A Cloud-Based Predictive Model for the Detection of Breast Cancer

A Cloud-Based Predictive Model for the Detection of Breast Cancer

Kuldeep Pathoee, Deepesh Rawat, Anupama Mishra, Varsha Arya, Marjan Kuchaki Rafsanjani, Avadhesh Kumar Gupta
Copyright: © 2022 |Pages: 12
DOI: 10.4018/IJCAC.310041
(Individual Articles)
No Current Special Offers


Invasive cancer is the biggest cause of death worldwide, especially among women. Early cancer detection is vital to health. Early identification of breast cancer improves prognosis and survival odds by allowing for timely clinical therapy. For accurate cancer prediction, machine learning requires quick analytics and feature extraction. Cloud-based machine learning is vital for illness diagnosis in rural areas with few medical facilities. In this research, random forests, logistic regression, decision trees, and SVM are employed, and the authors assess the performance of various algorithms using confusion measures and AUROC to choose the best machine learning model for breast cancer prediction. Precision, recall, accuracy, and specificity are used to calculate results. Confusion matrix is based on predicted cases. The ML model's performance is evaluated. For simulation, the authors used the Wisconsin Dataset of Breast Cancer (WDBC). Through experiments, it can be seen that the SVM model reached 98.24% accuracy with an AUC of 0.993, while the logistic regression achieved 94.54% accuracy with an AUC of 0.998.
Article Preview


Breast cancer develops when cells in the breast mutate (alter) and expand out of control, resulting in a mass of tissue commonly known as tumor. Like other cancers, it also has the ability to enter and expand into the tissue that surrounds the breast. It can also spread to other places of the body, resulting in the formation of additional tumors and known as metastasis when this happens. To minimize future progression and problems, it is essential to identify a breast tumor as early as possible and diagnose it correctly as benign or malignant. According to International Agency of Research Cancer, in 2020, approx. 19.3 million new cases of cancer were diagnosed and large number fatalities of about 10 million are expected because of cancer Ahamed, J. et al. (2022) and Alghunaim, S. et al. (2019). Now it become one of the most frequent cancers among females and has surpassed lung cancer and prostate cancer as the most invasive cancer globally. It is estimated about 2.3 million (11.7% of the total cancer cases) diagnosed as breast cancer in 2020, which means ones in every 8 cancers case is breast cancer. As per International Agency for Research on Cancer, press release December 2020, Breast cancer is expected to kill 685000 people in 2020, major of these fatalities occurs in low-resource areas and have become more common in underdeveloped and developing countries, and the rate among young women is escalating Francies, F. Z.et al. (2020). As per researches and experts, the count of people diagnosed with this disease will double by 2040. As a result, there is a need to develop or invest in novel cancer diagnosis tools and methods.

For identification of breast tumor or cancer, a variety of imaging modalities are used. As per author Ahamed, J., et al. (2022) and Alowibdi, J. S. et al. (2021) Some of the most commonly used imaging modalities for diagnosing Appati, J. K. et al. (2021) and identifying this fatal disease in its early stages are Mammography, Magnetic Resonance Imaging, Breast Thermography, Computed Tomography etc.

The author Bazazeh, D., & Shubair, R. (2016) and Bouarara, H. A. (2021) that the appearance of breast micro-calcifications on mammography is the most critical early breast cancer findings. Micro-calcification on mammography can lead to a cancer diagnosis in up to 0.3 percent of females who are tested. Previous computer-assisted detection techniques could detect micro-calcifications on mammography with a sensitivity of 80 to 100%, but they significantly increased false-positive rates.

Additional strategies are continually needed to improve efficiency and reduce the rate of incorrect predictions Gupta, B. B.et al. (2012) and Gupta, B. B. et al. (2015). Machine learning has made significant advancement in the automated analysis of medical pictures for inconsistent identification in recent years and it is being used in a wide range of healthcare applications, such as managing the medical data, case management of common chronic conditions, detecting disease in their early stage, medical assistance, leveraging patient health data in conjunction with environmental factors like exposure to pollution are few of them Caiazza, R. et al. (2021) and Carvalho, L. F. et al. (2014). ML technology can also assist healthcare interns in developing accurate medication treatments tailored to individual by processing enormous amounts of data. The same can be said for breast imaging used in the identification of breast cancer. ML-based automated image analysis saves time and effort compared to manual inspection by effectively extracting meaningful and relevant information from enormous amounts of data.

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2024)
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing