Contaminated science
Did lab test results confirm onions as culprits of recent E.coli outbreak?
In one sense, the E.coli outbreak attributed to McDonald's has ended, as reported cases have dwindled to a drip. In another sense, it hasn't ended, because the number of cases is still growing.
This is the challenge of foodborne disease outbreak investigations. It is still possible that the theory that onions caused the outbreak is a false lead. In the most successful investigations, scientists were able to isolate samples of contaminated foods which contain the specific strain of the bacteria causing illnesses. An example of a very successful case is the spinach investigation featured in Numbers Rule Your World (link).
***
Late last week, CDC put out a new press release (link), updating the public about the current investigation. But it manages to unnerve me with terrible messaging.
The communication on November 13, 2024 carries the following conclusion:
"Epidemiologic and traceback data show that fresh, slivered onions served at McDonald’s were the likely source of this outbreak. Affected onions served at McDonald's locations were recalled and are past shelf life."
The sentences point to two types of evidence: epidemiological data come from questionnaires sent to reported cases asking for information such as what foods were consumed prior to getting sick from E.coli; and traceback data require salvaging potentially contaminated ingredients at source and testing them in labs for the specific strain of E.coli associated with the current outbreak.
We already knew about the epi data. What's new in this press release is the traceback data. Epidemiological data always come first, and were used to point the finger at McDonald's, then Quarter Pounders at McDonald's, then fresh, slivered onions in Quarter Pounders at McDonald's.
Scroll to the bottom of the press release, and this is the entire paragraph published about traceback:
FDA tested recalled onions and one sample tested positive for non-O157:H7 Shiga toxin-producing E. coli. The E.coli found in onions was not the outbreak strain and no human illnesses have been linked to this strain. Additional testing results will be released when available by FDA.
It's a word salad worthy of U.S. presidential candidates.
Translation: the investigators did not find the specific strain of E.coli associated with this outbreak in the onion samples they collected from the farms. We don't know how many samples they tested but only one of them tested positive for any kind of E.coli, and unfortunately for the investigation, it wasn't the right strain. Thus, this positive result does not strengthen the evidence against onions from those farms, and their customer, McDonald's.
And yet, whoever wrote the summary paragraph inserted the false claim that epi and traceback data were consistent, and complementary.
As a scientist, I find that this type of communciations undermines my confidence in our public health organizations. One can say this is an instance of "story time". They lull us in with some data, and then spin a story ostensibly supported by the data but not really.
Indeed, most media outlets have swept the uncertainty under the rug, referring to this outbreak as the McDonald's outbreak, or the onions outbreak. The CDC press release actually only used the term the "likely" source.
***
For giggles, I asked ChatGPT whether the lab test results added to the evidence that onions were the cause of the outbreak, and here is its answer:
No, the lab testing did not directly add to the evidence that the onions were the cause of the E. coli outbreak. The epidemiological evidence was already strong, with 99% of the interviewed individuals reporting eating at McDonald's, and 84% specifically eating menu items containing fresh slivered onions. The lab testing of recalled onions found a non-O157:H7 strain of E. coli, which was not linked to human illnesses and did not match the outbreak strain. Therefore, while the testing confirmed that the onions were contaminated with E. coli, it did not provide direct confirmation that the specific strain responsible for the outbreak was linked to the onions. The epidemiological data (such as the high proportion of sick individuals who ate the onions) was the primary evidence supporting the conclusion that the onions were the source.
I like this answer!
***
Note: It's possible that the lab testers knew something else that links those tested onions to the outbreak but nothing about the lab test results as disclosed in the press release supports its summary paragraph.
Note 2: In the meantime, the economic damage of food recalls is real. McDonald's is reportedly spending $100 million to recover from the fallout (link).
