2min snip

The Joe Cohen Show cover image

How To Reduce Your Pace Of Aging: Understanding Longevity and Biological Aging with Ryan Smith

The Joe Cohen Show

NOTE

Comparing Blood-Based and Methylation-Based Algorithms for Age Prediction

The true age is more accurately predicted as a standalone, but let's talk about the exciting work of Morgan Levin in the field of epigenetics. She developed an algorithm using nine blood-based biomarkers and chronological age to predict biological age. She then trained DNA methylation to improve the accuracy of the predictions. Our publication shows that we created a blood-based algorithm that is 17% more predictive than Fino Age, using a larger group of 60,000 individuals. This demonstrates that including more data points improves age prediction. Aging is complex and variable, but with the right markers, accurate predictions can still be made.

00:00
Speaker 1
Yeah. So, so the answer is that the true age is more predicted as a standalone, but I love to talk about this because so Morgan Levin, you're absolutely right. She, her history is actually in this epigenetic space and she's probably one of the most exciting epigenetic researchers in this space, definitely an idol of mine. She started actually with Steve Horvath, who was the creator of these first clocks as a postdoc. Then she went to Yale and in that process, if her postdoc created this algorithm you're mentioning where she used nine blood-based biomarkers and then also chronological age as a feature to predict biological age. And she created first the score from just the blood-based biomarkers, but then she actually trained DNA methylation to predict that score that she got from the biomarkers. And so whenever we can talk about this, we can talk about both, one is a blood-based algorithm, the other one is a methylation-based algorithm, but they're based on that same data set. And so we actually in our only case publication have showed that we actually created a 17 blood-based biomarker that's around 17 times more predictive, or sorry, 17 percent more predictive than then Fino Age. So it uses a few more markers, but we trained it in a much larger group. Fino Age was changed in around 2000 individuals. We trained ours in 60,000 individuals. And we started with 61 biomarkers in blood, narrowed it down to 17 to create the most predictive algorithm, and it's 17 more predictive and more predictive. And so it goes to show you two things, I think. One is that you can still create amazing biomarkers of age prediction with just blood-based markers. But again, the more resolution, the more data points you can include into a model, the better your prediction is. And that's again, just because aging is so complex and so different and variable in everyone.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode