INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Breast Cancer Detection and Prediction using Machine Learning
Authors Name:
Gemechu Keneni
, Raghavendra R
Unique Id:
IJSDR2105051
Published In:
Volume 6 Issue 5, May-2021
Abstract:
One the top type of cancer in women takes twenty-five percent of all cancer death around the globe is breast cancer. Proper and early treatment is the best solution for best diagnosis. Manual diagnostic needs experienced pathologists and much amount of time. Automated technique of detecting breast cancer improves accuracy and saves the specified diagnosis time. Therefore, the aim of this thesis to build up a methodology which enable detecting to maximize the number of breast cancer, identified at infant stage increase effectiveness of the treatment so that to reduce the number of death from breast cancer. Detecting breast is one of the solutions to effective treatment of breast cancer. I use different machine learning algorithm like Logistic regression, decision tree and random forest classifier to forecast if the tumor is not cancer. The proposed techniques were evaluated employing a confusion matrix, and classification performance report back to assess which features a higher classification potential. The logistic regression algorithm has achieved an average accuracy of 95%, average precision of 95.0%, average recall 95.0% and an average F1 value of 95.0% over a test data-set of previously unseen 143.The decision tree algorithm has achieved an average accuracy of 93%, average precision of 93.0%, average recall 93.0% and an average F1 value of 93.0% over a test data-set of previously unseen 143.The random forest classifier algorithm has achieved an average accuracy of 96%, average precision of 96.0%, average recall 96.0% and an average F1 value of 96.0% over a test data-set of previously unseen 143.From the analysis of the experimental results, the random forest algorithm gives better results than the other supervising machine learning classifiers. The accuracy of the model is 96 % so we can see a few wrong predictions but mostly this model is successful in predicting a tumor Malignant (M) (harmful) or Benign (B) (not harmful) based upon the features provided in the data and the training given.
Keywords:
Breast Cancer, random forest, logistic regression, decision tree, benign, malignant,
Cite Article:
"Breast Cancer Detection and Prediction using Machine Learning", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.6, Issue 5, page no.316 - 320, May-2021, Available :http://www.ijsdr.org/papers/IJSDR2105051.pdf
Downloads:
000337215
Publication Details:
Published Paper ID: IJSDR2105051
Registration ID:193341
Published In: Volume 6 Issue 5, May-2021
DOI (Digital Object Identifier):
Page No: 316 - 320
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn