Thermometers may help: Caterers in China are reportedly using AI to spot unhygienic cooks

Thepaper.cn (via the South China Morning Post) reports that local authorities in eastern China have tapped artificial intelligence (AI) to clamp down on unsanitary cooks in kitchens — and to reward those who adhere to best practices.

According to the report, a camera-based system currently being piloted in the Zhejiang city of Shaoxing automatically recognizes “poor [sanitation] habits” and alerts managers to offending workers via a mobile app. It’s reportedly the fruit of a six-year project — Sunshine Kitchen — that seeks to bring transparency to food preparation in catering, hotels, school cafeterias, and restaurants.

Zhou Feng, director of the Food Service Supervision Department in Shaoxing, told Thepaper.cn that the system can identify 18 different “risk management” areas, including smoking and using a smartphone. On the flip side, it recognizes four positive habits, like disinfecting surfaces and hand washing, and monitors kitchen conditions that might impact food safety, such as temperature and humidity.

So far, the local Xianheng Hotel and over 87 catering companies are said to have trialed the system, and authorities reportedly plan to expand the number to over 1,000 this year.

It’s not the first time AI has been applied to food safety.

In November 2018, a study led by researchers at Google and Harvard’s T.H. Chan School of Public Health described a machine learning model — FINDER (Foodborne IllNess DEtector in Real time) — that leveraged search and location data to highlight “potentially unsafe” restaurants. FINDER took in anonymous logs from users who opted to share their location data, and it identified search queries indicative of food poisoning (e.g., “how to relieve stomach pain”) while looking up restaurants visited by the users who performed those searches.

In the end, FINDER not only outperformed complaint-based inspections and routine inspections concerning precision, scale, and latency (the time that passed between people becoming sick and the outbreak being identified), it managed to better attribute the location of foodborne illness to a specific venue than did customers.

San Francisco-based startup ImpactVision, meanwhile, leverages machine learning and hyperspectral imaging — a technique that combines spectroscopy and computer vision — to assess the quality of food in factories and elsewhere automatically. It’s now working with avocado distributors to replace their current systems, and with large berry distributors to potentially automate manual processes, such as counting strawberries.

Food Safety Talk live in Geneseo, NY

Don and I are recording a live show tonight at SUNY Geneseo thanks to an invite from Dr. Beth McCoy. Beth has been a listener since close to the beginning. It’s always cool to find out that someone actually listens to the stuff we talk about. As I did some prep for the show, I stumbled upon a local bar and grabbed a Genny Cream Ale. The bartender saw the Food Safety Talk decal I have on my MacBook and we struck up a conversation about what it’s like to work in the back of the house of a restaurant.

My most valuable experience as a food safety person remains washing dishes in a local Guelph bar.

Sex & drugs & rock and roll.

And food safety.

We talked food safety myths, eating leftover pizza, stuff both of us have seen in the kitchen and cleaning up puke (and dragging the mop bucket back into the kitchen).

 

Egg perfect protein (except when they have Salmonella) and inspections suck

Emily Hopkins of the Indy Star writes that at Indiana-based Rose Acre’s North Carolina farm, 3 million chickens produce about 2.3 million eggs every day, apparently under the watchful eye of a U.S. Department of Agriculture grader.

That grader is supposed to be at the farm every day. Which raises a question: Why did it take an outbreak of Salmonella, one that sickened 23 people in nine states, to alert officials to problems at the farm?

A USDA spokeswoman acknowledged to IndyStar that a typical day for a grader involves checking a facility’s equipment prior to that day’s operation. It’s at this point that any observed issues are addressed. After that, the grader will enter the grading booth to inspect eggs during the processing day.

“In this instance, our grader(s) did not observe issues that would have triggered a report to FDA inspectors,” the spokeswoman said via email.

But the USDA didn’t specifically address IndyStar’s question about whether a grader should have observed those issues.

According to an egg grading manual published by the USDA, graders must “continually monitor product handling and general condition of equipment, and housekeeping throughout the (egg processing) facility” and ‘identify sanitation problems requiring corrective action.”

That might have applied to the Rose Acre Farm, where many of the FDA violations were made in the egg processing building.

