Early stage breast cancer detection using ensemble approach of random forest classifier algorithm

Abstract

Author(s): Dumpala Shanthi

Breast Cancer is one of the most deadly diseases in the world and is commonly seen in women. Based on the severity, breast cancer is classified into two types. One is Benign type of breast cancer, which can be detected at early stages and can be cured with the help of medication. Other is Malignant type of breast cancer, which shows severe affect and might lead to death. To detect breast cancer at early stages, wide variety of algorithm techniques are used such as Navie Bayes, Convolution Neural Network, KNN, adaptive voting ensemble machine learning algorithm and so on. Most latest algorithm that is under practice is adaptive voting ensemble machine learning algorithm. In this algorithm, Wisconsin Breast Cancer dataset and CNN algorithm is used to classify images and for object detection. But the major drawback of ensemble machine learning algorithm is lack of accuracy. It is proved that Neutral Network works more effective on humans mostly in analysing data and to perform pre-diagnosis without medical knowledge. In this paper, we propose Random Forest Classifier algorithm to achieve more accuracy.

Share this article

44-7723-59-8358

Editors List

  • Yousef Alomi

    Yousef Alomi
    The Past Head, General Administration of Pharmaceutical Care at Ministry of Health,
    Saudi Arabia Critical Care/TPN
    Clinical Pharmacist Ministry of Health,
    Riyadh, Saudi Arabia.

  • Osamu Tanaka

    Osamu Tanaka
    Assistant Professor,
    Department of Radiation Oncology
    Asahi University Hospital
    Gifu city, Gifu, Japan

  • Maher Abdel Fattah Al-Shayeb

    Department of Surgical Sciences, Ajman University, UAE

  • Andrzej Zdziennicki

    Institute of Gynecology and Obstetrics, Medical University of Lodz, I Clinic of Gynecology and Gynecological Oncology (Lodz, Poland)

  • Krzysztof Urbanski

    Head of the Oncology Gynecology Clinic, Oncology Center - Instytut im. Maria Sklodowska Curie, Department in Krakow (Krakow, Poland)