چهارمین همایش ملی پژوهش های کاربردی امنیت غذایی: فرآوری، ایمنی و سلامت

رفتن به صفحه اصلی

ارائه مجازی مقاله

کد مقاله 1223

عنوان Integrating Artificial Intelligence, Genomics, and Predictive Microbiology for Microbial Risk Assessment of Foods of Animal Origin

نویسندگان Kimia Asi Ebrahimi - Seyed Matin Mousavi

چکیده Foodborne pathogens in foods of animal origin can enter the food chain at different stages, from primary animal production to processing, storage, and consumption. Conventional microbiological monitoring remains essential, but the increasing amount of genomic, environmental, processing, and epidemiological data has created opportunities for more data-driven approaches. This review examines the integration of artificial intelligence (AI), genomics, and predictive microbiology for microbial risk assessment of foods of animal origin. Machine learning and deep learning can analyze complex datasets and support pathogen detection, contamination prediction, and antimicrobial resistance prediction. Whole-genome sequencing provides detailed information about pathogen identity, genomic relationships, virulence, and antimicrobial resistance. Predictive microbiology can estimate microbial growth, survival, and inactivation under different environmental and processing conditions. Integrating these approaches may provide a more comprehensive assessment of microbial hazards across the farm-to-fork continuum. However, data quality, model validation, standardization, interpretability, computational requirements, and regulatory considerations remain important challenges. Future food safety systems may benefit from combining continuous monitoring, genomic surveillance, predictive models, and AI-based analysis to support more proactive microbial risk assessment.

فایل ها

فایل jpeg-jpg پوستر

محتوای ارائه مجازی مقاله

نظرات