For example, FDA inspectors who visited the farm after the Salmonella outbreak foundthat the procedure for cleaning the egg “orientor” was not being implemented, and employees were observed cutting corners while washing the eggs. Water from the “ceilings, pipes and down walls” was found dripping onto production equipment, and dried egg and shells were seen to have accumulated on the same areas over multiple days.

There were other violations, including excessive rodent activity, that were noted, but those were observed in the farm’s hen houses, which graders typically do not have access to.

After eggs are washed in the processing facility, graders check the eggs for cracks or other outside imperfections. They’ll also take a look inside the egg using a process called candling. Once the eggs are deemed up to USDA standards of quality, they receive a USDA seal.

The value of the program, which is voluntary, is that it communicates to consumers that they are buying a product held to higher standards, according to Darrin Karcher, an extension poultry specialist at Purdue University. 

“It gives another layer of credibility to the consumer,” Karcher said.

Karcher, however, could not say whether in this particular case the USDA grader missed an opporutnity. 

A grader’s day starts with a visual check of the processing plant before work begins, the USDA spokeswoman told IndyStar. If issues are observed, the grader is supposed to work with facility management to correct them before operations start. 

“This is not a substitute for FDA’s more in-depth food safety regulatory examinations of an entire operation,” the spokeswoman said. “We take our responsibility very seriously and any time a significant issue is identified, USDA graders flag it for FDA through a formal process to ensure their regulatory inspectors are informed in a timely manner.”

This is one of the largest egg recalls since 2010, when 500 million eggs from an Iowa producer were recalled, and nearly 2,000 illnesses caused by Salmonella were reported. That outbreak spurred the FDA and USDA to issue a memorandum of understanding outlining information sharing priorities. The MOU authorizes USDA graders to withhold the seal if they believe that a facility is in violation of food safety rules or if the product poses a risk. 

After the FDA linked the pathogen back to Rose Acres’s North Carolina farm, the company issued a voluntary recall of more than 206 million eggs, out of “an abundance of caution.”

Audits and inspections are never enough: A critique to enhance food safety

30.aug.12

Food Control

D.A. Powell, S. Erdozain, C. Dodd, R. Costa, K. Morley, B.J. Chapman

http://www.sciencedirect.com/science/article/pii/S0956713512004409?v=s5

Internal and external food safety audits are conducted to assess the safety and quality of food including on-farm production, manufacturing practices, sanitation, and hygiene. Some auditors are direct stakeholders that are employed by food establishments to conduct internal audits, while other auditors may represent the interests of a second-party purchaser or a third-party auditing agency. Some buyers conduct their own audits or additional testing, while some buyers trust the results of third-party audits or inspections. Third-party auditors, however, use various food safety audit standards and most do not have a vested interest in the products being sold. Audits are conducted under a proprietary standard, while food safety inspections are generally conducted within a legal framework. There have been many foodborne illness outbreaks linked to food processors that have passed third-party audits and inspections, raising questions about the utility of both. Supporters argue third-party audits are a way to ensure food safety in an era of dwindling economic resources. Critics contend that while external audits and inspections can be a valuable tool to help ensure safe food, such activities represent only a snapshot in time. This paper identifies limitations of food safety inspections and audits and provides recommendations for strengthening the system, based on developing a strong food safety culture, including risk-based verification steps, throughout the food safety system.

 

We don’t need no edumacation

For all the folks out there trying to educate consumers and others about food safety, forget it.

Stick with stories.

Pink Floyd figured that out in 1980, in what would become the soundtrack for my grade 12 (Stones’ Some Girls was the soundtrack for grade 10) and a weirdly accurate foretelling of my first marriage.

Everyone’s got a camera: NYC-market-worker-boot-on-fish edition

Ciara McCarthy of Patch reports a Chinatown fish market has become the latest Internet sensation. A video filmed by a customer shows a worker climbing on a tray of fish, apparently to reach an electrical box. His boots are seen on top of the fresh produce.

The video was shot at the Hung Fee Food Market, located at 214 Canal St., on Jan. 3 and uploaded to Facebook the next day by April Davidson, she told Patch in a message. It had been viewed nearly 180,000 times as of Tuesday.

