Tag Archives: big data

Chocolate

Chocolate and Big Data: The Recipe for Food Safety Is Changing

By Steven Sklare
No Comments
Chocolate

Almost everybody loves chocolate, an ancient, basic, almost universal and primal source of pleasure. “The story of chocolate beings with cocoa trees that grew wild in the tropical rainforests of the Amazon basin and other areas in Central and South America for thousands of years… Christopher Columbus is said to have brought the first cocoa beans back to Europe from his fourth visit to the New World” between 1502 and 1504.1

Unfortunately, the production of chocolate and chocolate products today is as complex as any other global food product with supply chains that reach from one end of the world to the other. The complexity of the supply chain and production, along with the universal demand for the finished product, exposes chocolate to increasing pressure from numerous hazards, both unintentional and intentional. For example, we know that more than 70% of cocoa production takes place in West African countries, particularly the Ivory Coast and Ghana. These regions are politically unstable, and production is frequently disrupted by fighting. While production has started to expand into more stable regions, it has not yet become diversified enough to normalize the supply. About 17% of production takes place in the Americas (primarily South America) and 9% from Asia and Oceania.2

In today’s world of global commerce these pressures are not unique to chocolate. Food quality and safety experts should be armed with tools and innovations that can help them examine specific hazards and fraud pertaining to chocolate and chocolate products. In fact, the global nature of the chocolate market, requires fast reflexes that protect brand integrity and dynamic quality processes supported by informed decisions. Digital tools have become a necessity when a fast interpretation of dynamic data is needed. If a food organization is going to effectively protect the public’s health, protect their brand and comply with various governmental regulations and non-governmental standards such as GFSI, horizon scanning, along with the use of food safety intelligent digital tools, needs to be incorporated into food company’s core FSQA program.

This article pulls information from a recent industry report about chocolate products that presents an examination of the specific hazards and fraud pertaining to chocolate and chocolate products along with ways to utilize this information.

Cocoa and chocolate products rely on high quality ingredients and raw materials, strict supplier partnership schemes and conformity to clearly defined quality and safety standards. During the past 10 years there have been a significant number of food safety incidents associated with chocolate products. The presence of Salmonella enterica, Listeria monocytogenes, allergens and foreign materials in cocoa/chocolate products have been reported on a global scale. Today, information on food safety incidents and potential risks is quickly and widely available by way of the internet. However, because the pertinent data is frequently siloed, food safety professionals are unable to take full advantage of it.

Top Emerging Hazards: Chocolate Products (2013-2018)

Publicly available data, from sources such as European Union RASFF, Australian Competition and Consumer Commission, UK Food Standards Agency, FDA, Food Standards Australia New Zealand (FSANZ), shows a significant increase in identified food safety incidents for cocoa/chocolate products from 2013 to 2018. For this same time period, the top emerging hazards that were identified for chocolate products were the following:

  • Allergens: 51.60%
  • Biological: 16.49%
  • Foreign bodies: 13.83%
  • Chemical: 7.45%
  • Fraud: 6.38%
  • Food additives & flavorings: 4.26%
  • Other hazards: 2.66%

By using such information to identify critical food safety protection trends, which we define to include food safety (unintentional adulteration) and food fraud (intentional adulteration, inclusive of authenticity/intentional misrepresentation) we can better construct our food protection systems to focus on the areas that present the greatest threats to public health, brand protection and compliance.

A Data Driven Approach

Monitoring Incoming Raw Materials
Assessment and identification of potential food protection issues, including food safety and fraud, at the stage of incoming raw materials is of vital importance for food manufacturers. Knowledge of the associated risks and vulnerabilities allows for timely actions and appropriate measures that may ultimately prevent an incident from occurring.

Specifically, the efficient utilization of global food safety and fraud information should allow for:

  • Identification of prevalent, increasing and/or emerging risks and vulnerabilities associated with raw materials
  • Comparative evaluation of the risk profile for different raw materials’ origins
  • Critical evaluation and risk-based selection of raw materials’ suppliers

A comprehensive risk assessment must start with the consideration of the identified food safety incidents of the raw material, which include the inherent characteristics of the raw material. Next, the origin-related risks must be taken into account and then the supplier-related risks must be examined. The full risk assessment is driven by the appropriate food safety data, its analysis and application of risk assessment scientific models on top of the data.

Using food safety intelligent digital tools to analyze almost 400 unique, chocolate product related food safety incidents around the globe provides us with important, useful insights about cocoa as a raw material, as a raw material from a specific origin and as a raw material being provided by specific suppliers. The graph below represents the results of the analysis illustrating the trend of incidents reported between 2002 and 2018. It can be observed that after a significant rise between 2009 and 2010, the number of incidents approximately doubled and remained at that level for the rest of the evaluated period (i.e., from 2010 to 2018), compared to the period from 2002 to 2005.

