🥳 RAPIDMINER 9.9 IS OUT!!! 🥳

The updates in 9.9 power advanced use cases and offer productivity enhancements for users who prefer to code.

CLICK HERE TO DOWNLOAD

Breast Cancer Detection

DocMusherDocMusher Member Posts: 329   Unicorn
edited November 2018 in Help

Hi RM friends,

For scientists or medical professionals interested in breast cancer detection, here is the link with the project. https://github.com/Ankitadutta2/Data-Mining-for-Breast-Cancer-Detection-using-RapidMiner

The text related with the project can be found here: https://github.com/Ankitadutta2/Data-Mining-for-Breast-Cancer-Detection-using-RapidMiner/blob/master/Team5_MiningReport.pdf

Cheers

Sven

 

#cancer #health #medicine

sgenzerlionelderkrikor

Comments

  • User141505User141505 Member Posts: 4 Contributor I
    HI. interesting. i am looking for some applications in real life data in breast cancer. I took the same dataset and performed a few more tests with the following results.

    KNN
    accuracy: 92.63% +/- 3.38% (micro average: 92.62%)
    Deep Learning
    accuracy: 97.37% +/- 2.37% (micro average: 97.36%)
    Logistic regression
    accuracy: 95.43% +/- 1.48% (micro average: 95.43%)
    NaiveBayes
    accuracy: 92.97% +/- 2.98% (micro average: 92.97%)
    Decision Tree
    accuracy: 92.97% +/- 3.70% (micro average: 92.97%)
    Random Forest
    accuracy: 95.43% +/- 2.37% (micro average: 95.43%)

    In my opinion stability is important as well (in this case the more stable model seems to be Logistic regression).
    The more accurate and yet stable is deep learning (as highlighted from the ROC analisys). I attach a few screenshots.






Sign In or Register to comment.