A framework for prioritization of foodborne pathogen illness clusters for successful public health intervention using machine learning-based analysis

A framework for prioritization of foodborne pathogen illness clusters for successful public health intervention using machine learning-based analysis of integrated surveillance and outbreak population genomics datasets

Funding period: 2019-2023
Lead: John Nash
Total GRDI funding: $718,000

The large-scale implementation of whole genome sequencing the surveillance of foodborne pathogens has led to the increased detection of case clusters that exceeds existing capacity for epidemiological investigation. It is in this context that this project will seek to develop novel analytical tools for the analysis of sequencing data to facilitate cluster prioritization based on parameters demonstrated to lead to successful public health interventions (e.g. the attribution of outbreak clusters to likely food vehicles to inform short and long-term foodborne illness prevention and control strategies), including the identification of biomarkers predictive of overall human health risk and of strain source.