Cocoa incidents, FOODAKAI
Graph from Case Study: Chocolate Products: lessons learned from global food safety and fraud data and the guidance it can provide to the food industry,
an industry report from FOODAKAI. Used with permission.

By further analyzing the data stemming from the 400 food safety incidents and breaking them down into more defined hazards, for incoming raw materials, we can clearly see that chemical hazards represent the major hazard category for cocoa.

  • Chemical: 73.46%
  • Biological: 16.49%
  • Organoleptic aspects: 5.93%
  • Other Hazards: 4.38%
  • Fraud: 2.32%
  • Foreign bodies: 2.06%
  • Food additives and flavorings: .77%
  • Allergens: .52%
  • Food contact materials: .52%

Using the appropriate analytical tools, someone can drill down into the data and identify the specific incidents within the different hazard categories. For example, within the “chemical hazard” category specific hazards such as organophosphates, neonicotinoids, pyrethroids and organochlorines were identified.

Comparative Evaluation of Risk Profiles for Different Origins of Raw Materials
The main regions of origin for cocoa globally are Africa, Asia and South America. After collecting and analyzing all relevant data from recalls and border rejections and the frequency of pertinent incidents, we can accurately identify the top hazards for cocoa by region.

The top five specific hazards for the regions under discussion are listed in Table I.

Africa South America Asia
1 Organophosphate 2,4-dinitrophenol (DNP) 2,4-dinitrophenol (DNP)
2 Molds Pyrethroid Poor or insufficient controls
3 Neonicotinoid Aflatoxin Aflatoxin
4 Pyrethroid Cadmium Spoilage
5 Organochlorine Anilinopyrimidine Salmonella
Table I.  Top Five Hazards By Region

After the first level of analysis, a further interpretation of the data using the appropriate data intelligence tools can help to reach to very specific information on the nature of the incidents. This provides additional detail that is helpful in understanding how the regional risk profiles compare. For example, the prevalence of chemical contamination, as either industrial contaminants or pesticides, has been a commonly observed pattern for all three of the regions in Table I. However, beyond the general hazard category level, there are also different trends with regard to specific hazards for the three different regions. One such example is the increased presence of mold in cocoa beans coming from Africa.

The primary hazard categories for cocoa, as a raw ingredient were identified and a comparison among the primary hazards for cocoa by region (origin-specific) should take place. The next step in a data-powered supplier assessment workflow would be to incorporate our use of global food safety data in evaluating the suppliers of the raw materials.

The Role of Global Food Safety Data

This article has been focused on chocolate products but has only touched the surface in terms of the information available in the complete report, which also includes specific information about key raw materials. Let’s also be clear, that the techniques and tools used to generate this information are applicable to all food products and ingredients. As we strive to produce food safely in the 21st Century and beyond, we must adapt our methods or be left behind.

The regulatory environment the food industry must operate in has never been more intense. The threats to an organization’s brand have never been greater. This is not going to change. What must change is the way in which food companies confront these challenges.

Global food safety data can contribute to the establishment of an adaptive food safety/QA process that will provide time savings and improve a quality team’s efficiency and performance.

Based on the continuous analysis of food recalls and rejections by key national and international food authorities, a food safety / quality assurance manager could establish an adaptive supplier verification process and risk assessment process by utilizing the knowledge provided by such data. In that way, QA, procurement, food safety and quality departments can be empowered with critical supplier data that will inform the internal procedures for incoming materials and ingredients (e.g., raw materials, packaging materials) and allow for adaptive laboratory testing routines and compliance protocols. Moreover, food safety systems can become adaptive, enabling quality assurance and safety professionals to quickly update points of critical control when needed, and intervene in important stages of the chocolate manufacturing process.

References

  1. Discovering Chocolate. The Great Chocolate Discovery. Cadbury website. Retrieved from https://www.cadbury.com.au/About-Chocolate/Discovering-Chocolate.aspx.
  2. Chocolate Industry Analysis 2020 – Cost & Trends. Retrieved from https://www.franchisehelp.com/industry-reports/chocolate-industry-analysis-2020-cost-trends/.
Stephanie Pollard, ClearLabs
In the Food Lab

The Power of Advanced NGS Technology in Routine Pathogen Testing

By Stephanie Pollard
No Comments
Stephanie Pollard, ClearLabs

The food industry is beginning to transition into an era of big data and analytics unlike anything the industry has ever experienced. However, while the evolution of big data brings excitement and the buzz of new possibilities, it also comes coupled with an element of confusion due to the lack of tools for interpretation and lack of practical applications of the newly available information.

