Discovery Forum 2017: Dr. Nancy Klimas

[FMMM1]

Nice catch @FMMM1!

Took another look at Xiao's 2017 presentation (14:20 on the video) where he presents a gene expression chart:

Up front he said it was "preliminary" data, so wonder if during the past year they did further analysis? Sleeping sickness is on the chart just further down the list.

Xiao is among speakers @BenH just posted for this year's Symposium. Looking forward to his presentation.

And wondering if Nancy Klimas' findings complement these?

The fact that there's a drug for sleeping sickness (Suramin) makes that even more interesting. I.e. you can test whether ME/CFS will respond to Suramin.

I hope my previous comment doesn't put anyone off participating in this forum.

 

[Belbyr]

Funny how suramin seemed to help Autism in a small study

 

[used_to_race]

Is this paving the way for ML applications in ME/CFS? Is there a way to connect with ML researchers who might be interested in applying it to treatments like rituximab or working with ME/CFS research centers?

I wouldn't be able to say. It seems like a good place to apply ML research, especially the clustering techniques that may be able to help us understand the heterogeneity of the condition. The issue as always is funding. And while research in software is comparatively cheap (after the data has been collected), the way grant approvals work deters most of the best researchers from going into the field of ME/CFS research. People would rather study conditions for which funding is more plentiful. In a few years I think this will begin to change, maybe sooner.

 

[Gemini]

It seems like a good place to apply ML research, especially the clustering techniques that may be able to help us understand the heterogeneity of the condition.

After reading your earlier post about them @used_to_race I wondered if Klimas would have to do some form of clustering classifying to select patients for the treatment trial she outlines on this video to reset homeostasis?

Is there a possibility software companies that develop ML applications would see an opportunity here if they were told about it, or is it too early for them do you think?

 

[used_to_race]

After reading your earlier post about them @used_to_race I wondered if Klimas would have to do some form of clustering classifying to select patients for the treatment trial she outlines on this video to reset homeostasis?

Yes I would think this could be helpful to figure out which data points are significant and which aren't. The nice thing about having a large dataset is that you don't have to use all of it. However, "cleaning" your data is a huge part of the process and this is really difficult for a group like ME/CFS patients who likely have different diseases or are misdiagnosed. I'd like to see a paper that tries to do clustering on separate, more well-understood diseases, such as Crohn's vs. UC or Rheumatoid Arthritis vs. Osteoarthritis. I saw a paper that showed ANA positivity could help predict joint involvement in Juvenile Idiopathic Arthritis, and that's the kind of analysis that needs to be done.

Is there a possibility software companies that develop ML applications would see an opportunity here if they were told about it, or is it too early for them do you think?

It's tricky because the companies that stand to benefit financially from ME/CFS treatment are probably drug companies. I would imagine the big pharma companies have some ML/AI involvement but I don't know a lot about it; it's probably nothing compared to a Google or an Amazon.

 

[junkcrap50]

Big news from Cort about Klimas's study for ME/CFS based on her predictive modeling.
https://www.healthrising.org/blog/2...tisite-klimas-reset-chronic-fatigue-syndrome/

At least one major disease group thinks Dr. Klimas has struck gold with her approach [using computational biology modeling]. The Parkinson’s Foundation is apparently so excited at the possibilities of computational biology that they wanted to transport her and her entire team into Parkinson’s research. When that thankfully failed, they gave her a nice, big budget to get access to the computational modeling platform and train another team how to use it.

(The Parkinson’s effort will use the Institute’s modeling platform to understand the dynamics of the central nervous system in producing the disease. Studies are already underway using mouse models (Parkinson’s has a couple of them) to improve the current model.)

In return, she asked the Foundation to fund a 20-person ME/CFS trial. That trial is expected to begin this fall. It will include post-menopausal women and use the same drug combination (etanercept and mifepristone) used in the GWI trial.

The participants will do an exercise test – then take down inflammation using etanercept for a month and then rebalance the hormonal system using mifepristone. If the model is correct, the treatment combination will push ME/CFS patients’ systems back to health.

The Gulf War Illness trial started earlier this year. I don’t know the results. The ME/CFS trial should either have started by now or be beginning shortly. (It’s already filled up.)