit, Sarawan ;
Teerawattananon, Yot ;
Thakkinstian, Ammarin .
ASIA-PACIFIC JOURNAL OF PUBLIC HEALTH, 2013, 25 (05) :368-387
[4]   Variation of breast cancer risk among BRCA1/2 carriers [J].
Begg, Colin B. ;
Haile, Robert W. ;
Borg, Ake ;
Malone, Kathleen E. ;
Concannon, Patrick ;
Thomas, Duncan C. ;
Langholz, Bryan ;
Bernstein, Leslie ;
Olsen, Jorgen H. ;
Lynch, Charles F. ;
Anton-Culver, Hoda ;
Capanu, Marinela ;
Liang, Xiaolin ;
Hummer, Amanda J. ;
Sima, Cami ;
Bernstein, Jonine L. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2008, 299 (02) :194-201
[5]   Sedentary Time and Its Association With Risk for Disease Incidence, Mortality, and Hospitalization in Adults A Systematic Review and Meta-analysis [J].
Biswas, Aviroop ;
Oh, Paul I. ;
Faulkner, Guy E. ;
Bajaj, Ravi R. ;
Silver, Michael A. ;
Mitchell, Marc S. ;
Alter, David A. .
ANNALS OF INTERNAL MEDICINE, 2015, 162 (02) :123-+
[6]   Dietary fat reduction and breast cancer outcome: results from the Women's Intervention Nutrition Study (WINS) [J].
Blackburn, George L. ;
Wang, Katherine A. .
AMERICAN JOURNAL OF CLINICAL NUTRITION, 2007, 86 (03) :878S-881S
[7]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[8]   Catechol estrogen quinones as initiators of breast and other human cancers: Implications for biomarkers of susceptibility and cancer prevention [J].
Cavalieri, Ercole ;
Chakravarti, Dhubajyoti ;
Guttenplan, Joseph ;
Hart, Elizabeth ;
Ingle, James ;
Jankowiak, Ryszard ;
Muti, Paola ;
Rogan, Eleanor ;
Russo, Jose ;
Santen, Richard ;
Sutter, Thomas .
BIOCHIMICA ET BIOPHYSICA ACTA-REVIEWS ON CANCER, 2006, 1766 (01) :63-78
[9]   NEAREST NEIGHBOR PATTERN CLASSIFICATION [J].
COVER, TM ;
HART, PE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1967, 13 (01) :21-+
[10]  
Cristianini N., 2000, An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods