Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Biomarker for chronic fatigue syndrome identified

med.stanford.edu

Post reply on HN
Print view View original

41–50 of 228 posts

Re: Biomarker for chronic fatigue syndrome identified

#41

Post by freeradical13 »

Why did they need machine learning? It seems from Figures 2B-G that there's a clear cut off.

"Moreover, to create a classifier for ME/CFS patients capable of identifying new patients, required for a robust diagnostic tool, we developed a trained kernel Support Vector Machine (SVM), a supervised machine-learning algorithm, using our experimental data. To classify new patients based on whether they fall to the right of the decision boundary, we initially selected the two features with the largest significance: change from the baseline to the plateau and change from the minimum to the plateau for the in-phase components of the impedance. Using these features, a cubic polynomial kernel SVM was able to classify the two populations, although the two features are highly correlated, as shown in Fig.2H."

https://www.pnas.org/content/pnas/early/2019/04/24/190127411...

Re: Biomarker for chronic fatigue syndrome identified

#42

Post by vaelin »

whalabi wrote: post #31

I'm just astonished by this. Millions of people (in the US alone!) suffer from this illness and I think everyone has wondered, or heard it wondered, if it's imaginary. For all these people to know there's something actually physically wrong with them is massive. It'll shift the thinking of everyone in the profession, of their families and friends and colleagues, and of themselves. It's a huge, huge breakthrough.

I have ME/CFS. The evidence has been clear that it is a physical condition for quite a while now. In fact, the Institute of Medicine clarified that point in a thorough report in 2015:

> The primary message of the committee’s report is that ME/CFS is a serious, chronic, complex, systemic disease that often can profoundly affect the lives of patients.

>Many health care providers are skeptical about the seriousness of ME/CFS, mistake it for a mental health condition, or consider it a figment of the patient’s imagination. Misconceptions or dismissive attitudes on the part of health care providers make the path to diagnosis long and frustrating for many patients. The committee stresses that health care providers should acknowledge ME/CFS as a serious illness that requires timely diagnosis and appropriate care. [1]

Having said that, I am obviously delighted by this study for a whole host of reasons. A diagnostic test will be hugely beneficial in driving home the message that it is not, in fact, an imaginary condition. It will also be beneficial in testing treatment outcomes, as the lack of a test has made gauging treatment efficacy very challenging.

There are a lot of hurdles to overcome yet, but we are FINALLY on the right path.

[1] Quotes contained in the Key Brief PDF - http://www.nationalacademies.org/hmd/Reports/2015/ME-CFS.asp...

Re: Biomarker for chronic fatigue syndrome identified

#43

Post by vaelin »

derefr wrote: post #27

Does it say anywhere in the paper what the “promising drug” that decreases the effect might be?

Not in the paper, but Ron gave a talk where he mentioned an MS drug (I have forgotten which) and a new drug that targets mitochondria which is not yet licensed for anything.

Sorry I can't be more specific. I don't remember the details.

Re: Biomarker for chronic fatigue syndrome identified

#46

Post by UglyToad »

This sounds brilliant if it can be replicated. From what I've read and heard large parts of the medical establishment still treats ME/CFS patients as lazy/making it up. For there to be a positive diagnosis rather than a diagnosis of exclusion is the first step to getting these people the help they deserve.

Re: Biomarker for chronic fatigue syndrome identified

#47

Post by vaelin »

daedalus_f wrote: post #37
whalabi wrote: post #31

I'm just astonished by this. Millions of people (in the US alone!) suffer from this illness and I think everyone has wondered, or heard it wondered, if it's imaginary. For all these people to know there's something actually physically wrong with them is massive. It'll shift the thinking of everyone in the profession, of their families and friends and colleagues, and of themselves. It's a huge, huge breakthrough.

