In each of the screenshots below, the top line shows the title I provided the network with, and everything below that is the network's work. It takes around 30 seconds to generate an abstract, though it took over 24 hours of training the network to get it to this level.
-
-
Prikaži ovu nit
-
First, I tried to give it a title to a made-up randomised controlled trial. It seems a _bit_ unreasonable to compare renal denervation against apixaban for hypertension. Fasciantingly, it volunteered a clinical trial registration data at the end of the abstract.pic.twitter.com/Z9794BpgdJ
Prikaži ovu nit -
Next I gave it a title for a meta-analysis. Obviously, the title I chose is ludicrous, but I wanted to see what it did. Amazingly, it decided to put a search strategy in the methods section. It also provides relative risks, though the choice of the modified Rankin Scale...pic.twitter.com/Vjp6fhlFW2
Prikaži ovu nit -
I thought I'd try something which I have particularly little experience with: cost-effectiveness analysis. While the conclusion might be correct, I'm not sure it adequately conveys the study's findings... I do enjoy how the significance matches the p values (> vs < 0.05).pic.twitter.com/5rXlTUh8Hr
Prikaži ovu nit -
Finally, I thought I'd try something incendiary. It turns out the prevalence of narcotic use amongst adult cardiologists is 71%! And it must be true, they used eigenvectors! Sorry for the slander, my South American colleagues.pic.twitter.com/j700yVryve
Prikaži ovu nit -
What's remarkable is how "scientific" the abstracts feel. Like I said, at no stage have I told it that an abstract should have a background, or that conclusions come at the end, or that meta-analyses should provide effects sizes and literature searches. It's learnt all this.
Prikaži ovu nit -
I hope you found this interesting. I'm happy to provide more examples if people want to give me titles. I might try to get the neural network working online like I did for pacemakers (http://ppm.jph.am/ ) - though the hardware requirements for this are much steeper!
Prikaži ovu nit
Kraj razgovora
Novi razgovor -
-
-
If you trained it to write your PhD thesis would it be fair game to pass you?

-
Infarct volume, I knew we'd picked the wrong endpoint!pic.twitter.com/PDbIf6NeHo
- Još 1 odgovor
Novi razgovor -
-
-
Are the estimates true based on searches articles or are these just made up values? Fascinating
-
Good question! Hard to tell, they certainly look reasonable. Could log the ratios and see if the estimates are central. If not, probably made up!
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.