Search results

Hopefully this biomarker will indeed be "unique" and hopefully it will not be unique between ME/CFS patients and healthy controls only.

@forestglip Thank you ! What I am looking for is to end up with the data you described and feed them to my software framework. What I am hoping to do is to generate a pathway analysis that will help us identify the bigger picture. An example is this thread which was made possible by analysing...

@forestglip Would it be possible to share this work via Google sheets or something similar? Let me know if I can help on extracting this information

Post exertional malaise in patients of Cancer-related Fatigue ? https://pubmed.ncbi.nlm.nih.gov/32105793/

This is one of the most important threads potentially. Thank you @Yann04

Perhaps this particular run appears to output generalities ( I believe it is not) but I have seen numerous cases where LLMs are able to analyze information taking into account different conceptual levels and identifying information which was not readily available. I haven't seen a single case...

Something I like related to scepticism : "It is bad enough that so many people believe things without any evidence. What is worse is that some people have no conception of evidence and regard facts as just someone else's opinion." ~ Thomas Sowell Original tweet ...

What patients think or what researchers think about the usefulness of these tools is irrelevant really. What matters is actionable results and knowing the strengths and weaknesses of these tools . If such tools can help us connect pieces of the puzzle together then this is what counts...

I think, this is the future of medical research : I am sharing below a dialogue using a detailed prompt which integrates symptoms, findings and then asks for causal factors. During the end of the conversation I submit two hypotheses : One for "viral persistence" and one for n-linked...

Here is the answer from anthropic Claude AI. Mentioning MECFS to the Prompt biases the results: Prompt : The following have been found to be increased in a patient group. suggest causes : 1 Leptin 2 Cadherin-related family member 5 3 All-trans-retinol dehydrogenase [NAD(+)] ADH4 4...

I would like to Thank Dr Wenzhong Xiao for including me as a co-author in the paper and also point the attention of researchers to the mention of N-Linked glycosylation due to low asparagine levels. From the paper : A proposed intervention for patients was forwarded to Dr Xiao last week...

I believe this thread and poll is very important and seeing that some members have mentioned the liver, I would like to give my two cents : -Alcohol is a toxin. The liver is the organ responsible for most of detoxification that is taking place in the human body. -Regarding detoxification ...

@Chris Ponting If you are reading this, please look at the following thread on Twitter. I use a proprietary software framework since 2017 and by using the differentially expressed proteins mentioned on your paper, transferases receive a very high relevance ranking. The thread can be found here :

FWIW, machine learning has identified in the past norepinephrine and BH4 as being highly predictive. Observe also that Liver disease was identified back then @Chris Ponting . Norepinephrine (2018) BH4 (2019) :

I find it extremely disturbing and frustrating that despite extensive research we are still unable to confidently say whether ME/CFS is Post-Viral or not

@hotblack Yes, RAG would be a strategy to minimise hallucinations. I also did some work with NLP (Natural Language Processing) and Information Extraction which could help identify passages of text with specific importance when it comes to training. See an example below where NLP is used to...

All of these steps you mentioned are possible and make sense. You could also add to the system certain criteria that are needed for making sure that proper sampling took place, whether appropriate statistical tests have been used and so forth. The main concern is hallucinations of LLMs and...

This is a good idea and I have been discussing and giving some comments on some possible approaches with a PhD guy at University of Texas. We are looking at implementing a RAG (Retrieval-Augmented Segmentation) -actually this is his idea- and we were thinking of building a knowledge base in the...

One more study suggesting impaired liver function. Perhaps the time has come to perform Fibroscan tests in ME patients.

Patient mentioning enoxaparin being important in amelioration of symptoms