As we step into this new era and begin to embrace these changes, we need to invest time to educate ourselves on the possibilities before us, then make informed and action-oriented decisions on how to best use big data to move food safety and quality into the next generation.

Stephanie Pollard will be presenting “The Power of Advanced NGS Technology in Routine Pathogen Testing” at the 2018 Food Safety Consortium | November 13–15One of the big questions for big data and analytics in the food safety industry is the exact origins of this new data. Next Generation Sequencing (NGS) is one new and disruptive technology that will contribute significantly to a data explosion in our industry.

NGS-based platforms offer the ability to see what was previously impossible with PCR and other technologies. These technologies generate millions of sequences simultaneously, enabling greater resolution into the microbial ecology of food and environmental surfaces.

This represents a seismic shift in the food safety world. It changes the age-old food microbiology question from: “Is this specific microbe in my sample?” to “what is the microbial makeup of my sample?”

Traditionally, microbiologists have relied on culture-based technologies to measure the microbial composition of foods and inform risk management decisions. While these techniques have been well studied and are standard practices in food safety and quality measures, they only address a small piece of a much bigger microbial puzzle. NGS-based systems allow more complete visibility into this puzzle, enabling more informed risk management decisions.

With these advances, one practical application of NGS in existing food safety management systems is in routine pathogen testing. Routine pathogen testing is a form of risk assessment that typically gives a binary presence/absence result for a target pathogen.

NGS-based platforms can enhance this output by generating more than the standard binary result through a tunable resolution approach. NGS-based platforms can be designed to be as broad, or as specific, as desired to best fit the needs of the end user.

Imagine using an NGS-based platform for your routine pathogen testing needs, but instead of limiting the information you gather to yes/no answers for a target pathogen, you also obtain additional pertinent information, including: Serotype and/or strain identification, resident/transient designation, predictive shelf-life analysis, microbiome analysis, or predictive risk assessment.

By integrating an NGS-based platform into routine pathogen testing, one can begin to build a microbial database of the production facility, which can be used to distinguish resident pathogens and/or spoilage microbes from transient ones. This information can be used to monitor and improve existing or new sanitation practices as well as provide valuable information on ingredient quality and safety.

This data can also feed directly into supplier quality assurance programs and enable more informed decisions regarding building partnerships with suppliers who offer superior products.

Similarly, by analyzing the microbiome of a food matrix, food producers can identify the presence of food spoilage microbes to inform more accurate shelf-life predictions as well as evaluate the efficacy of interventions designed to reduce those microbes from proliferating in your product (e.g. modified packaging strategies, storage conditions, or processing parameters).

Envision a technology that enables all of the aforementioned possibilities while requiring minimal disruption to integrate into existing food safety management systems. NGS-based platforms offer answers to traditional pathogen testing needs for presence/absence information, all the while providing a vast amount of additional information. Envision a future in which we step outside of our age-old approach of assessing the safety of the food that we eat via testing for the presence of a specific pathogen. Envision a future in which we raise our standards for safety and focus on finding whatever is there, without having to know in advance what to look for.

Every year we learn of new advancements that challenge the previously limited view on the different pathogens that survive and proliferate on certain food products and have been overlooked (e.g., Listeria in melons). Advanced NGS technologies allow us to break free of those associations and focus more on truly assessing the safety and quality of our products by providing a deeper understanding of the molecular makeup of our food.

Big data

Embracing Big Data as an Asset to Your Company

By Maria Fontanazza
No Comments
Big data

Big data has become a fairly common term used across industries. It refers to large, complex volumes of data that are generated from multiple sources. The challenge may not be so much in gathering the data but more so in what to do with the information. Although it can be a bear to manage, if able to harness data correctly, food companies could have a leg up on their competition.

“The food industry is behind. As an example, the aerospace industry has the ability to monitor engines on a transatlantic flight to ensure they are operating at the optimal conditions. This data is being used by engineers within different organizations to make improvements,” says Kathy Wybourn, director of food & beverage, USA & Canada at DNV-GL. “Just having the ability to collect information in real time will shift the industry from reactive to proactive. This will require the industry to fit the pieces together to collect information. As an example, you could reject a product at the supplier site, even before it leaves the supplier—you would have all that information at the tips of your fingers.” In a Q&A with Food Safety Tech, Wybourn discusses how the food industry can benefit from the proper use of big data.

Food Safety Tech: What does the term “big data” mean to the food industry?

