Related Experiment Video
Updated: May 12, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Machine Learning Models for Predicting Pediatric Hospitalizations Due to Air Pollution and Humidity: A Retrospective
Zohar Barnett-Itzhaki1,2, Vered Nir3,4, Almog Kellner2
1Ruppin Research Group in Environmental and Social Sustainability, Ruppin Academic Center, Emek Hefer, Israel.
Insights
Predictive models accurately forecast pediatric hospitalizations due to respiratory issues, linking environmental factors like air pollution and humidity to increased emergency visits. These models aid public health planning.
Area of Science:
- Environmental Health
- Pediatric Respiratory Medicine
- Data Science in Healthcare
Background:
- Pediatric respiratory health is significantly impacted by air pollution and humidity.
- Previous research links environmental factors to adverse respiratory outcomes in children.
Purpose of the Study:
- To develop predictive models for pediatric hospitalizations.
- To assess the combined influence of environmental exposures and clinical features on respiratory hospitalizations.
Main Methods:
- Retrospective analysis of 2500 children (aged 1-18) with respiratory symptoms.
- Collected air pollution data (NOx, NO2, SO2) and relative humidity (RH) linked to residential locations.
- Utilized Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) machine learning models for prediction.
Main Results:
- Hospitalizations were more common in boys and during winter months.
- Increased emergency visits correlated with highly polluted days and lower relative humidity.
- RF and XGBoost models demonstrated high accuracy (0.7-0.98), precision (0.88-0.99), and AUC (81%-99%).
- Key predictive features included temperature, NOx, RH, and SO2 exposure.
Conclusions:
- Developed models effectively predict pediatric respiratory hospitalizations.
- Findings highlight the critical role of air pollution and humidity in pediatric respiratory health.
- The models serve as valuable tools for public health planning and resource allocation.
Background:
Exposure to air pollution and meteorological conditions, such as humidity, has been linked to adverse respiratory health outcomes in children. This study aims to develop predictive models for pediatric hospitalizations based on both environmental exposures and clinical features.
Methods:
We conducted a retrospective analysis of 2500 children (aged 1-18) who presented with respiratory symptoms at the emergency department, during 2016-2017. Air pollution data, including NOx and NO2 concentrations, and relative humidity (RH) were collected from nine monitoring stations and were cross-referenced with the children's residential locations to assess their specific exposure level. Statistical tests, including Chi-square and Wilcoxon tests, were used to analyze the data. Machine learning models, specifically Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), were developed to predict the children's hospitalizations.
Results:
Boys were more likely to be hospitalized than girls (60.6% vs. 39.4%, p = 4.31e-06). Hospital visits peaked during winter (p = 3.56e-37). Increased emergency room visits were statistically significantly associated with highly polluted days (p = 0.038). Hospitalized children were exposed to lower RH (median 64.9%) compared to nonhospitalized children (median 69.4%, p = 0.005). The RF and XGBoost models were reliable, with accuracy rates of 0.7-0.98, Precision scores of 0.88-0.99, and AUC scores of 81%-99%. Key features included temperature, NOx levels, RH, and exposure to SO2.
Conclusion:
This study investigates the effects of air pollution and humidity on pediatric respiratory health. The models developed offer valuable tools for predicting hospitalizations and are intended to support public health planning and resource allocation.
More Related Videos
09:33Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India
Published on: December 23, 2022
08:17Generation of a Chronic Obstructive Pulmonary Disease Model in Mice by Repeated Ozone Exposure
Published on: August 25, 2017
Related Concept Videos
01:18Steps in Outbreak Investigation
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
01:25Statistical Methods for Analyzing Epidemiological Data
01:30Pneumonia I: Introduction
Risk Factors
Various factors influence the likelihood of developing pneumonia. Age plays a crucial role, with infants, children under two, and individuals over 65 at increased risk due to their...
01:47Lung Capacity