Related Experiment Video
Updated: Jul 9, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Research on children's health prediction based on Improved Grey Wolf Optimization algorithm-Random Forest model
1Department of Public Teaching, Hefei Preschool Education College, Hefei, China.
Medicine
|February 3, 2026
Summary
A new hybrid model (IGWO-RF) improves pediatric health prediction accuracy to 92.1% by optimizing Random Forest hyperparameters. Key health determinants include BMI, exercise, and PM2.5 exposure, offering potential for early risk stratification.
Area of Science:
- Pediatric Health
- Computational Health
- Artificial Intelligence in Medicine
Background:
- Childhood health is vital for public health assessment, yet faces challenges from lifestyle changes and environmental factors, leading to increased obesity, allergies, and respiratory issues.
- Traditional health assessments suffer from data lag and subjectivity, necessitating advanced predictive models.
- The complexity of pediatric health necessitates innovative approaches for accurate and timely risk assessment.
Purpose of the Study:
- To introduce a novel hybrid model, Improved Grey Wolf Optimization-Random Forest (IGWO-RF), for enhanced pediatric health prediction.
- To improve the accuracy and interpretability of health prediction models using children's physical examination data.
- To identify key determinants of children's health through advanced explainable AI techniques.
Main Methods:
- A Random Forest (RF) model was developed using children's physical examination data.
- The Grey Wolf Optimization (GWO) algorithm was enhanced with dynamic weight strategies and elite retention mechanisms (IGWO) to optimize RF hyperparameters.
- Shapley Additive Explanations (SHAP) values were employed for model interpretability and identification of significant health factors.
Main Results:
- The IGWO-RF model achieved a prediction accuracy of 92.1% and a F1-score of 90.8%, outperforming traditional RF (85.3%) and PSO-RF (88.7%).
- SHAP analysis identified body mass index (0.32), daily exercise time (0.21), and particulate matter 2.5 exposure (0.18) as the primary determinants of children's health.
- The model demonstrated superior performance in pediatric health risk stratification.
Conclusions:
- The IGWO-RF model offers a significant advancement in pediatric health prediction accuracy and interpretability.
- Key factors influencing children's health, such as BMI, exercise, and environmental exposures, were quantitatively identified.
- The proposed methodological framework shows promise for developing early warning systems for pediatric health risks and other chronic diseases.
Related Concept Videos
02:04Conservation of Small Populations
Small population sizes put a species at extreme risk of extinction due to a lack of variation, and a consequent decrease in adaptability. This weakens the chances of survival under pressures such as climate change, competition from other species, or new diseases. Large populations are more likely to survive pressures such as these, as such populations are more likely to harbor individuals that have genetic variants that are adaptive under new stresses. Small populations are much less likely to...
01:17Wald-Wolfowitz Runs Test I
The Wald-Wolfowitz test, also known as the runs test, is a nonparametric statistical test used to assess the randomness of a sequence of two different types of elements (e.g., positive/negative values, successes/failures). It examines whether the order of the elements in a sequence is random or if there is a pattern or trend present. This nonparametric test applies to any ordered data despite the population and sample data distribution, even if a higher sample size is available.
The test works...
The test works...
01:17Wald-Wolfowitz Runs Test II
The Wald-Wolfowitz runs test, commonly referred to as the runs test, is a nonparametric test used to assess the randomness of ordered data. The test evaluates the number of runs, which are consecutive sequences of similar elements within the data. If the number of runs is significantly higher or lower than expected, the data is considered non-random, indicating a detectable pattern or structure.
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and 0s. In...
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and 0s. In...