Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Egg and Poultry Production Safety Research Unit » Research » Publications at this Location » Publication #415949
Research Project: Reduction of Foodborne Pathogens and Antimicrobial Resistance in Poultry Production Environments

Location: Egg and Poultry Production Safety Research Unit

Title: Exploring Pathogen Presence Prediction in Pastured Poultry Farms through Transformer-Based Models and Attention Mechanism Explainability

Author
item RAM DAS, ATHISH - Mississippi State University
item PILLAI, NISHA - Mississippi State University
item NANDURI, BINDU - Mississippi State University
item Rothrock, Michael
item RAMKUMAR, MAHALINGAM - Mississippi State University

Submitted to: Microorganisms
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/22/2024
Publication Date: 6/23/2024
Citation: Ram Das, A., Pillai, N., Nanduri, B., Rothrock Jr, M.J., Ramkumar, M. 2024. Exploring Pathogen Presence Prediction in Pastured Poultry Farms through Transformer-Based Models and Attention Mechanism Explainability. Microorganisms. https://doi.org/10.3390/microorganisms12071274.
DOI: https://doi.org/10.3390/microorganisms12071274

Interpretive Summary: In this study, we explore how transformer models, known for their attention mechanisms, can improve pathogen prediction in pastured poultry farming. By combining farm management practices with microbiome data, our model outperforms traditional prediction methods in terms of f1 score – an evaluation metric of model performance, fulfilling an essential need in predictive microbiology. Additionally, the emphasis is on making our model’s predictions explainable. We introduce a novel approach for identifying feature importance using the model’s attention matrix and the PageRank algorithm, offering insights that enhance our comprehension like established techniques such as DeepLIFT. Our results showcase the efficacy of transformer models in pathogen prediction for food safety and mark a noteworthy contribution to the progress of explainable AI within the biomedical sciences. This study sheds light on the impact of effective farm management practices and highlights the importance of technological advancements in ensuring food safety

Technical Abstract: In this study, we explore how transformer models, known for their attention mechanisms, can improve pathogen prediction in pastured poultry farming. By combining farm management practices with microbiome data, our model outperforms traditional prediction methods in terms of f1 score – an evaluation metric of model performance, fulfilling an essential need in predictive microbiology. Additionally, the emphasis is on making our model’s predictions explainable. We introduce a novel approach for identifying feature importance using the model’s attention matrix and the PageRank algorithm, offering insights that enhance our comprehension like established techniques such as DeepLIFT. Our results showcase the efficacy of transformer models in pathogen prediction for food safety and mark a noteworthy contribution to the progress of explainable AI within the biomedical sciences. This study sheds light on the impact of effective farm management practices and highlights the importance of technological advancements in ensuring food safety