Comparison of Naïve Bayes Algorithm and Decision Tree C4.5 for Hospital Readmission Diabetes Patients using HbA1c Measurement

Abstract

Diabetes is a metabolic disorder disease in which the pancreas does not produce enough insulin or the body cannot use insulin produced effectively. The HbA1c examination, which measures the average glucose level of patients during the last 2-3 months, has become an important step to determine the condition of diabetic patients. Knowledge of the patient's condition can help medical staff to predict the possibility of patient readmissions, namely the occurrence of a patient requiring hospitalization services back at the hospital. The ability to predict patient readmissions will ultimately help the hospital to calculate and manage the quality of patient care. This study compares the performance of the Naïve Bayes method and C4.5 Decision Tree in predicting readmissions of diabetic patients, especially patients who have undergone HbA1c examination. As part of this study we also compare the performance of the classification model from a number of scenarios involving a combination of preprocessing methods, namely Synthetic Minority Over-Sampling Technique (SMOTE) and Wrapper feature selection method, with both classification techniques. The scenario of C4.5 method combined with SMOTE and feature selection method produces the best performance in classifying readmissions of diabetic patients with an accuracy value of 82.74 %, precision value of 87.1 %, and recall value of 82.7 %.

Diabetes Diagnosis Using Machine Learning

“…Optimizing the performance of the classification model by feature selecting is an important part [6]. Feature selection, as a data preprocessing strategy, has been proven to be effective and efficient in preparing data (especially high-dimensional data) for various data mining and machine-learning problems.…”

Predicting Hospital Readmission of Diabetic Patients Using Machine Learning

“…Optimizing the performance of the classification algorithm model by feature selecting is an important part [9]. Feature selection, as a data preprocessing strategy, has been proven to be effective and efficient in preparing data (especially high-dimensional data) for various data mining and ML problems.…”

“…This cost reached about $327 billion in 2017 [7]. The ability to predict patient readmissions will ultimately help the hospital to calculate and manage the quality of patient care [9]. Studying data over time can play a role in predicting the magnitude and frequency of future events [10].…”

Comparison of Classification Data Mining C4.5 and Naïve Bayes Algorithms of EDM Dataset

“…This is evidenced by the level of accuracy ranging from 75% -100% and execution time of 0 seconds. Further research by Pujianto [12] on Diabetes Patients with HbA1c Measurement. This paper proposes two comparisons of classification methods C4.5 and Naive Bayes with HbA1c measurement in seeing the performance of the two methods.…”