Beating Smartwatch based Body Composition Analysis (using Bio impedance snalysis) approach isn't a great feat as its single point crude sensor is widely inaccurate compared to production grade multi segment multi frequency inbody machines using same technique
Google PhotoScan (~2.1 pp MAE) may put it between DXA and well performed multi site Bodyfat Caliper by an skilled operator and WAY ABOVE US Navy circumference, consumer BIA ( smart scale with handlebars), poorly performed calipers.
But i remember microsoft research paper:
>In 2022, a Microsoft Research associated team published “Smartphone camera based assessment of adiposity”. Their Visual Body Composition (VBC) system used ordinary smartphone photographs plus a CNN to predict body fat percentage against DXA. In a 134 person, two site validation cohort, it achieved 2.16 ± 1.54 percentage point mean absolute error, with concordance to DXA of CCC = 0.96.
So from 2022 to 2026, we still don't have a model which can provide benefit to people.
This can help so many people using apps which currently simply wrap Gemini Flash to detect "body fat."
Unfortunately, none of these models, code, or training data are available freely.
These companies are seriously withholding public benefit. Currently, a guy who wants to get a DXA scan has to pay $50 in the US and 1,500-4,000 INR in India.
In poor countries this DXA may not be affordable to vast majority, if models are released we can perhaps setup even a "photo booth" with better cameras and widely available sensors
Companies spend billions of dollars on charity but not where it can produce benefit to the average person; so much technical talent, yet not a single public free model. This is actually a life changing opportunity if you can get it done!
Putting this out here in case anyone with metabolic disorders may find it useful. Labcorp has a recently added blood screening, the 'Metabolic Vulnerability Index' aka MVX. This looks outside the 'standard of care' cholesterol/glucose/bp triad which typically results in managed decline to identify underlying causes of said triad.
A metabolic specialist who understands how these work is essential to the recovery process.
Some insurance companies offer something like that. It's not a discount, per se, but it is money that can go towards your medical expenses in exchange for hitting specific incentive goals.
If this gets good enough, you could imagine your phone periodically tracking body composition and combining it with wearables, bloodwork, glucose, etc. Suddenly some measurements that currently require a clinic and specialized equipment become essentially free and continuous.
...at the same time, giving Google/Apple photos of your body is creepy
I expect Apple Health to integrate this kind of cool functionality in the future. Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
> Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
You can do this by connecting to your provider already. Open Health, select the search (magnifying glass) icon, then scroll down and select "add account". If your provider is in there you can link them and see your labs in the app. With mine, the authorization to access is up to one year so it has to be renewed periodically.
I thought this wasn’t fully implemented because incompetence and lack of tech foresight in healthcare systems, or because said data providers have realized the value of this info and won’t share it at the level of 2007 Facebook users.
> Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
You shouldn't be able to. while the ability when used correctly would be very nice, there are too many scams/frauds and other abuses where that ability will be used against somebody. (maybe not you - if all you have is the same cholesterol as everybody else there isn't much gain from you - but some data is a lot more sensitive)
Beating Smartwatch based Body Composition Analysis (using Bio impedance snalysis) approach isn't a great feat as its single point crude sensor is widely inaccurate compared to production grade multi segment multi frequency inbody machines using same technique
Google PhotoScan (~2.1 pp MAE) may put it between DXA and well performed multi site Bodyfat Caliper by an skilled operator and WAY ABOVE US Navy circumference, consumer BIA ( smart scale with handlebars), poorly performed calipers.
But i remember microsoft research paper:
>In 2022, a Microsoft Research associated team published “Smartphone camera based assessment of adiposity”. Their Visual Body Composition (VBC) system used ordinary smartphone photographs plus a CNN to predict body fat percentage against DXA. In a 134 person, two site validation cohort, it achieved 2.16 ± 1.54 percentage point mean absolute error, with concordance to DXA of CCC = 0.96.
So from 2022 to 2026, we still don't have a model which can provide benefit to people.
This can help so many people using apps which currently simply wrap Gemini Flash to detect "body fat."
Unfortunately, none of these models, code, or training data are available freely.
These companies are seriously withholding public benefit. Currently, a guy who wants to get a DXA scan has to pay $50 in the US and 1,500-4,000 INR in India.
In poor countries this DXA may not be affordable to vast majority, if models are released we can perhaps setup even a "photo booth" with better cameras and widely available sensors
Companies spend billions of dollars on charity but not where it can produce benefit to the average person; so much technical talent, yet not a single public free model. This is actually a life changing opportunity if you can get it done!
Putting this out here in case anyone with metabolic disorders may find it useful. Labcorp has a recently added blood screening, the 'Metabolic Vulnerability Index' aka MVX. This looks outside the 'standard of care' cholesterol/glucose/bp triad which typically results in managed decline to identify underlying causes of said triad.
A metabolic specialist who understands how these work is essential to the recovery process.
I wonder if this could be used by insurance companies to determine premiums?
Great idea. I'd be happy to get a discount for my leanness, low RHR (resting heart rate) and daily step counts.
https://www.fepblue.org/manage-your-health/incentives-discou...
Some insurance companies offer something like that. It's not a discount, per se, but it is money that can go towards your medical expenses in exchange for hitting specific incentive goals.
Why must you tempt the insurance companies
because they ding you for high cholesterol regardless of what every other metric says.
And you think more data is going to stop them from doing that?
If this gets good enough, you could imagine your phone periodically tracking body composition and combining it with wearables, bloodwork, glucose, etc. Suddenly some measurements that currently require a clinic and specialized equipment become essentially free and continuous.
...at the same time, giving Google/Apple photos of your body is creepy
I think the reasoning is that Google/Apple already have all your photos.
I expect Apple Health to integrate this kind of cool functionality in the future. Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
> Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
You can do this by connecting to your provider already. Open Health, select the search (magnifying glass) icon, then scroll down and select "add account". If your provider is in there you can link them and see your labs in the app. With mine, the authorization to access is up to one year so it has to be renewed periodically.
is this one of those US only features?
https://en.wikipedia.org/wiki/Fast_Healthcare_Interoperabili...
They seem to be using that. So only providers whose data is accessible via FHIR.
Isn’t that what the whole HealthKit ecosystem is?
I thought this wasn’t fully implemented because incompetence and lack of tech foresight in healthcare systems, or because said data providers have realized the value of this info and won’t share it at the level of 2007 Facebook users.
> Heck, I'm not sure why I can't have it pull my labs by connecting other applications.
You shouldn't be able to. while the ability when used correctly would be very nice, there are too many scams/frauds and other abuses where that ability will be used against somebody. (maybe not you - if all you have is the same cholesterol as everybody else there isn't much gain from you - but some data is a lot more sensitive)
I’m kinda surprised Apple doesn’t do something like this. I would imagine it’s a lot easier with phones with LiDAR
Been meaning to try this myself
Google already has a product called PhotoScan.
Come on guys!
waist-to-hip ratio already took us beyond BMI, a long time ago.