Kathy Wybourn, DNV-GL
Kathy Wybourn, director of food & beverage, USA & Canada at DNV-GL

Kathy Wybourn: Large volumes of data that is collected from both internal and external sources, used to make smarter business decisions. The supply chain in the food industry is very complex—receiving supplies from all over the globe. [Big data can identify] trends in different regions of the world and assist food companies make better risk decisions about their supply chain. Big data will ultimately improve the safety and quality of products for consumers. Improved supply chain management [and] traceability of products will also lower the risk of food fraud.

We’ve moved from an analog to digital age. The internet has provided the connectivity to link data from raw materials to end users. Using social media data, GPS, photos, videos and data sensors can provide real-time data about raw materials through manufacturing, distribution and retail, which will allow an organization to have better insights into information and decision making along the entire supply chain.

DNV GL recently conducted a survey called “ViewPoint” about the application of Big data. The survey found that 50% of the respondents already have been doing something with Big Data in different ways. Interesting enough, Big Data has different meanings and importance to the respondents, but what is common, is the fact that data will be used differently in the future than what is currently in their tool box. Big Data will allow better insight and enable companies to make fact-based decisions and better manage both performance and risks. The respondents may have different definitions for Big Data, but they all agree that data will be used differently than today for making both internal and external business decisions.

“A higher number of food and beverage companies indicate that big data will have a high or fairly high impact on their business in the next 2¬–3 years. The companies in this industry indicate fewer barriers, even today, in taking advantage of big data concepts. Already, 21% say that their management team is preparing for the new reality and seemingly more food and beverage companies plan to invest in big data.” – DNV-GL Viewpoint Report

FST: How can the industry use big data to make food safer and more sustainable?

Wybourn: Big data will allow the food industry to become even more transparent, which will help improve food safety. Big data will improve supply chain management and allow organizations to make more informed decisions regarding processes, both internally and externally. Food manufacturers can improve efficiency and quality of their own manufacturing processes: Increasing output and solving operational problems faster, which will both have a positive effect on an organization’s bottom line.

Non-conformity data is powerful and can be collected through advanced analytics throughout the supply chain. This data can be further sorted by regions of the world, which will improve knowledge and insight about suppliers. Big data brings further insight beyond what is gained from one audit, which will allow organizations to be confident about making better risk decisions.

Additionally, big data can be used to assess your organization’s performance by benchmarking against other companies’ performance in the areas of nonconformities to food safety standards in their own or different regions.

FST: Can you give some examples of where food companies are or should be leveraging big data to help them in the compliance phase of FSMA?

Wybourn: Both large as well as small companies are struggling with FSMA preventive controls. FSMA mandates that a manufacturing facility have a risk-based supply chain program for raw materials and ingredients for hazards that require a supply chain applied control. Manufacturing sites may rely on a supplier or customer to control a hazard. An organization’s ability to manage big data to improve the organization’s tools to capture, store and analyze this data can greatly improve the monitoring of hazards and lower risk to the supply chain.

FST: Do you have examples of how some companies are leveraging technology to make the best use of their data?

Wybourn: DNV GL has new digital platforms, which can be used to benchmark your own organization to the performance of others.

eAdvantage is a customer portal that provides customers with a complete overview of their former and future audit activities. Through the portal they can see upcoming activities, work with findings and close non-conformities, communicate with an auditor, share audit information, access certificates and monitor their overall progress.

Lumina is a set of tools that provides better insight into a company’s management system. It analyses information hidden in the company’s audit data and allows to benchmark that company against thousands of others worldwide based on more than 1.6 million audit findings. It allows an organization to obtain an overview of their own sites performance, spot warning signs at an early stage and see how they compare to similar companies in the industry, giving confidence to make the right decisions.

Veracity is an open industry data platform, ideal for integrating data in a secure way. The Veracity eco-system handles asset data, manages data quality and applies advanced analytics, connecting industry players for frictionless data aggregation, sharing and benchmarking. In the aquaculture industry, this will lay the foundation for predictive analyses, decision support, indication warning, and simulation capabilities unlocking substantial growth potential in the global aquaculture industry. All the while, we make sure fish farmers and other data providers retain ownership and control of their data.

I believe we are only at the tip of an iceberg of where big data can take the food & beverage Industry.

FST: Is it possible to get too much data? Are food companies going to be bombarded with too much info that they don’t know how to use?

Wybourn: The answer is simple, yes. We live in a world of data abundance and information overload each day. Data sets are growing rapidly, and the ability to store and analyze data is daunting. The tools we have today will become obsolete tomorrow. One only can sort through data with the tools he/she has today to understand even the simplest of processes.