Cool, but can we not call this AI?
Building an AI to predict human age from a blood sample
41–50 of 68 posts
Re: Building an AI to predict human age from a blood sample
#42Great work! I love how well presented all of the information is. I'd be really interested to see how well a baseline linear model using those features would perform - it seems like it could do pretty well.
Hey I really appreciate it mate. I'll try and get a baseline linear model going and get back to you with the results.
Re: Building an AI to predict human age from a blood sample
#43Is the underlying concept related to 'By analyzing proteins in the blood, one can estimate a person's biological age, as well as weight, height, and hip circumference, mentioned in this article ? https://www.dailymail.co.uk/sciencetech/article-3349739/Woul...
The two concepts definitely may be related, but the approach used in this paper doesn't make use of proteins in the blood. Rather it uses the DNA methylation extracted from white blood cells in the blood.
Interesting article thanks for sharing.
Re: Building an AI to predict human age from a blood sample
#44Far-reaching prediction: they're going to do facial prediction from blood samples as well. Law enforcement really wants to generate sketches from unknown DNA found at crime scenes. That is, of course, in addition to the all-encompassing family trees we're providing them with 23andme.
Haha yeah we better watch out. Another prediction could be that blood tests will become standard when signing up for various forms of insurance.
Re: Building an AI to predict human age from a blood sample
#45What 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.
Interesting point, the idea of transfusing blood from healthy subjects had never occurred to me.
I'm not sure I understand; what was the claim from the startups, and what does the rumor mill say is happening at a low level?
Re: Building an AI to predict human age from a blood sample
#46For 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 y…
Yes the Horvath Clock seems to be the standard.
Thanks for sharing the book i'll have to sheck it out!
Re: Building an AI to predict human age from a blood sample
#47For some context, the author is an undergraduate student.
Haha yes good point take everything with a grain of salt
Re: Building an AI to predict human age from a blood sample
#48> 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 obtain…
I apologize for the confusion, i've since removed this typo.
The data is only split once, before using a correlation test to select the features that the model would be trained on. As far as I can tell there is no data snooping occurring because the data is split into train and test sets before any decision are made.
Re: Building an AI to predict human age from a blood sample
#49Looks like a beginner-level sklearn task. Linear regression would probably be ok, if not, there is random forest or a 2-layer perceptron. No use for a deep network.
I'll try out these models and get back to you with their effectiveness.
Re: Building an AI to predict human age from a blood sample
#50When 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…
that's exactly the thing I'm seeing in my field (computational materials science). Basically a simple regression model (with very simple features) brings you 90% there, still people compete on publishing (on ONE shitty benchmark dataset) ever better results – the most-cited people are using KRR, e.g. each fit uses 2TB of RAM and "days" of CPU (features of length O(1000) and 100000 samples). The sample data is probabl…
This is great if you only need 90%. But often that extra 10% is the difference between a state of the art commercially viable product and vaporware that nobody will pay for.
It’s sort of like production software in general. Sometimes the core product is pretty easy to prototype... but serving it to all your users with very high reliability and uptime is not so easy, and that’s what actually gets them to pull out the credit card.