How microplastics influence health risk pathways in urban water systems? integrated binary classification, machine...

Area of Science:

• Environmental Science
• Public Health
• Data Science

Background:

• Microplastic contamination in urban water systems presents significant human health risks.
• Existing frameworks for assessing these risks are limited in scope and integration.
• Understanding the complex interplay between microplastic sources, exposure, and health is crucial.

Purpose of the Study:

• To develop an integrated framework for quantifying and predicting microplastic-driven health risks in urban water systems.
• To synthesize evidence from diverse studies using advanced computational methods.
• To establish a data-driven approach for informing urban water management and mitigation strategies.

Main Methods:

• Systematic literature review of 1,742 records, with 47 studies included.
• Integration of machine learning (Random Forest), Bayesian inference, and structural equation modeling (SEM).
• Development of a synthesized dataset incorporating environmental, exposure, biological, and health outcome variables.

Main Results:

• Six distinct microplastic contamination-health regimes were identified (R² = 0.73).
• Machine learning accurately predicted health impairment (R² = 0.84) and regulatory exceedance risk (80% accuracy).
• SEM revealed land-use intensity significantly impacts health via wastewater loading and biological stress, explaining 89.9% of health variance.

Conclusions:

• An integrated predictive framework combining machine learning and Bayesian SEM effectively quantifies microplastic health risks.
• Microplastic health impacts are driven by coupled environmental pressures, exposure pathways, and biological responses.
• The findings support evidence-based urban water management and the optimization of microplastic mitigation strategies.