使用身体组成大数据对儿童和青少年的身高估计:机器学习和可解释的人工智能方法
Dohyun Chun1,2, Taesung Chung3, Jongho Kang2,4
1College of Business Administration, Kangwon National University, Chuncheon, Gangwon-do, Korea.
Digital health
|March 31, 2025
概括
身体组成,包括软瘦质量和体脂质量百分比,可以准确预测儿童和青少年的身高. 这种人工智能模型为儿科生长评估提供了可解释的见解.
科学领域:
- 儿科内分泌学 儿科内分泌学
- 生物统计学 生物统计学
- 人工智能在医学中的应用
背景情况:
- 准确的身高估计对于监测儿童和青少年成长以及识别潜在的健康问题至关重要.
- 传统的方法可能无法完全捕捉影响增长的因素的复杂相互作用.
- 利用先进的AI和身体组成数据可以提高预测准确性和可解释性.
研究的目的:
- 为儿科患者群体开发一个精确和可解释的高度估计模型.
- 利用身体组成变量和可解释的AI (XAI) 技术来预测身高.
- 确定影响儿童和青少年身高的关键体质成分指标.
主要方法:
- 在一大数据集 (n=54,374) 的儿童和青少年 (6-18岁) 上训练了一种增强光度梯度的机器学习模型.
- 该模型结合了人体测量和详细的身体成分测量.
- 可解释的人工智能方法,包括SHAP和PDP,用于解释模型预测.
主要成果:
- 高度估计模型的准确性很高,男孩的平均绝对百分比误差为1.64%,女孩为1.63%.
- 软瘦质量 (SLM) 和身体脂肪质量百分比 (BFMP) 被确定为身高的重要预测因素.
- 在SLM和估计身高之间观察到正相关性,而BFMP显示出反向关系.
结论:
- 身体构成变量是儿童群体中身高的可靠预测因素.
- 开发的AI模型为高度估计提供了准确和可解释的见解.
- 这种方法对推进儿科生长评估和监测工具充满希望.
相关概念视频
Nature and Nurture
20.3K
Many human characteristics, like height, are shaped by both nature—in other words, by our genes—and by nurture, or our environment. For example, chronic stress during childhood inhibits the production of growth hormones and consequently reduces bone growth and height. Scientists estimate that 70-90% of variation in height is due to genetic differences among individuals, and 10-30% of variation in height is due to differences in the environments that individuals experience,...
20.3K
What are Estimates?
4.9K
It isn't easy to measure a parameter such as the mean height or the mean weight of a population. So, we draw samples from the population and calculate the mean height or mean weight of the individuals in the sample. This sample data acts as a representative measure of the population parameter. These sample statistics are known as estimates.
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
The estimate for the mean of a sample is denoted by ͞x, whereas the mean of the population is designated as μ. Further, parameters such...
4.9K
Polygenic Traits
64.4K
When more than one gene is responsible for a given phenotype, the trait is considered polygenic. Human height is a polygenic trait. Studies have uncovered hundreds of loci that influence height, and there are believed to be many more. Due to the high number of genes involved, as well as environmental and nutritional factors, height varies significantly within a given population. The distribution of height forms a bell-shaped curve, with relatively few individuals in the population at the...
64.4K
Variation: Normal Distribution, Range, and Standard Deviation
22.0K
In the field of psychology, there are several ways to organize measurements of a trait, feature, or characteristic (i.e., variables). Qualitative data, such as ethnicity, can be tabulated into a frequency count to provide information about the proportion, as well as the variety of groups in a sample or population. On the other hand, researchers can perform a wider set of calculations on quantitative data. The mean, mode, and median, for instance, are central tendency measures to identify a...
22.0K
Estimation of the Physical Quantities
4.0K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
4.0K
Mechanistic Models: Compartment Models in Individual and Population Analysis
19
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
19


