Researchers have developed a data-driven framework that uses routinely measured water quality indicators to predict pathogen concentrations and estimate their potential health risks, according to an Aug. 7 report. The study, published in Biocontaminant, combines machine learning with quantitative microbial risk assessment (QMRA) to create an ML-QMRA framework for monitoring drinking water sources.
The researchers collected 95 surface water samples from two drinking water sources in a major city in Eastern China between May 2024 and December 2025. They monitored three commonly used indicator bacteria—fecal coliforms, Escherichia coli, and Enterococcus faecalis—alongside six pathogens: Pseudomonas aeruginosa, Salmonella spp., Shigella spp., adenovirus, norovirus, and enterovirus.
The results revealed that while the three fecal indicator bacteria were significantly correlated with each other, their relationships with viral pathogens were generally weak or inconsistent. This finding suggests bacterial indicators alone may not always accurately reflect viral contamination.
To improve prediction capabilities, the team compared six machine learning approaches: Multiple Linear Regression, Least Squares Boosting, Decision Tree, Support Vector Machine, Random Forest, and Multilayer Perceptron models. Random Forest and Decision Tree models performed particularly well; all optimized models achieved R² values above 0.75. The Decision Tree model showed especially strong performance for Pseudomonas aeruginosa with an R² above 0.90. Independent data collected in January and February 2026 supported the ability of most models to make predictions beyond the original training period.
Predicted pathogen concentrations were linked to QMRA calculations expressed as disability-adjusted life years (DALYs). Most estimated risks remained below the World Health Organization benchmark of 10−6 DALYs per person per year; however, Salmonella spp., Shigella spp., and enterovirus showed probabilities of exceeding this benchmark under unfavorable exposure conditions.
Disinfection efficiency was identified as the dominant factor influencing estimated health risk. To enhance model transparency, SHapley Additive exPlanations (SHAP) analysis indicated turbidity was among the strongest predictors for fecal indicator bacteria—accounting for up to 62% of predictive importance—while temperature, dissolved oxygen, rainfall, and other variables contributed differently across individual pathogens.
The authors concluded that routine physicochemical measurements can provide useful predictive information about pathogen levels, but stressed that further validation is needed across different watersheds and conditions.
