Building of Informatics, Technology and Science
Vol 7 No 1 (2025): June (2025)

Classification of High Risk of Obesity in Women using Decision Tree Methods

Rizawanti, Riftika (Unknown)
Rajiansyah, Rajiansyah (Unknown)



Article Info

Publish Date
30 Jun 2025

Abstract

Excessive body fat accumulation characterizes obesity, a medical condition primarily caused by an energy imbalance. This excess fat is stored throughout the body, including the abdomen, thighs, and arms. Obesity is a global health concern, prevalent in Indonesia, impacting physical, psychological and social well-being. Women are more susceptible to obesity due to a combination of biological and lifestyle factors. A community health center study of 156 patients revealed that 71.20% exhibited central obesity, with women comprising 76.60% of this group and men 31.6%. This study focuses on the disproportionate impact of obesity on women. To better understand and address obesity, classification is crucial. This study uses a Decision Tree method to classify 898 women based on 14 assessments for high obesity risk, comparing its performance using three attribute selection criteria. The Decision Tree (Gini Index) model achieved 77.22% overall accuracy (Figure 12). The Normal category has 83% precision and 88.30% recall. The Overweight category had 62.50% precision and 63.83% recall. The Obese category had 75% precision and 66.67% recall. The Underweight category achieved 100% precision and recall. While the model demonstrates good classification performance, particularly for Normal and Underweight categories, it requires further refinement to better differentiate between Overweight and Obese individuals.

Copyrights © 2025






Journal Info

Abbrev

bits

Publisher

Subject

Computer Science & IT

Description

Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. ...