I have been a Zoe subscriber, and agree with what you are saying. Not only can the microbiome change from day to day, but so can glucose response curves. The scoring and "personalization" is shrouded in mystery, not transparent science. Caramelized nuts with 50% sugar are high scoring and still defended by the Zoe coaches. I can't buy into that at all.
It seems to me that all succesful 'diets' have the same thing in common. Lots of whole brains veg, fruit, nuts etc, minimal saturated fat from animal sources. This seems to be the advice on the zoe program, dressed up as personalised.
Thanks Dr N for this post and the one critiquing Zoe's recent study published in Nature. I get the points made about trial design and microbiome, but would love to know thoughts on CGM views of someone like Peter Attia who has written (on his own blog) about benefits of CGM use even for non-diabetics.
Yeah, I'm really curious to see how this field plays out. The couple papers I've looked at so far have used very clever reporting tactics or methodologies to report significance.
Further, the perception component I think should be noted: if participants know they're on some kind of unique AI/ML-based personalised diet that they invariably will have heard is 'better', this could be a confounder compared to those not on any.
I would love to read your Big data and personalized nutrition: the key evidence gaps, but it is indeed behind a paywall. I would love the pdf - how can I go about it? My email is irina.mateies@gmail.com
Given the advances in genAI (especially the creation of healthcare LLMs) what about a nutrition solution that is essentially an AI deititian? An app that generates a meal plan or helps a user balance their meal plan. Then it can go on to education. Look at what Limbic AI has achieved for therapy in the NHS.
PS - your content is so refreshingly honest and needed!
I have been a Zoe subscriber, and agree with what you are saying. Not only can the microbiome change from day to day, but so can glucose response curves. The scoring and "personalization" is shrouded in mystery, not transparent science. Caramelized nuts with 50% sugar are high scoring and still defended by the Zoe coaches. I can't buy into that at all.
It seems to me that all succesful 'diets' have the same thing in common. Lots of whole brains veg, fruit, nuts etc, minimal saturated fat from animal sources. This seems to be the advice on the zoe program, dressed up as personalised.
Thanks Dr N for this post and the one critiquing Zoe's recent study published in Nature. I get the points made about trial design and microbiome, but would love to know thoughts on CGM views of someone like Peter Attia who has written (on his own blog) about benefits of CGM use even for non-diabetics.
Yeah, I'm really curious to see how this field plays out. The couple papers I've looked at so far have used very clever reporting tactics or methodologies to report significance.
Further, the perception component I think should be noted: if participants know they're on some kind of unique AI/ML-based personalised diet that they invariably will have heard is 'better', this could be a confounder compared to those not on any.
I would love to read your Big data and personalized nutrition: the key evidence gaps, but it is indeed behind a paywall. I would love the pdf - how can I go about it? My email is irina.mateies@gmail.com
Given the advances in genAI (especially the creation of healthcare LLMs) what about a nutrition solution that is essentially an AI deititian? An app that generates a meal plan or helps a user balance their meal plan. Then it can go on to education. Look at what Limbic AI has achieved for therapy in the NHS.
PS - your content is so refreshingly honest and needed!
I love everything you do, Doc! I'm such a huge fan of your work!