Using Decision Tree and Naive Bayes to Predict Kidney Stones Disease

EasyChair Preprint 8855

Abstract

High incidence of diseases related to kidney stones disease become one of the major concerns in health care systems around the world. Early Prediction of this disease decreases its appearance and its related costs, using classification which is one of the data mining techniques that can help in making the best predictions. This study aimed to develop a model for the early detection of kidney stones to provide a decision support system. The data was collected from 500 patients who visited the urology clinic in Rosary’s sister’s hospital in Irbid from 2017 through 2019, and some of them were diagnosed to have kidney stones whereas the others were diagnosed with different diseases. The gathered data was analyzed using the WEKA toolkit, which provides many data mining algorithms such as Decision Tree J48 and Na¨ıve Bayes, which were used in this paper to build a predictive model. The results show the effectiveness of the model build using the Na¨ıve Bayes algorithm for predicting a kidney stone disease. Moreover, according to the applied models, show the family history of kidney stones, is the most vital parameter in the prediction of kidney stones disease.

Keyphrases: Classification, Data Mining, Decision Tree, Na¨ıve Bayes, kidney stone.

@booklet{EasyChair:8855,
  author    = {Samer Nofal and Rana Nidal},
  title     = {Using Decision Tree and Naive Bayes to Predict Kidney Stones Disease},
  howpublished = {EasyChair Preprint 8855},
  year      = {EasyChair, 2022}}