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

61–70 of 228 posts

Re: Biomarker for chronic fatigue syndrome identified

#61

Post by freeradical13 »

L2R wrote: post #50
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.

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 boundaries, presumably just looking at the data and making a reasonable cutoff. Is all the extra effort in a case like this worth the time investment?

Re: Biomarker for chronic fatigue syndrome identified

#62

Post by GordonS »

NautilusWave wrote: post #44

This biomarker seems incredibly general; I suspect people with certain presentations of a mitochondrial disease would have the same biomarker.

Agreed, but it's still great to have evidence of a physical condition, as many CFS patients have been made to feel like crackpots at some point, and indeed some doctors use it as a convenient label for people they believe to be mentally ill.

Of course, this also raises a question about how those with mental illness are often treated.

Re: Biomarker for chronic fatigue syndrome identified

#64

Post by thrrrrrway »

I had CFS like symptoms so bad I was stuck in bed for several years and the doctor basically would not help me. Eventually I decided to treat it myself with antibiotics and anti parasitic medication. I basically came to the conclusion that for my specific case I had an unknown blood parasite and the fatigue was being caused by neurotoxins. I don't think all CFS are caused by an infection but mine definitely was and I have my life back. If you a researcher looking for a cure, try to test medications that flush neurotoxins out to see if the disease goes away and then try figuring out what is creating them in the first place to treat them.

Re: Biomarker for chronic fatigue syndrome identified

#65

Post by erentz »

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…

> The leading hypothesis remains that chronic fatigue syndrome is a mental illness.

According to who? At least in the USA I see no evidence of that. The research is all pointing towards dysautonomia, dysimmunity, and metabolic issues.

Re: Biomarker for chronic fatigue syndrome identified

#66

Post by verroq »

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…

SVMs are as old school ML as they get. They guarentee the maximum separation at the decision boundary. However it doesn’t scale very well for higher dimensional data. The standard used to be to use some dimensionality reduction technique like PCA to preprocess before feeding it into the SVM.

This is all before deep learning.

Re: Biomarker for chronic fatigue syndrome identified

#67

Post by heavenlyblue »

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…

>> This folks is how science is supposed to unfold and it all happening right in front of our eyes for everyone to see in real time. Quite astonishing.

So you imply that only scientists with money and direct personal interest in the research are supposed to work on the given topic?

Re: Biomarker for chronic fatigue syndrome identified

#68

Post by cpncrunch »

GordonS wrote: post #53
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…

I don't think CFS is a mental illness, and I haven't seen evidence that that's the "leading hypothesis" (I've been diagnosed with CFS, although that was before I was later diagnosed with nerve damage), so this is something I've read deeply on. CFS can absolutely cause mental illness though - constant fatigue, and sometimes pain, can take a terrible toll.

The evidence shows that CFS is triggered by stress or viral infections (which are physiologically stressful), and that it is associated with dysruptions to the HPA axis.

Everyone I know who has recovered (including myself) has said that dealing with psychological issues is the most important factor in recovering.

Re: Biomarker for chronic fatigue syndrome identified

#69

Post by AdamCraven »

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.

As someone who has suffered from CFS for a long time, it is definitely not imaginary.

To say it’s purely physical is discounting the mental aspect of the disease. I personally suffered trauma as a child and I’ve seen first hand what strong negative emotions can do to the body.

I would think it unlikely that there will be a miracle drug that will cure it, I believe it is a disease of both the mental and physical.

For anyone affected by CFS and think that trauma may play a part, the book “The Body Keeps the Score” has helped me get more energy and control back.

Re: Biomarker for chronic fatigue syndrome identified

#70

Post by cpncrunch »

erentz wrote: post #65
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…

> The leading hypothesis remains that chronic fatigue syndrome is a mental illness. According to who? At least in the USA I see no evidence of that. The research is all pointing towards dysautonomia, dysimmunity, and metabolic issues.

Those are all well known to be significantly influenced by stress, and all the evidence is pointing towards the stress system being central to CFS.
Post reply on HN