A Model for Prediction of Kidney Cancer Using Data Analytic Technique

Our focus in this research work is to present an efficient algorithm for apt prediction of cancer of the kidney in which medical practitioners and patients could gain valuable knowledge for early and proactive intervention strategies to save lives from this harmful disease. To achieve these objectives, dataset pertaining to patients of cancer of the kidney were acquired from selected private and public hospitals in south west Nigeria. A two-layered classifier system consisting of Rule Induction (RI) and Decision Tree (DT) classifiers was designed to build the model based on data analytic approach. The classifier system designed was tested successfully using case study data from fifty-two (52) selected Local Governments in South West Nigeria using purposive and selective sampling technique. Ten classification algorithms were used in the modeling. Waikato Environment for Knowledge Analysis was used for the experiment and each model was built in two different ways (10-fold cross validation and percentage split mode). Performance comparison of the various algorithms considered was carried out using standard metrics of accuracy for classification and speed of model building benchmarks. The experimental results show that the J48 decision tree algorithm outperform all other algorithms in all the layers with correctly classified instances of 74.7%, F-Measure of 0.614, TP rate of 0.747, FP rate of 0.135, precision and recall of 0.687 and 0.714 respectively. It took the best algorithm, 0.03 seconds to build the model. This proves that the algorithm is suitable for the research purpose. The results from the system framework when tested with test data shows that the identified attributes, algorithm and the system model performed well and can serve as valuable tool for early detection of the disease in patients. CCS Concepts • Software and its engineering ➝Software organization and properties ➝Extra-functional properties ➝Software performance