“Seriously, seriously, you’re gonna stand there on the food with your boots?” Davidson can be heard asking in the video.

The footage has garnered thousands of shares on Facebook and has spurred hundreds of Yelp reviewers to leave negative comments on the market’s page.

A woman who answered the phone at the fish market said she didn’t speak English and there wasn’t anyone available to comment.

An employee at the store told Pix 11 that the man had been called in to fix an emergency electrical problem and said that all the fish that were stepped on were thrown out before they could be sold.

The New York Department of Agriculture and Markets found “critical deficiencies” at the food market after conducting a review on Monday, spokeswoman Lisa Koumjian told Patch. The state agency dispatched a food safety inspector after seeing the video.

The Hung Kee Food Market was assigned a “C” grade for its sanitary conditions, Koumjian said. The state will conduct a follow-up inspection at the market in the near future. 

“The food safety inspector also addressed the consumer complaint regarding an individual standing on fresh fish,” Koumjian said in a statement.

“Management stated that a contractor, who was hired to repair an emergency electrical issue, stood directly on a fish display to access the electrical panel. Management has since instructed employees on proper access for electrical panels without jeopardizing product integrity and wholesomeness.”

Some Yelp reviewers came to the shop’s defense in the wake of the internet backlash. 

One man, who identified himself on Yelp as “Sailor J.” wrote, “Ok, I’ve been on the ocean for 30+ years… Have ANY of you freaksouts (who’ve likely never even been to this market) ever seen the deck of a typical commercial fishing boat when operating in full gear?” he wrote in his review. “The bottom of this guys shoes is, by far, not the nastiest thing these fish have touched.”

Popular doesn’t mean safe

There’s lots of popular food places. They might even make great food. Doesn’t mean that they know how to do food safety.

According to Wales Online, a popular chippy (one of my favorite UK terms) received a zero on their hygiene rating. Zero isn’t good. Unless the scale is -1 to zero. But it isn’t in Wales. Environmental health folks rate businesses on a scale from zero-5. 

The Fryery, in Rumney , was ranked at number nine on hungryhouse’s list after the online food ordering platform unveiled the list as part of its annual Most Loved Takeaway awards in April. 

But an inspection on November 20 handed the shop a zero rating meaning “urgent improvement” is necessary.

The Cardiff takeaway, which is located in Newport Road, is run by Kash Amin.

Mr Amin, who started working at his family’s takeaway at the age of 11 in 1988, has continued working in and running takeaways ever since – including Victor’s in Newport . 

Mr Amin said he was unhappy with the process of food hygiene rating inspections and said he had now paid £150 to appeal the decision.

Here’s the rating, doesn’t say much about the specifics of what was wrong. I wish more jurisdictions, including Wales, posted the entire inspection. The summary leaves a lot to assumptions.

It was probably the kitchen sink: 82 sick with Salmonella from UK restaurant 2015-16

From Eurosurveillance:

It is estimated that over 38,000 community cases of salmonellosis occur annually within the United Kingdom (UK) [1,2]. Salmonellosis often results from consumption of contaminated food or water [3], however, transmission via asymptomatic shedding by food handlers and exposure to contaminated environments where conditions are favourable for pathogen survival have also been implicated [3,4]. Here we report the findings of an investigation of an outbreak of salmonellosis where the environment was pivotal in continued transmission.

On 7 March 2015, Public Health England (PHE) East Midlands was alerted by the clinical microbiology laboratory of a local hospital to 21 cases of Salmonella enterica serovar Typhimurium gastroenteritis, with onset in February 2015. Seven cases in this initial phase of the outbreak required hospitalisation. Following this notification we suspected there was a community outbreak of S. Typhimurium; investigations and attempts to control the outbreak followed.

