EC Gynaecology

The most prevalent kind of cancer in women is found in the breasts, and it is called breast cancer. The method of research begins with a step that is necessary: the identification of breast cancer risk factors. The key approach for attaining the basic aims of this study, which were to determine the predictors of breast cancer risk variables and the relative value of each predictor, was to make use of neural network analysis. These were the primary goals of this study. The present investigation was based on an analysis of neural networks that was carried out on data that was presented on Kaggle [1]. The breast cancer risk variables that can be utilized to predict the disease are the primary focus of this collection. The only dependent variable was the result, which was either no disease (1) or disease (2). A total of eight independent factors were included for this study. In total, there were 116 different cases contained within the dataset. While the category of disease comprised 37 cases, the category of no disease included 79 cases, which accounted for 68.1% of the total, and the category of disease contained 37 cases, which accounted for 31.9% of the total. The architectural model was built using a number of characteristics, such as the training component, which had the following values: the gross entropy error was 23.7884, and the proportion of erroneous predictions was 10.1%. One or more consecutive steps that showed no improvement in errora was used as the halting rule for the experiment. Over the entire testing session, the total gross entropy error came to 14,327, and 13.5% of the predictions that were made turned out to be incorrect. In descending order of importance, the factors that were found to have the greatest influence on the risk of developing breast cancer were: resistin (21.5%), insulin (18.2%), HOMA (17.5%), BMI (16.2%), glucose (14.7%), leptin (4.6%), adiponectin (4.1%), and age (3.30%). Age was found to have the least amount of influence on the risk of developing breast cancer. In conclusion, artificial intelligence is a valuable tool that can be used to determine the factors that will have an impact on the future.

Keywords: Artificial Intelligence; Breast Cancer; Resistin; Insulin; HOMA; BMI; Glucose; Leptin; Adiponectin

1. https://www.kaggle.com/uciml/breast-cancer-wisconsindata
2. Ponnuraja CC., et al. “Decision Tree Classification and Model Evaluation for Breast Cancer Survivability: A Data Mining Approach”. Biomedical and Pharmacology Journal 10 (2017): 281-289.
3. Ganggayah MD., et al. “Predicting factors for survival of breast cancer patients using machine learning techniques”. BMC Medical Informatics and Decision Making 48 (2019).
4. Bray F., et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians (2018).
5. Li J., et al. “Predicting breast cancer 5-year survival using machine learning: A systematic review”. PLoS ONE4 (2021): e0250370.
6. Islam T., et al. “The Malaysian breast Cancer survivorship cohort (MyBCC): a study protocol”. BMJ Open The New England Journal of Medicine 5 (2015): e008643.
7. Delen D., et al. “Predicting breast cancer survivability: a comparison of three data mining methods”. Artificial Intelligence in Medicine2 (2005): 113-127.
8. Polyak K. “Heterogeneity in breast cancer”. The Journal of Clinical Investigation10 (2011): 3786-3788.
9. Altman Douglas G. “Prognostic models: a methodological framework and review of models for breast cancer”. Cancer Investigation3 (2009): 235-243.
10. Altman DG and Royston P. “What do we mean by validating a prognostic model?” Statistics in Medicine4 (2015): 453-473.
11. Stone P and Lund S. “Predicting prognosis in patients with advanced cancer”. Annals of Oncology Official Journal of the European Society for Medical Oncology6 (2007): 971.
12. Kourou K., et al. “Machine learning applications in cancer prognosis and prediction”. Computational and Structural Biotechnology Journal 13 (2015): 8-17.
13. Bhoo-Pathy N., et al. “Trends in presentation, management and survival of patients with de novo metastatic breast cancer in a southeast Asian setting”. Scientific Reports 5 (2015): 16252.
14. Pearce CB., et al. “Machine learning can improve prediction of severity in acute pancreatitis using admission values of APACHE II score and C-reactive protein”. Pancreatology 6 (2006): 123-131.
15. Huber M and Kurz C. “Predicting patient-reported outcomes following hip and knee replacement surgery using supervised machine learning”. BMC Medical Informatics and Decision Making 1 (2019): 3.
16. Chen W., et al. “A comparative study of logistic model tree, random forest, and classi fi cation and regression tree models for spatial prediction of landslide susceptibility”. Catena 151 (2017): 147-160.
17. Genuer R., et al. “VSURF: an R package for variable selection using random forests”. RJ2 (2015): 19-33.
18. Amato F., et al. “Artificial neural networks in medical diagnosis”. Journal of Applied Biomedicine 2 (2013): 47-58.
19. Pilaftsis A and Rubio J. “The Higgs Machine Learning Challenge”. Journal of Physics: Conference Series7 (2015): 072015.
20. Erener A., et al. “A comparative study for landslide susceptibility mapping using GIS-based multi-criteria decision analysis (MCDA), logistic regression (LR) and association rule mining (ARM)”. Engineering Geology Journal 203 (2016): 45-55.
21. Sacchet MD., et al. “Support vector machine classification of major depressive disorder using diffusion-weighted neuroimaging and graph theory”. Frontiers in Psychiatry 6 (2015): 21.
22. Inas Saleh Almazari., et al. “Prediction of breast cancer using neural network analysis is effective”. Journal of RNA and Genomics (2021).
23. Wolberg H. “Wisconsin breast cancer database”. University of Wisconsin Hospitals; Madison, WI, USA (1991).
24. Alickovic E and Subasi A. “Breast cancer diagnosis using GA feature selection and rotation forest”. Neural Computing and Applications 28 (2017): 753-763.
25. Ak MF. “A comparative analysis of breast cancer detection and diagnosis using data visualization and machine learning applications”. Health Care2 (2020): 11.
26. Ivan Pocrnic., et al. “Herring and Gregor Gorjanc”. Journal: Genetics Selection Evolution1 (2022).
27. Malkov S., et al. “Mammographic texture and risk of breast cancer by tumor type and estrogen receptor status”. Breast Cancer Research 18 (2016): 122.
28. Vishali S and Anita B. “An analysis on prediction of breast cancer using radius nearest neighbor algorithm over other classification algorithms”. Materials Today: Proceedings (2021).
29. De Gonzalez AB., et al. “Estimated risk of radiation-induced breast cancer from mammographic screening for young BRCA mutation carriers”. Journal of the National Cancer Institute 101 (2009): 205-209.