How Data Analytics Supports Food Security

Data analytics can reduce the risk of foodborne illness, improve collaboration between food processing and service teams, and help identify food fraud. As technology advances, researchers, policy makers and food safety professionals are finding new ways to collect, use and analyze data. Here are some of the latest advancements in data analytics and food safety.

Improve risk assessment strategies

Data and monitoring have long been an integral part of food safety risk assessment. Today, researchers are combining big data, machine learning, and microbial genomics to create next-generation quantitative microbial risk assessment (QMRA).

University of Maryland researchers have received funding from the United States Department of Agriculture’s National Institute of Food and Agriculture (USDA-NIFA) to support work that combines learning automatic and computational analysis with genomic sequencing and data on the characteristics of foodborne pathogens. They intend to leverage the big data available in the agriculture and food sectors and integrate data from food production, processing, food safety risk factors and genomics data to inform – and potentially transform – public health strategies to prevent foodborne illnesses and accelerate outbreak response. .

EQRM can be used to: predict the behavior and transmission of pathogens through food production, processing and the supply chain; identify areas of the chain that may lead to contamination; and estimate the likelihood and consequences of adverse public health effects from the consumption of contaminated products.

Abani Pradhan, associate professor of nutrition and food science at the University of Maryland and principal investigator of this project, explains that this data analysis project should lead to better accuracy thanks to the inclusion of AI and genomics. “The abundance of information including available molecular and genomic data should increase the robustness of disease risk estimates by reducing sources of uncertainty and variability in the QMRA model,” Pradhan said. “This is important because there are so many different species of each foodborne pathogen, and even within the same species there are different variations or types called serovars.”

Pradhan’s team starts with Salmonella, as it has more than 2,500 serovars, all of which have widely varying characteristics. A pathogen’s resistance to heat stress or antimicrobials, its infectivity, and its rapid growth and spread are all characteristics of the pathogen that can be partially explained by genomic data.

“The idea is to link this genetic information to the characteristics of the pathogen to bridge the gap between genes and food safety aspects for consumers,” Pradhan said. “If we can use machine learning tools to understand the links between genotypes and phenotypes, based on that we can determine which serovars are of most concern so that we can focus our experimental work on those types and further strengthen our templates to create a risk assessment. which provides a more robust and comprehensive picture of risk for risk mitigation.

Use online data to detect security issues

The United States has a strong regulatory and monitoring system to identify foodborne threats. In 2019, researchers led by Adyasha Maharana of the Department of Biomedical Informatics and Medical Education at the University of Washington wanted to see if online consumer reviews might contain safety cues that could identify unsafe food products. before official inspections or recalls. They created a database linking Amazon food and grocery product reviews to FDA product recall data, and analyzed more than a million Amazon reviews containing words like “sick.” , “sick” and “fault”. The results showed that only 0.4% of Amazon reviews containing these words were for recalled products.

The researchers also found synonyms for terms related to FDA recalls in 20,000 notices, although these products are still on the market. The researchers concluded that this “may suggest that many more products should have been recalled or investigated” and note that their work could be used to help regulators determine what to investigate.

A similar project, Google’s FINDER (Food-borne Illness Detector in Real Time) machine-learning algorithm, uses search and location logs to identify restaurants that could be making people sick in real time. FINDER pulls data from people’s Google search queries for terms or symptoms that suggest they might have food poisoning. It then combines this information with Google’s location data logs to determine which restaurants these people may have visited.

They tested this approach in Las Vegas and Chicago for four months in each city. The data analytics app helped food inspectors find 25% more unsafe restaurants than the inspection method used previously.

None of these case studies suggest regulators should scrap their more established procedures. However, combining this type of data analysis with existing policies could further improve security.

Reduce food fraud

Many consumers today want to know that the food they eat is from organic farms or has been produced to certain standards. That’s why many restaurants now list the supply chain partners they use for specific menu items. This type of reporting and data sharing also provides better food traceability. Having accurate information about the origin of a food or beverage makes it easier to troubleshoot and track issues when they arise.

End-to-end traceability and real-time monitoring technologies continue to evolve, bringing new, more powerful tools that help suppliers at every link in the farm-to-table chain identify losses, thefts and potential security issues.

At the University of Adelaide, researchers have improved current methods of detecting wine fraud by combining fluorescence spectroscopy and machine learning to determine the molecular fingerprint of a drink. The team looked at Cabernet Sauvignon from three different wine regions. They found that their method could correctly authenticate the geographic origins of wine with 100% accuracy.

It is impossible to eliminate all food and beverage safety risks from the supply chain. However, successful applications of data analytics that help keep people safe are definitely steps in the right direction. As more companies in the food and beverage industry embrace new data analytics tools, other exciting opportunities will emerge. Even as things stand, the apps are full of promise.

Comments are closed.