Biomarker for chronic fatigue syndrome identified • Hacker News Board

Re: Biomarker for chronic fatigue syndrome identified

#151

Post by mises » Sun, May 05, 2019, 9:11 PM UTC

perseusmandate wrote: post #56

jdietrich wrote: post #48

Earlier quoted context omitted.

>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 im…

It isn't just that the suffering from mental illness is real, it causes very real physical health issues and deeply disrupts your body's hormonal makeup via the HPA axis. The strict delineation between physiological and psychological illnesses is mostly a Western construct and the unfortunate effect is that the CFS community has an obsession with proving that it is a 100% physical illness without any mental component…

Careful not to swing too far the other way. In situations where physical treatments are an option (even if they would only help, not cure), it is important not to give such treatments if it is a mental illness as treatments have risks. If it is mental, mental illness treatment might actually help.

Re: Biomarker for chronic fatigue syndrome identified

#152

Post by tigershark » Sun, May 05, 2019, 9:11 PM UTC

wavepruner wrote: post #129

GordonS wrote: post #55

Earlier quoted context omitted.

Keep in mind that CFS is a currently a diagnosis of exclusion - many people labelled with CFS may in fact have another, undiagnosed illness. For example, it's been found that a lot of CFS (and fibromyalgia) patients turn out to have small fiber neuropathy (damage to he nerve fibers that signal pain), and neurotoxins have been shown to cause general fatigue (I'm in mobile, so no references for now I'm afraid). The ski…

I found out last year the root cause of my CFS is life-long mercury toxicity (a well understood neurotoxin). I am responding very positively to treatment. I rarely talk about it because people get very upset when I tell them about the evidence of where the mercury came from.

Do you eat 20 cans of tuna a day? When I was much younger I ate 1-2 cans of tuna pretty much every day for few years and I didn’t have any ill effect at all.

Re: Biomarker for chronic fatigue syndrome identified

#153

Post by sagebird » Sun, May 05, 2019, 9:16 PM UTC

kens wrote: post #137

Smaug123 wrote: post #2

Paper at https://www.pnas.org/content/pnas/early/2019/04/24/190127411... Pleasantly surprised to discover that it was legally available! The test appears to be ridiculously good. Perfect separation of 40 subjects into those who have been diagnosed with CFS and those who are known to be healthy, from blood samples. I want to see this replicated, by people who are not the original authors; but if this test is anything…

Thanks for the paper link. I read the paper and it's really a semiconductor sensor engineering paper, not a biology paper. The paper seems very preliminary; it shows that CFS and non-CFS sample have widely different impedances under osmotic stress, but the mechanism behind this is entirely hand-waving. If I'm reading the paper correctly, the samples were peripheral blood mononuclear cells (i.e. lots of different cell…

The use of machine learning needs to be explained. I’m half expecting it to boil down to “we evolved the neural nets until it perfectly separated the two groups” — overfitting “learning”.

Re: Biomarker for chronic fatigue syndrome identified

#154

Post by rufus85 » Sun, May 05, 2019, 9:18 PM UTC

I have some doubts that this will be 100% specific to CFS, but as professor Davis said at this point it's important to demonstrate that these patients have something wrong with them.

Davis called this the last major disease we know almost nothing about. It's 2-3 as common as multiple sclerosis with worse impact on the person's life. It's also the most underfunded illness when the number of patients and the severity is taken into account.

Re: Biomarker for chronic fatigue syndrome identified

#155

Post by not_a_moth » Sun, May 05, 2019, 9:23 PM UTC

rfugger wrote: post #118

not_a_moth wrote: post #107

Since poor sleep quality is a core symptom of CFS I can't help wonder if sleep is the underlying component. I think we've all underestimated the critical nature of sleep in immune, metabolic, stress, cognitive aspects, etc. It's also hard to self-assess the quality of your sleep, eg. clock-time at each phase, central apnea events, 02 saturation, noise/ light/ movement disturbances while you are asleep, etc.

A sleep study is critical to ruling out sleep issues before getting a proper diagnosis of ME/CFS. No good doctor would diagnose CFS without a sleep study.

That could rule out apneas but not the overall possibility, based on typical sleep studies anyways. e.g. you regularly go to bed thinking about the stuff you have to do tomorrow, so your brain doesn't enter deep sleep phases for long; your doctor thinks 6-7 hours of sleep is good, when you in particular need more like 8.5 ; your neighborhood is noisy, etc.

Re: Biomarker for chronic fatigue syndrome identified

#156

Post by Someone » Sun, May 05, 2019, 9:24 PM UTC

freeradical13 wrote: post #61

L2R wrote: post #50

Earlier quoted context omitted.

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.

I see, so basically instead of intuiting a simple threshold (e.g. >X% change), they apply an SVM which is able to discover more accurate thresholds (and error ranges). Do you have any suggested resources on learning more about SVM? I guess my question comes from the observation that these advanced statistical techniques such as machine learning haven't been around for long and yet medicine has often created decision…

Learning about them: https://en.wikipedia.org/wiki/Support-vector_machine.

That will tell you SVMs are ancient (linear version dates back to 1963), and that what they do here isn’t really machine learning, but something similar to linear regression: just as linear regression finds the best (in some strict mathematical sense) line describing a set of points, this finds the best (in a similar mathematical sense) line splitting two sets of points.

For software, take a look at https://www.csie.ntu.edu.tw/~cjlin/libsvm/. Easy to use, fairly flexible, with a Java applet you can play with.

Re: Biomarker for chronic fatigue syndrome identified

#157

Post by tigershark » Sun, May 05, 2019, 9:25 PM UTC

jdietrich wrote: post #48

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 im…

Can you please explain me how can be something that happens physically in white blood cells and their plasma a psychological illness?

Re: Biomarker for chronic fatigue syndrome identified

#158

Post by rufus85 » Sun, May 05, 2019, 9:26 PM UTC

There is something akin to a daily exertion limit in CFS. When patients exceed it, they have a relapse. It is very easy to have these relapses because the exertion limit is so low.

There must be a biological mechanism behind this limitation. It could be something to do with energy generation in cells and this test may be measuring the associated impairment.

Re: Biomarker for chronic fatigue syndrome identified

#159

Post by sagebird » Sun, May 05, 2019, 9:26 PM UTC

ipunchghosts wrote: post #126

danieltillett wrote: post #3

Earlier quoted context omitted.

I have to agree with you here - the separation is too good. You just never get anything in the real world that works this well with complex diseases.

Who care is the separation is "too good." It's a lead. This is what science is. You find leads and followup on them. Lots of dead ends in the process.

You should care if it “too good” because it could be a sign of overfitting or tampering with data during analysis to reach a desired conclusion. Replication should shed some light here.

Re: Biomarker for chronic fatigue syndrome identified

#160

Post by DoreenMichele » Sun, May 05, 2019, 9:30 PM UTC

ipunchghosts wrote: post #57

Journalists, this is quite the story. Here you have a bunch of really sick patients with docs around the world saying it's in there head. Then a UK study comes out (PACE) saying patients should engage in activity to help themselves. This only makes the patients worse and eventually so bad that the study was pulled. In comes dr ron davis. His son acquired me cfs while traveling in india. Completely unsatisfied with th…

really interesting research is occurring on trypanosomes, metabolic traps, and the microbiome.

Maybe I missed something, but can you point me to some of this?

Thanks.