Comparison of Mutual Information and Recursive Feature Elimination in Hypertension Prediction Using K-Nearest Neighbor (Case Study: Puskesmas Mlati II)

Susilo, Joko (2025) Comparison of Mutual Information and Recursive Feature Elimination in Hypertension Prediction Using K-Nearest Neighbor (Case Study: Puskesmas Mlati II). Tugas Akhir thesis, University of Technology Yogyakarta.

Text Abstrak_5211911014_Joko Susilo.pdf Download (207kB)

Abstract

ABSTRACT Hypertension is a significant global health issue and a leading cause of various severe complications. This study aims to develop a hypertension prediction model using the K-Nearest Neighbor (K-NN) algorithm and compare the effectiveness of two feature selection methods —Mutual Information (MI) and Recursive Feature Elimination (RFE) — in improving the model's performance. The research methodology comprises several stages: problem identification, collection of clinical hypertension patient data from Puskesmas Mlati II, data analysis, development of the K-NN model using both feature selection methods, model implementation, and system evaluation. The results show that the hypertension diagnosis prediction model using the K-NN algorithm provides strong outcomes. The feature selection method of Mutual Information, with selected features including TG, HDL, LDL, and Creat, yielded the best performance with an accuracy of 92.59%. On the other hand, the Recursive Feature Elimination method, with selected features such as Age, cholesterol, HDL, Urea, and Creatinine, achieved an accuracy of 87.03%. Both methods were found to effectively reduce data dimensionality without significantly compromising accuracy, and the developed model exhibited high precision, recall, and F1-score values. The developed system was successfully implemented, enabling users to make predictions for hypertension and view their prediction history. Keywords: Hypertension, K-Nearest Neighbor, Feature Selection, Mutual Information, Recursive Feature Elimination.

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Sains Dan Teknologi > Informatika Medis
Depositing User:	Informatika Medis
Date Deposited:	08 Aug 2025 07:35
Last Modified:	08 Aug 2025 07:35
URI:	http://eprints.uty.ac.id/id/eprint/18463

Actions (login required)

View Item