Hypothesis-generating interviews at the outset of the investigation identified that several cases had eaten at the same restaurant during the incubation period for their illness. Descriptive epidemiological analyses including subsequent cases pointed to the restaurant being the likely source. This popular, purpose (newly) built restaurant had opened only 18 months before the outbreak. The restaurant offered a full table-service menu, self-service salad bar and hot self-service carvery buffet serving roasted meats (turkey, beef, gammon and pork at weekends) and vegetables and condiments. Despite interventions to control the initial outbreak, cases continued to emerge followed by a prolonged period of transmission until 2016. The evolution of the investigation into this community outbreak and subsequent control measures is described, with specific reference to the use of whole genome sequencing (WGS) to link isolates and the role of the drains in continued pathogen transmission.

Mapping and visual inspection of the drainage systems identified significant issues. Water filled traps (u-bends) designed to prevent foul air flow from the drainage system into the building had failed and smoke testing revealed some ineffective drain seals, potentially allowing contaminated bio-aerosol to be disseminated into the kitchen. One sink drain was not connected to any drainage system with waste water pooling under the floor. Other larger drains had failed after leaking waste-water washed away the supporting substrate forming a cavity under the kitchen area. It transpired at that point that drainage water had, on occasion, risen into the kitchen area, although this had not been previously reported. Substantial remedial works were undertaken, however, these were found to have failed on re-inspection and so these drains were later decommissioned.

Biofilm [15] and flooded areas in underfloor cavities may have sustained this outbreak, after repeated environmental cleaning failed. Drainage problems in one area of the kitchen led to liquid from the drains seeping into the kitchen suggesting a contamination pathway. We found isolates matching the outbreak strain on kitchen cloths, swabs from kitchen sinks, and pot wash areas suggesting contact with sinks may have provided a second contamination pathway. We also identified ineffective drain water-traps potentially allowing the movement of contaminated bio-aerosols [13]. Smoke tests demonstrated the potential for dissemination of foul air into the kitchen.

Investigation using whole genome sequencing of a prolonged restaurant outbreak of salmonella typhimurium linked to the building drainage system, England, February 2015 to March 2016

Eurosurveillance, John Mair-JenkinsRoberta Borges-StewartCaroline HarbourJudith Cox-RogersTim Dallman, Philip AshtonRobert JohnstonDeborah ModhaPhilip MonkRichard Puleston,  https://doi.org/10.2807/1560-7917.ES.2017.22.49.17-00037

http://www.eurosurveillance.org/content/10.2807/1560-7917.ES.2017.22.49.17-00037

 

Less food poisoning associated with employee paid sick time?

I refer to parenting as hypocrisy disease.

And there’s been more than a few times when Amy has said to me, practice what you preach.

Like barfing and going to work.

People should not work when they are sick.

But in the world of food, people are going to lose their jobs if they don’t show up.

Hsuan et al. write in the American Journal of Preventative Medicine that:

Previous studies suggest an association between paid sick leave (PSL) and better population health, including fewer infectious and nosocomial gastrointestinal disease outbreaks. Yet few studies examine whether laws requiring employers to offer PSL demonstrate a similar association. This mixed-methods study examined whether laws requiring employers to provide PSL are associated with decreased foodborne illness rates, particularly laws that are more supportive of employees taking leave.

Methods:

The four earliest PSL laws were classified by whether they were more or less supportive of employees taking leave. Jurisdictions with PSL were matched to comparison jurisdictions by population size and density. Using difference-in-differences, monthly foodborne illness rates (2000-2014) in implementation and comparison jurisdictions before and after the laws were effective were compared, stratifying by how supportive the laws were of employees taking leave, and then by disease. The empirical analysis was conducted from 2015-2017.

Results:

Foodborne illness rates declined after implementation of the PSL law in jurisdictions with laws more supportive of employees taking leave, but increased in jurisdictions with laws that are less supportive. In adjusted analyses, PSL laws that were more supportive of employees taking sick leave were associated with an adjusted 22% decrease in foodborne illness rates (p=0.005). These results are driven by campylobacteriosis.

Conclusions:

Although the results suggest an association between more supportive PSL laws and decreased foodborne illness rates, they should be interpreted cautiously because the trend is driven by campylobacteriosis, which has low person-to-person transmission.

