Gastroesophageal reflux disease (GERD) is a clinical condition that occurs when the gastric content within the stomach rises into the esophagus. If left untreated, GERD can result in complications such as esophageal inflammation, ulcers, and even cancer. In this study, the early detection of GERD is performed using the GERD dataset obtained from the Harvard Dataverse online repository and processed with the XGBoost machine learning model. The SMOTE technique was implemented as a solution to address the data imbalance present in the dataset. In addition, this study applied Principal Component Analysis (PCA) and Pearson Correlation to select the most relevant attributes, with the aim of improving computational efficiency. The results demonstrated that feature selection through Pearson correlation and feature extraction using principal component analysis (PCA) yielded the optimal model performance when utilizing 16 attributes and 16 principal components, respectively. The XGBoost model with PCA achieves a macro average F1-score of 0.9615, while the XGBoost model with Pearson Correlation attains a value of 0.9809. Subsequently, the XGBoost model based on the original dataset yielded a macro F1-score value of 0.9568. The findings of this research indicate that the XGBoost model with the Pearson Correlation-based feature selection method has a better f1-score value than the feature extraction method with PCA or based on the original dataset with a difference in value of 0.0194 and 0.0241 respectively in enhancing the performance of the XGBoost model for early detection of GERD in this study.
Keywords : GERD Detection, Machine Learning, PCA, Pearson Correlation, SMOTE, XGBoost.