methylation information by sequencing the DNA in the blood is good enough to predict age
Building an AI to predict human age from a blood sample
21–30 of 68 posts
Re: Building an AI to predict human age from a blood sample
#22When I see work like these it get me the impression that ML hype is way too real.
The goodness of the result of a machine learning model like this one should be compared with the goodness of a simple "standard" model like linear regression.
Yeah it is kinda cool that we can use 10 lines of TF to spin up huge computation, but I guess that a simple linear regression would have provide results that are at least similar to the one of the neural network.
Re: Building an AI to predict human age from a blood sample
#23>Back to the computer science: 470,000+ features sounds nice at first, but is a recipe for overfitting when we only have 700 samples at our disposal. Proceeds to use (1024^2 * 2 + 1024) parameters in the neural network.
Yeah, that's what I thought too. Interesting work nonetheless!
Re: Building an AI to predict human age from a blood sample
#24methylation information by sequencing the DNA in the blood is good enough to predict age
Is it faster/cheaper though?
Re: Building an AI to predict human age from a blood sample
#25> Therefore I first split the data into training and testing sets at a ratio of 9:1, and selected the 25 most correlated features in the training set. Each of these features had a correlation with age between 0.83 and 0.94.
> The data was then split into training and testing sets at a ratio of 9:1, and fed into a sequential neural network.
What?? I thought it was split already.
(How training and test sets were obtained sounds fairly confusing. Did the author make sure there's no "data snooping" ?)
Re: Building an AI to predict human age from a blood sample
#26>Back to the computer science: 470,000+ features sounds nice at first, but is a recipe for overfitting when we only have 700 samples at our disposal. Proceeds to use (1024^2 * 2 + 1024) parameters in the neural network.
Part of the issue is that many of the neurons in a neural network end up contributing little to the performance. This is why the practice of pruning, the removal of neurons that don't contribute much, exists [1]. Neurons can end up having so little gradient that they end up stuck (Big problem with RELU), or can end up being insignificant due to the subsequent layers weights of that neuron.
As the author is using RELU, he will have a decent number of neurons 'die'. So some 'over-provisioning' is not a bad idea in theory. Also, if my keras isn't so rusty, I think the author is using less parameters than you are stating.
Still a more reasonable dropout rate and maybe some regularization/batch normalization might help, but I would say not over fitting on only 700 samples is a hard task, even with a network much smaller than that.
I would be pretty shocked if this neural net wasn't over fit
[1]-https://towardsdatascience.com/pruning-deep-neural-network-5...
Re: Building an AI to predict human age from a blood sample
#27Re: Building an AI to predict human age from a blood sample
#28What if I transfuse blood from healthy young subjects? That was a claim from some startups, a wacky VC or two, and even a joke in the Silicon Valley HBO show. The rumor mill says this is happening at a low level.
Re: Building an AI to predict human age from a blood sample
#29For reference, the generally accepted standard for determining age from blood is the Horvath clock [1]. It seems to be accurate and only uses a penalized regression. Keep in mind this represents what your age is in reference to a "healthy" person. For example, a 50-year-old who smokes may have the equivalent practical age of a 60-year-old who doesn't. The Horvath clock is useful for evaluating lifestyle changes and your overall healthspan.
If people want to learn more about how DNA methylation relates to aging, I recommend reading Lifespan by David Sinclair.
[1] https://www.semanticscholar.org/paper/DNA-methylation-aging-...
Re: Building an AI to predict human age from a blood sample
#30For anyone interested, there's a tool http://www.aging.ai which does exactly that, using deep-learning algorithms on, and I quote, "hundreds of thousands anonymized human blood tests".
I've used it myself for fun after doing a blood test. It's a free alternative to InsideTracker's InnerAge product.