CFSME ATLAS site

Robius said:
Thanks Jonathan! As a Norwegian, I think we as a country might be behind on our official view on ME and that's partly why my science interest has grown. If the site does more harm then good I will not hesitate on pulling it down, but I want to work on it a few months and see where it ends up.
Click to expand...
Velkommen! I hope you join us.

I think that having a searchable repository of ME/CFS research that’s tagged according to inclusion criteria, topic and so on is valuable no matter what.

The thing that might do more harm than good is when claims made in papers are presented as fact when they very often don’t hold up under scrutiny. Even lots of established truths are simply false.

With LLM specifically, there’s also the issue of hallucinations etc. that might end up spreading (slightly) wrong information that requires lots of effort to catch and correct.
 
Utsikt said:
Velkommen! I hope you join us.

I think that having a searchable repository of ME/CFS research that’s tagged according to inclusion criteria, topic and so on is valuable no matter what.

The thing that might do more harm than good is when claims made in papers are presented as fact when they very often don’t hold up under scrutiny. Even lots of established truths are simply false.

With LLM specifically, there’s also the issue of hallucinations etc. that might end up spreading (slightly) wrong information that requires lots of effort to catch and correct.
Click to expand...
 
Trish said:
Me too. I've split it in the thread title.
Click to expand...
I agree. Looking back, I was testing things and chose the name a bit too quickly. I may be able to change it later if people seem to find the site genuinely useful.
I am paying for it myself. I can manage that, but probably not for long if the site is not good enough to justify it. Still, I think we are not far from a point where systems like this will be able to do this extremely well with the right setup.

For now, I see this as version 0.1. Perhaps the right setup could eventually be developed in a group like this. I would be happy to build it.
I could share the setup I have today here, if that would be useful, and people could then give their input. It may be that this version is good enough to refine and harden, or it may be that a fresh start would be better.
 
Peter T said:
A bit of a tangent, but I am struggling to read the name as intended. I struggle not to see it as CFS-meat-las. The misreading as the word ‘meat’ tends to override for me other interpretations.

Increasingly ME/CFS is being used. It may be others do not have this problem, but personally I would find MECFSAtlas a clearer format.
Click to expand...
Agree.. was reading MEAT, and MECFSAtlas would be better!

Good to see the effort and welcome to forum! Best of luck w the project..
 
Robius said:
That said, I think some of the criticism here is fair and useful. In particular, questions about trust, review depth, classification quality, PEM tagging, and the exact role of AI in summarisation and structuring are legitimate. I do not take those objections lightly. If anything, they point to the areas that need to become stricter, more transparent, and more editorially legible. My intention is not to let machine-generated structure masquerade as scientific certainty. The intention is to build a system that can become more robust over time, with clearer distinctions between machine-assisted processing, human review, and authored synthesis.
Click to expand...
Hi and welcome. Don't be put off by the criticism, it's what we do here, and it's all meant in a constructive way. Brief and direct aren't meant to be rude, some of us struggle a lot with brain fog and sometimes that gets confused as a bit mean. As you have noticed over the years, the literature on ME/CFS is a mess and so with that comes a lot of repetitive criticism. It's not always easy but we have seen a lot, and always try to make other people's projects better for it if they are willing.

I think this project is something that could be useful, and opinions vary among forum members on the usefulness of AI to achieve this, but what matters most here is that AI is not a fixed thing, it will get better, and having a strong foundation for this can become very useful over time.

I hope you stick around. This forum has many goals, from simply being a support community (no medical advice, though) to being hopelessly annoyed at the low quality of research and the lost opportunity that LC has represented. There isn't a more rigorous community dedicated to improving the science of ME/CFS out there, at least not that we are aware of.
 
Robius said:
Thanks Jonathan! As a Norwegian, I think we as a country might be behind on our official view on ME and that's partly why my science interest has grown. If the site does more harm then good I will not hesitate on pulling it down, but I want to work on it a few months and see where it ends up.
Click to expand...
By the way, there are several threads relevant to Norway, if you haven't found them yet. Several things going on right now, with a guidelines project that isn't doing great, a disability law case that rendered a verdict recently involving, somehow, the head of Norwegian medical research, and quite a lot going back years.

Many of them can be found by searching for Norway, and we have regional threads that sum up things happening in either one or a few country, lumped up in Scandinavia here: https://www.s4me.info/threads/news-from-scandinavia.647/.
 
You must log in or register to reply here.
Back
Top Bottom