Scholarlink

Obesity, as a significant global health challenge and a root cause of numerous diseases, has shown an alarming rise in prevalence, particularly among adults aged 19–65. According to recent statistics, more than 650 million adults worldwide were classified as obese in 2022 (WHO). This growing concern necessitates accurate prediction and strategic prevention methods. This research focuses on employing computational machine learning algorithms to compare four models—logistic regression, decision trees, support vector machines (SVMs), random forest—to identify the primary features contributing to obesity in adults. The results of this comparative analysis highlight that weight and height have a significant impact on obesity risk. Additionally, the frequency of vegetable consumption, the number of main meals, and age are also crucial and prove to be deterministic factors.These assessed insights highlight the potentials for attuning personalized, intervention programs for people of all age group people to effectively address obesity.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating Machine Learning Models for Obesity Prediction: Analyzing the Impact of Key Lifestyle and Demographic Factors

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Anusha Dhawan,
  • Ashiya Garg,
  • Hiba Ali,
  • Ritu Rani,
  • Garima Jaiswal,
  • Arun Sharma

摘要

Obesity, as a significant global health challenge and a root cause of numerous diseases, has shown an alarming rise in prevalence, particularly among adults aged 19–65. According to recent statistics, more than 650 million adults worldwide were classified as obese in 2022 (WHO). This growing concern necessitates accurate prediction and strategic prevention methods. This research focuses on employing computational machine learning algorithms to compare four models—logistic regression, decision trees, support vector machines (SVMs), random forest—to identify the primary features contributing to obesity in adults. The results of this comparative analysis highlight that weight and height have a significant impact on obesity risk. Additionally, the frequency of vegetable consumption, the number of main meals, and age are also crucial and prove to be deterministic factors.These assessed insights highlight the potentials for attuning personalized, intervention programs for people of all age group people to effectively address obesity.