This is promising data but it’s very early. The authors are not really sure what the test is measuring on a cellular level, though they speculate a lot in the discussion, and we can’t yet truly infer a causal link between what’s causing the test result and disease status. It’s is going to take a lot more validation before we get to the stage where this is clinically useful. For instance, the control group were health…

It could also be measuring the result of extreme inactivity. I am bedridden, and I have no doubt that lying in bed for years has had a profound effect on my physiology independently of my ME/CFS.

The acid test will be when we compare ME/CFS patients to matched MS patients. However, as Ron Davis has stated, it might also be the case that MS patients have ME/CFS, as ME/CFS is highly heterogenous and may be arrived at from multiple directions.

There are lots of details that need to be ironed out. Nevertheless, this is exciting news.

Re: Biomarker for chronic fatigue syndrome identified

#48

Post by jdietrich »

whalabi wrote: post #31

I'm just astonished by this. Millions of people (in the US alone!) suffer from this illness and I think everyone has wondered, or heard it wondered, if it's imaginary. For all these people to know there's something actually physically wrong with them is massive. It'll shift the thinking of everyone in the profession, of their families and friends and colleagues, and of themselves. It's a huge, huge breakthrough.

>Millions of people (in the US alone!) suffer from this illness and I think everyone has wondered, or heard it wondered, if it's imaginary.

For all these people to know there's something actually physically wrong with them is massive.

IMO the broader issue is the stigma against mental illness. The leading hypothesis remains that chronic fatigue syndrome is a mental illness. Both your comment and the linked article imply a false dichotomy between "real" physical illness and "imaginary" mental illness. Mental illnesses are every bit as "real" as physical illnesses. They cause real suffering, real disability and real death. If chronic fatigue syndrome happens to have a psychological etiology, then sufferers still deserve compassion, effective treatment and proper research.

The research in question has a relatively small sample size and only compares CFS patients with healthy volunteers. Identifying abnormalities in immunological or stress-response functioning may not be particularly useful in proving that CFS is "real" (i.e. non-psychological), because we have identified similar abnormalities in patients with depressive disorders. Some researchers argue that major depressive disorder may be an autoimmune disorder, although this is far from a mainstream opinion.

https://doi.org/10.1073/pnas.1901274116

https://doi.org/10.1371/journal.pone.0138904

https://doi.org/10.1016/j.it.2005.11.006

https://doi.org/10.1016/j.pnpbp.2004.11.003

Re: Biomarker for chronic fatigue syndrome identified

#49

Post by benatkin »

ufo wrote: post #33
benatkin wrote: post #19

Earlier quoted context omitted.

> No one knows the cause yet If we can determine for sure that it's happening a at a much higher rate than in the past, we have a pretty good idea that the cause is the conditions that we live in. Diet that is one thing in which the changes over the years have been similar across different regions. If it was air pollution, the increased rates would show up in some regions but not others. Ditto radiation. I don't thin…

Even today it is very hard to get an accurate CFS dianosis. Patients often are diagnosed with as suffering from a viral infection, or psychological, neurological, or immune disease. They almost always only get a CFS diagnosis after all the other treatments fail. I definitely would not be surprised if it turned out to be present in the past, but misdiagnosed. One thing that certainly does not help is that the primary…

I don't think severe limitations in physical mobility were as common in the past. I'm not the only one who thinks this. The creators of WALL•E clearly think it as well.

Re: Biomarker for chronic fatigue syndrome identified

#50

Post by L2R »

freeradical13 wrote: post #41

Why did they need machine learning? It seems from Figures 2B-G that there's a clear cut off. "Moreover, to create a classifier for ME/CFS patients capable of identifying new patients, required for a robust diagnostic tool, we developed a trained kernel Support Vector Machine (SVM), a supervised machine-learning algorithm, using our experimental data. To classify new patients based on whether they fall to the right of…

Nothing wrong with an SVM. How else would they create a decision boundary for classifying patients? The choice of the polynomial kernel is interesting, but I don't think it causes any issues given the data.
Post reply on HN