Review Article - Journal of RNA and Genomics (2021) Volume 0, Issue 0

Prediction of breast cancer using neural network analysis is effective.

Breast cancer is one of the most frequent cancers among females internationally. The main objectives of the present study were to predict the breast cancer using neural network analysis. A dataset posed on Kaggle was analyzed to predict breast cancer by neural network analysis. A model of the study consisting of three layers was constructed. Three layers included input layer of 5 covariates: perimeter mean, radius mean, smoothness mean, texture mean, and area mean. The second layer was the hidden layer, and the third layer was the output layer. The correct prediction percent of the model was 95%. The results of the model showed that the strongest predictors were arranged in the following order: perimeter mean, area mean, smoothness mean, texture mean, and radius mean. Taken together, breast cancer can be effectively diagnosed using neural network analysis that produced a model with 95% prediction correction.

Author(s): Inas Saleh Almazari, Kawther Faisal Amawi, Mohammad Abu Assab, Maisa MA AL-QUDAH, Ala Abu Helo, Ahed J Alkhatib

Abstract PDF