cross-posted from: https://programming.dev/post/37623211
- Researchers have developed an AI model that estimates long-term disease risk across more than 1,000 medical conditions
- The model, trained and tested on anonymised medical data from the UK and Denmark, can forecast health outcomes over a decade in advance
- While not ready for direct clinical use, the AI model offers new ways to study disease and inform healthcare strategies
Weak. I can predict the future TWO decades in advance. I have this origami thing that I use
“can” and not “could”? you haven’t had a chance to test it yet but already claim to have invented a machine that can predict the future a decade in advance? it better be the journalists that picked that word because if the scientists are saying that, then their funding would do better somewhere else
A systematic assessment on data from the UK Biobank not used for training showed that these calculated risks correspond well to the observed number of cases across age and sex groups.
This, for instance, is a test.
sure maybe it was tested with data already known to the researchers, but that’s not a real world test, that’s still a fully controlled environment. and the researchers, being human, aren’t perfect, the data about what the AI was meant to predict could’ve slipped into the training data. using historic data to predict slightly less historic data is a good first step, and it’s of course exciting! but we’re not done here
nobody can read AI code after its been trained, so until all possibility of human error can be fully disspelled by continuous testing it in real time and having the AI actually predict events that come to be - it’s a could, not a can.
And we know its forecasts will be very accurate, because we also looked into our crystal ball that tells us the actual future and both showed very similar outcomes. /s
deleted by creator
