Prediction of Pediatric Irritable Bowel Syndrome using Machine Learning Ensemble Approach

Abstract

Machine learning Ensembling approach has the potential to resolve Irritable Bowel Syndrome(IBS) problem. Machine learning techniques have numerous benefits that include high flexibility and power, lack of parametric assumptions, etc. The researchers do not properly understand the causes of the IBS. The researchers found that the IBS caused due to the combination of the physical and the mental health problems.Ensemble methods combine the predictions from the various machine learning algorithms which use these predictions as inputs for the second-level learning models. This research focuses on detection of Irritable Bowel Syndrome (IBS) using machine learning ensemble approach. The experimental analysis is performed using various machine learning models: Support vector machines (SVM), Neural Network, Linear Regression, Random Forest, Decision tree, AdaBoost (Adaptive Boosting), Naive Bayes, Boosted tree, Multilayerperceptrone, and Binary Discriminate analysis. The data was collected from the Website of UMASS Medical School. The collected data wasof the pediatric patients. The data was used to predict the presence of IBS in pediatric patients. In our research, we ensemble ten different models to build a new model having high accuracy to predict a pediatric patient is IBS or not. The implementation of proposed ensemble model was done in R language. The RRF model was used for feature selection task. We used R language for the implementation of the proposed ensemble model. The RRF model was used for feature selection task. Preliminary results of the experiment show that our model is 93.32% accurate in predicting whether a pediatric patient is IBS positive or not.