Breast cancer is most common type of cancer for women's all over the world. When a tumor is detected, first step is to identify the type of tumor among malignant and benign. Using machine learning techniques applied to the data, type of tumor is predicted. Data is taken from Breast Cancer Wisconsin Centre. It has 569 women diagnosed with cancer and 31 variables associated with ten attributes of cell nucleus. Target variable is type diagnosed (malignant or benign). After preprocessing data several machine learning classifiers are build with different training data samples. Performance with respect to size of training data and model is then observed.
Input variables : Tumor features like radius mean, texture mean, perimeter mean, area mean, smoothness mean, compactness mean, concavity mean, concave points mean, symmetry mean
Output Variables : Type of tumor(M=malignant, B=benign)
Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : github.com
Model Category | : | Public |
Date Published | : | August, 2017 |
Healthcare Domain | : | Provider |
Code | : | github.com |
Health Risk Management |
Disease Detection |