Evaluating the Spatial Risk of Bacterial Foodborne Diseases Using Vulnerability Assessment and Geographically Weighted Logistic Regression

Machine learning surveillance of foodborne infectious diseases using wastewater microbiome, crowdsourced, and environmental data

Clostridium perfringens (CP) is a common cause of foodborne infection, leading to significant human health risks and a high economic burden. Thus, effective CP disease surveillance is essential for preventive and therapeutic interventions; however, conventional practices often entail complex, resource-intensive, and costly procedures. This study introduced a data-driven machine learning (ML) modeling framework for CP-related disease surveillance. It leveraged an integrated dataset of municipal wastewater microbiome (e.g., CP abundance), crowdsourced (CP-related web search keywords), and environmental data. Various optimization strategies, including data integration, data normalization, model selection, and hyperparameter tuning, were implemented to improve the ML modeling performance, leading to enhanced predictions of CP cases over time. Explainable artificial intelligence methods identified CP abundance as the most reliable predictor of CP disease cases. Multi-omics subsequently revealed the presence of CP and its genotypes/toxinotypes in wastewater, validating the utility of microbiome-data-enabled ML surveillance for foodborne diseases. This ML-based framework thus exhibits significant potential for complementing and reinforcing existing disease surveillance systems.

A metagenome-derived artificial intelligence modeling framework advances the predictive diagnosis and interpretation of petroleum-polluted groundwater

Groundwater (GW) quality monitoring is vital for sustainable water resource management. The present study introduced a metagenome-derived machine learning (ML) model aimed at enhancing the predictive understanding and diagnostic interpretation of GW pollution associated with petroleum. In this framework, taxonomic and metabolic profiles derived from GW metagenomes were combined for use as the input dataset. By employing strategies that optimized data integration, model selection, and parameter tuning, we achieved a significant increase in diagnostic accuracy for petroleum-polluted GW. Explanatory artificial intelligence techniques identified petroleum degradation pathways and Rhodocyclaceae as strong predictors of a pollution diagnosis. Metagenomic analysis corroborated the presence of gene operons encoding aminobenzoate and xylene biodegradation within the de novo assembled genome of Rhodocyclaceae. Our genome-centric metagenomic analysis thus clarified the ecological interactions associated with microbiomes in breaking down petroleum contaminants, validating the ML-based diagnostic results. This metagenome-derived ML framework not only enhances the predictive diagnosis of petroleum pollution but also offers interpretable insights into the interaction between microbiomes and petroleum. The proposed ML framework demonstrates great promise for use as a science-based strategy for the on-site monitoring and remediation of GW pollution.

Machine learning approach as an early warning system to prevent foodborne Salmonella outbreaks in northwestern Italy

Salmonellosis, one of the most common foodborne infections in Europe, is monitored by food safety surveillance programmes, resulting in the generation of extensive databases. By leveraging tree-based machine learning (ML) algorithms, we exploited data from food safety audits to predict spatiotemporal patterns of salmonellosis in northwestern Italy. Data on human cases confirmed in 2015-2018 (n = 1969) and food surveillance data collected in 2014-2018 were used to develop ML algorithms. We integrated the monthly municipal human incidence with 27 potential predictors, including the observed prevalence of Salmonella in food. We applied the tree regression, random forest and gradient boosting algorithms considering different scenarios and evaluated their predictivity in terms of the mean absolute percentage error (MAPE) and R2. Using a similar dataset from the year 2019, spatiotemporal predictions and their relative sensitivities and specificities were obtained. Random forest and gradient boosting (R2 = 0.55, MAPE = 7.5%) outperformed the tree regression algorithm (R2 = 0.42, MAPE = 8.8%). Salmonella prevalence in food; spatial features; and monitoring efforts in ready-to-eat milk, fruits and vegetables, and pig meat products contributed the most to the models' predictivity, reducing the variance by 90.5%. Conversely, the number of positive samples obtained for specific food matrices minimally influenced the predictions (2.9%). Spatiotemporal predictions for 2019 showed sensitivity and specificity levels of 46.5% (due to the lack of some infection hotspots) and 78.5%, respectively. This study demonstrates the added value of integrating data from human and veterinary health services to develop predictive models of human salmonellosis occurrence, providing early warnings useful for mitigating foodborne disease impacts on public health.

Comprehensive Dynamic Influence of Multiple Meteorological Factors on the Detection Rate of Bacterial Foodborne Diseases under Spatio-Temporal Heterogeneity

Foodborne diseases are a critical public health problem worldwide and significantly impact human health, economic losses, and social dynamics. Understanding the dynamic relationship between the detection rate of bacterial foodborne diseases and a variety of meteorological factors is crucial for predicting outbreaks of bacterial foodborne diseases. This study analyzed the spatio-temporal patterns of vibriosis in Zhejiang Province from 2014 to 2018 at regional and weekly scales, investigating the dynamic effects of various meteorological factors. Vibriosis had a significant temporal and spatial pattern of aggregation, and a high incidence period occurred in the summer seasons from June to August. The detection rate of Vibrio parahaemolyticus in foodborne diseases was relatively high in the eastern coastal areas and northwestern Zhejiang Plain. Meteorological factors had lagging effects on the detection rate of V. parahaemolyticus (3 weeks for temperature, 8 weeks for relative humidity, 8 weeks for precipitation, and 2 weeks for sunlight hours), and the lag period varied in different spatial agglomeration regions. Therefore, disease control departments should launch vibriosis prevention and response programs that are two to eight weeks in advance of the current climate characteristics at different spatio-temporal clustering regions.