从简单的人类测量测量中预测身体脂肪百分比:一种机器学习方法
Nikolaos Theodorakis1,2,3,4, Georgios Feretzakis3, Magdalini Kreouzi5
1Department of Cardiology, Amalia Fleming General Hospital, Athens, Greece.
Studies in health technology and informatics
|April 9, 2025
概括
准确的身体脂肪百分比 (BF%) 估计至关重要. 机器学习模型显示,腹周长是比体重指数 (BMI) 更好的预测指标,提供了更简单,更有效的评估方法.
科学领域:
- 生物识别信息 生物识别信息
- 机器学习 机器学习
- 医疗信息学 医疗信息学
背景情况:
- 准确的身体脂肪百分比 (BF%) 评估对健康和健身至关重要.
- 估计BF%的黄金标准方法往往是昂贵的和侵入性的.
- 像体质指数 (BMI) 这样的现有指标可能无法完全捕捉肥胖.
研究的目的:
- 开发和比较机器学习模型来预测身体脂肪百分比 (BF%).
- 使用可访问的人类测量数据识别BF%最重要的预测因素.
- 为了评估周长测量与BMI在BF%估计中的有效性.
主要方法:
- 使用了一个包含年龄,性别,BMI和身体周长等变量的数据集.
- 采用多重回归技术和用于预测建模的神经网络.
- 应用特征重要性分析 (ElasticNet,SHAP) 以确定关键预测因素.
主要成果:
- 斜坡回归在估计BF%时表现出最高的准确性 (R2得分).
- 腹周被确定为BF%的最重要的预测指标.
- 这项研究挑战了仅仅依赖BMI来评估肥胖.
结论:
- 机器学习模型可以使用易于获得的测量方法有效估计BF%.
- 与BMI相比,腹部周长是BF%的优越预测指标.
- 将周长测量纳入实践可以提高成本效益的BF%评估.
相关概念视频
01:02Hypodermis
3.8K
The hypodermis (the subcutaneous layer or superficial fascia) is present directly below the dermis. It connects the skin to the underlying fascia (fibrous tissue) of the bones and muscles. It is not strictly a part of the skin, although the border between the hypodermis and dermis can be difficult to distinguish. The hypodermis consists of well-vascularized, loose, areolar connective tissue and adipose tissue, which functions as a mode of fat storage and provides insulation and cushioning for...
3.8K
01:24Obesity
347
The Body Mass Index (BMI) is a numerical value derived from a person's weight and height, used to categorize individuals into weight ranges. It is calculated using the formula: weight in kilograms divided by height in meters squared. Obesity is a health condition characterized by excessive accumulation of adipose tissue that poses health risks, often diagnosed with a BMI ≥ 30. This excess fat storage occurs when surplus dietary calories are converted into triglycerides and stored in...
347