'AI' extracts new knowledge from old science papers

Marco

Marco

Senior Member (Voting Rights)
In the domain of thermoelectric materials only for the time being but this machine learning program was able to 'predict' later findings from older papers :

https://www.zerohedge.com/news/2019...ntific-papers-makes-discoveries-missed-humans

But in principle the approach could be extended to other areas :

"This algorithm is unsupervised and it builds its own connections," said the study's lead author, Vahe Tshitoyan, adding "You could use this for things like medical research or drug discovery. The information is out there. We just haven’t made these connections yet because you can’t read every article."
Click to expand...

I doubt there is enough good science around ME/CFS for this approach to be directly useful but advances in understanding the immune system; metabolimics; the central nervous system etc may be relevant.

Original paper abstract : https://www.nature.com/articles/s41586-019-1335-8
 
Andy said:
I'm sure @mariovitali would support the message from this paper.
Click to expand...

I will say it depends @Andy.

We do not want to be employing AI methods for the sake of it or because it is a buzzword. We need tangible results and thus prove that this technology outperforms other approaches.


I do agree with the paper in the sense that this technology can be used for medical research. However we have to make sure that the data is of good or sufficient quality and also to make "reality checks" very often to identify whether the software works as expected or not.

I was really happy to see that AI and Network Analysis was mentioned in the NIH conference but also in SolveCFS where Machine Learning and AI are discussed as technologies that "could help move the needle". It remains to be seen if this will be indeed the case.
 
Forbin said:
The AI's going to be pretty frustrated when it gets to the PACE trial.
Click to expand...
E X C E P T I O N F O U N D

W E H A V E L O S T I N T E L L I G E N C E
intelligence.jpg
 
Thought this would be best here rather than on a new thread.
Carl Malamud is on a crusade to liberate information locked up behind paywalls — and his campaigns have scored many victories. He has spent decades publishing copyrighted legal documents, from building codes to court records, and then arguing that such texts represent public-domain law that ought to be available to any citizen online. Sometimes, he has won those arguments in court. Now, the 60-year-old American technologist is turning his sights on a new objective: freeing paywalled scientific literature. And he thinks he has a legal way to do it.

Over the past year, Malamud has — without asking publishers — teamed up with Indian researchers to build a gigantic store of text and images extracted from 73 million journal articles dating from 1847 up to the present day. The cache, which is still being created, will be kept on a 576-terabyte storage facility at Jawaharlal Nehru University (JNU) in New Delhi. “This is not every journal article ever written, but it’s a lot,” Malamud says. It’s comparable to the size of the core collection in the Web of Science database, for instance. Malamud and his JNU collaborator, bioinformatician Andrew Lynn, call their facility the JNU data depot.
Click to expand...
www.nature.com/articles/d41586-019-02142-1
 
Andy said:
Thought this would be best here rather than on a new thread.

www.nature.com/articles/d41586-019-02142-1
Click to expand...
From projects like this I'm really looking forward for an evaluation of the entire body of psychosomatic medical research to show how, other than terminology, it still parrots the exact same tropes as a full century ago, unchanged and just as hollow. The phrasing may be different but the substance is exactly the same. It will be pretty illuminating.

Especially with the recent rise of FND as a shiny new thing despite the fact that it dates back at least as far as a century ago, in the exact same form (whatever form warm air can take anyway). Same with BPS that is simply a rebranding of the early psychosocial model and simply added baked-in deceit.

Same manure. Same rear ends. However you bottle it, whatever comes out is just as toxic. Although at least actual manure is useful, unlike the tripes it came from.
 
The cache, which is still being created, will be kept on a 576-terabyte storage facility at Jawaharlal Nehru University (JNU) in New Delhi.
Click to expand...

Or... just buy 72 of these 8TB hard drives for $120 a piece and create your own 576TB storage facility for about $8,600. :)

upload_2019-7-18_12-44-0.jpeg
 
You must log in or register to reply here.
Back
Top Bottom