Predicting Myalgic Encephalomyelitis/Chronic Fatigue Syndrome from Early Symptoms of COVID-19 Infection , 2023, Hua et al

Sly Saint

Sly Saint

Senior Member (Voting Rights)
Abstract
It is still unclear why certain individuals after viral infections continue to have severe symptoms. We investigated if predicting myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) development after contracting COVID-19 is possible by analyzing symptoms from the first two weeks of COVID-19 infection. Using participant responses to the 54-item DePaul Symptom Questionnaire, we built predictive models based on a random forest algorithm using the participants’ symptoms from the initial weeks of COVID-19 infection to predict if the participants would go on to meet the criteria for ME/CFS approximately 6 months later. Early symptoms, particularly those assessing post-exertional malaise, did predict the development of ME/CFS, reaching an accuracy of 94.6%. We then investigated a minimal set of eight symptom features that could accurately predict ME/CFS. The feature reduced models reached an accuracy of 93.5%. Our findings indicated that several IOM diagnostic criteria for ME/CFS occurring during the initial weeks after COVID-19 infection predicted Long COVID and the diagnosis of ME/CFS after 6 months.

https://www.mdpi.com/2624-8611/5/4/73
 
Questionniares were filled in online by about 300 people at about 6 months of self identified Long Covid. The data for their symptoms at 2 weeks after infection were based on recall filled in at the same time point as the 6 months data, not done at the time, so liable to a high degree of recall bias. This was basically a data analysis exercise, no medical examinations were done.

And it used the DePaul questionnaire with its flawed questions on PEM that focus on fatigue immediately after exercise, not delayed malaise.

I doubt anything useful can be concluded from this.
 
Trish said:
The data for their symptoms at 2 weeks after infection were based on recall filled in at the same time point as the 6 months data, not done at the time, so liable to a high degree of recall bias.
Click to expand...
Agree. Direct quote from the article:

"Participants were asked to complete two symptom questionnaires, one of which detailed “present” symptoms and the other “recalled” symptoms from the first two weeks after COVID-19 diagnosis, an average of 21.7 weeks prior."
​
It would be interesting data if it came from a longitudinal cohort.
 
Trish said:
The data for their symptoms at 2 weeks after infection were based on recall filled in at the same time point as the 6 months data, not done at the time, so liable to a high degree of recall bias
Click to expand...
How is that not a straightforward reason for the journal to reject the paper?

Added: journal information


Psych
Psych is an international, peer-reviewed, open access journal on psychiatric sciences and psychology, published quarterly online by MDPI.
 
You must log in or register to reply here.
Back
Top Bottom