Salmonella is a leading cause of foodborne illness in the United States and around the world, disproportionately impacting vulnerable populations. It cost the U.S. economy $4.1 billion annually, with 1.35 million infections, 26,500 hospitalizations, and 420 deaths, with unchanged rates for three decades despite national goals. Salmonella has become a “One Health” issue requiring collaborative efforts across the animal-human-environment interface, recognizing that all are interconnected. To resolve this issue, the proposed project, through collaboration with the end-to-end supply chain, food banks, and educators, will create SENS-D, a sensor-enabled decision support system. SENS-D will incorporate multiple rapid sensing technologies along with visualization, prediction, and optimization capabilities to provide data-driven solutions to mitigate foodborne pathogen risks for a safe, equitable, and resilient food system.  

Our interdisciplinary team, consisting of 19 investigators encompassing expertise in Public Health, Poultry Science, Food Science, Animal Science, Supply Chain Analytics, Engineering, Analytics, and ML/AI, is well-positioned to address this public health concern. This collaborative effort has allowed us to work toward our common goal - a timely solution for a safe, equitable food system. The research team is working alongside multisectoral partners for broader and faster adoption to address the unique needs of disadvantaged populations in food nutrition, accessibility, and equity. SENS-D develops innovative sensing technologies and prototypes of the sensing systems for rapid detection and quantification of Salmonella serovars along the poultry supply chain. This technology enables detection within 10 to 60 minutes and is coupled with a data-driven decision-support system (DSS).

This holistic approach deploys sensors across the supply chain and integrates real-time sensing results into a centralized “One Health” data environment encompassing population health, poultry/food production, and environmental data, that empowers the DSS. By combining results from samples collected throughout the food supply chain, the project ensures a comprehensive understanding of contamination dynamics. The DSS features (1) optimization models for sensor placement in the food supply chain, (2) intelligent distribution of perishable foods in cold chain operations while considering the predicted Salmonella levels and shelf-life of products, (3) workforce planning and targeted outreach to vulnerable populations at high-risk for Salmonella infections, and (4) analytical toolkit for evaluating policies and interventions to reduce and prevent the spread of Salmonella infections. SENS-D can potentially be adapted for detecting other foodborne pathogens in beef, pork, dairy, and green leaf products. Additionally, it can be used to diagnose bacterial and viral infectious diseases in clinical settings, potentially reducing the $152 billion economic burden of foodborne illness in the US. Implementing this technology ensures equitable food security for local and global consumers, reducing the economic burden of foodborne illnesses