Association of paid sick leave laws with foodborne illness rates

Am J Prev Med. 2017 Sep 1. pii: S0749-3797(17)30359-8. doi: 10.1016/j.amepre.2017.06.029. [Epub ahead of print]

Hsuan C, Ryan-Ibarra S, DeBurgh K, Jacobson DM

https://www.ncbi.nlm.nih.gov/pubmed/28870665

Norovirus modeling: Stay at home after the barfing and pooping is gone

Duret et al. write in Risk Analysis:

We developed a quantitative risk assessment model using a discrete event framework to quantify and study the risk associated with norovirus transmission to consumers through food contaminated by infected food employees in a retail food setting.

This study focused on the impact of ill food workers experiencing symptoms of diarrhea and vomiting and potential control measures for the transmission of norovirus to foods.

The model examined the behavior of food employees regarding exclusion from work while ill and after symptom resolution and preventive measures limiting food contamination during preparation.

The mean numbers of infected customers estimated for 21 scenarios were compared to the estimate for a baseline scenario representing current practices. Results show that prevention strategies examined could not prevent norovirus transmission to food when a symptomatic employee was present in the food establishment. Compliance with exclusion from work of symptomatic food employees is thus critical, with an estimated range of 75–226% of the baseline mean for full to no compliance, respectively.

Results also suggest that efficient handwashing, handwashing frequency associated with gloving compliance, and elimination of contact between hands, faucets, and door handles in restrooms reduced the mean number of infected customers to 58%, 62%, and 75% of the baseline, respectively.

This study provides quantitative data to evaluate the relative efficacy of policy and practices at retail to reduce norovirus illnesses and provides new insights into the interactions and interplay of prevention strategies and compliance in reducing transmission of foodborne norovirus.

Quantitative risk assessment of norovirus transmission in food establishments: Evaluating the impact of intervention strategies and food employee behavior on the risk associated with norovirus in foods

Risk Analysis, Vol. 37, No. 11, 2017

DOI: 10.1111/risa.12758

Duret et al.

http://onlinelibrary.wiley.com/doi/10.1111/risa.12758/epdf

 

The Good, Bad, and Ugly Texas edition

An audit investigation of the Austin Public Health Department reveals inspectors napping, shopping, and taking extended breaks. Unfortunately things like this happen and without proper management and effective leadership, things like this will continue to happen.
Disappointing when the actions of a few inspectors tarnish the reputation of others who actually take pride in the work they do and have an ethical, moral backbone. When I first started as an inspector, I recall hearing a number of stories of bribery on the job and other ridiculous things. Like any profession, you have the good, bad, and ugly.

David Barer of KXAN writes
Austin Public Health’s Environmental Services Division, which conducts restaurant inspections among other duties, “wasted city resources as a result of grossly inefficient practices and procedures,” according to the audit.
Auditors also found three environmental health officers wasted time while on the city clock, and two “may have attempted to conceal their misuses on their inspection reports.”
Environmental health officers spend a majority of their time in the field with “limited oversight,” according to the report. Inspectors had no set list of daily inspections; rather, inspectors chose to inspect whichever restaurant was due, and officers were not required to notify supervisors ahead of inspections or check in before or after they were conducted, auditors found.
Investigators said they found several instances of officers saying their inspections took place at times that did not square with what the auditors observed.
According to the report, supervisors were only conducting a “supervisory audit,” which is an in-person check of an officer’s inspection, on less than two percent of inspections. Despite concerns about officers wasting time, management did not regularly review or question how time was being used in the field.
· KXAN Investigation: Restaurant inspectors weren’t meeting inspection-rate standards.
Audit office investigators followed three environmental health officers inspectors during their daily routine and found inspectors napping, shopping and exercising, according to the report.
Investigators found one environmental health officer working out at a local gym for an hour and a half to two hours on at least two separate days. She also left work an hour early on one occasion. She “also may have attempted to conceal the misuse by misrepresenting the time in and out on her written inspection reports,” the audit states.
Another employee was observed napping in her car and misrepresented the times she went in and came out of a restaurant inspection, auditors said.

The rest of the story can be found here:
http://kxan.com/2017/09/01/audit-finds-austin-restaurant-inspectors-shopping-napping-while-on-the-job/