I’m looking forward to hearing about Google’s new XR smart glasses at Google IO today (I’ll be watching from here: https://www.youtube.com/watch?v=wYSncx9zLIU ). This could be a game-changer for people wishing to optimize their health. e.g. imagine going to the grocery store and before you buy something it immediately highlights items that are probably not the best for your health (with a red x) and points out ones for which there is some evidence that it helps. Or, imagine you go to a cafe and order something and immediately see nutritional content (better than dedicated apps for this on a smartphone, since the glasses would have access to the whole context – what cafe you are in, what ingredients they list online, etc.) in the AR window. Couple that with Android’s new fitness-trackers and you could get personalized recommendations.
Interesting. I’ve looked at Hero before. My concern is that it’s designed for medications, not supplements. I take 8 different things daily and Hero doesn’t really support that workflow. Curious if anyone here has actually used it for a complex supplement stack?
Clinical trial flaws ‘being scaled, not solved’ by AI: report
https://www.fiercebiotech.com/cro/flaws-are-being-scaled-not-solved-ai-clinical-trials-report
The Wearable Showdown: Oura Ring 5 vs. Fitbit Air vs. Whoop MG vs. Apple Watch (WSJ)
Our columnist tests out the latest fitness trackers for your wrist, finger and elsewhere, with a focus on sleep monitoring and heart-rate accuracy
The next morning, I reviewed my results with Dr. Rafael Pelayo, a clinical professor of sleep medicine, who says a restorative night includes a mix of different stages: deep, REM (aka rapid eye movement) and lighter sleep, plus several micro-awakenings.
A sleep technician looked at my brain waves, muscle activity, eye movements and snoring audio to determine the stages. Even though the wearables can only infer the stages, using heart rate and movement data, they kept up pretty well.
The Apple Watch clocked the same sleep duration, down to the minute (six hours and 52 minutes) and its sleep staging aligned most with the lab results. The Fitbit Air was a close second, followed by Oura.
The Whoop tripped up early, mistaking my late-night reading for light sleep. Emily Capodilupo, senior vice president of research at Whoop, says its sleep algorithms have been validated against polysomnography, and peer-reviewed studies found its sleep detection reliable.
Read the full story: The Wearable Showdown: Oura Ring 5 vs. Fitbit Air vs. Whoop MG vs. Apple Watch (WSJ)
Wearables, and the flood of data they generate, inch closer to entering the clinic
Oura, Whoop to connect users to clinicians virtually for possible diagnosis and treatment
I tried this new body scanner at a gym recently called the Evolt360. Unsure how accurate it is.
Here is the reading I got minus some personal/identifying data:
I’d argue this is somewhat accurate but not perfect.
Two Stanford grads raise $11M to build a noninvasive wearable for hormone tracking
Through its wearable, Clair Health said it’s able to determine what is causing hormones to change and how the body responds to those changes by evaluating the biomarkers picked up by its sensors. It also continuously monitors changes through the four phases of a menstruation cycle and doesn’t just rely on the day of menstruation. Through these markers, the app shows information about the pace of aging, inflammation and bloating, and the rate of perceived exertion.
Clair Health also wants to help women seeking care for menopause and perimenopause by providing more data to share with healthcare providers, allowing them to receive better support rather than orally recounting their symptoms.
This looks intriguing…
Midjourney goes from generating cat images to full-body ultrasound scans
The AI image generator says this side project will be ‘in many ways superior to even MRI machines.’
Midjourney CEO David Holz just showed off the company’s first hardware product and plans to build a San Francisco spa, which he admitted is a bit different from the “cat pictures” produced by its AI image generator. Dubbed The Midjourney Scanner, it’s an ultrasound-based full-body scanner that uses a ring of sensors to capture vertical slices of the inside of your body, looking at the composition of your muscle, fat, bone, and organs to start. Holz said ideally, you could do this once a year or every single day, as it “aims for image quality comparable to MRI in many ways.”
He mentioned that one way he’d like to use it would be to see how his body changes in response to diet and workout changes, saying, “I’m not the most measured man on Earth yet, you know, but maybe I want to have that daily [measurable information]. A set of job listings advertises the company’s goal as trying to “build and launch the world’s first full-body ultrasound CT scanner, ultimately bringing safe, fast, and high fidelity preventative scanning to billions via a magical spa experience.”
The Midjourney Scanner was developed in a partnership with ultrasound tech company Butterfly Network, which said it uses “40 Butterfly Ultrasound-on-Chip™ imaging modules per system.”
Read the full story (Verge): Midjourney goes from generating cat images to full-body ultrasound scans
Midjourney Medical
We’re a new division of Midjourney focused on a radical new vision for healthcare using a totally new form of medical imaging we call “Ultrasonic CT” or simply “the full body ultrasound”.
Ultrasonic CT lets us aim for whole-body imaging that’s in many ways superior to even MRI machines, but the scan takes as little as 60 seconds.
There is no radiation, no powerful magnetic fields - just sound and water and 60 seconds.
Our goal at Midjourney Medical is to deploy around 50,000 of these scanners around the world over the next 6 years and use this fleet of sensors to do a billion full-body scans every month.
Our first location will be in San Francisco and will open at the end of 2027.
The center itself is a flagship health spa we are calling the"Midjourney Spa." It will have hot tubs, saunas, cold plunges and10 scanners with the capability to do more body scans a year than all MRI scanners on Earth combined.
https://www.midjourney.com/medical
https://www.midjourney.com/medical/blogpost
https://www.midjourney.com/medical/scan_gallery
A research paper on the technology:
THe preprint (available to read): Whole-Body Human Ultrasound Tomography - PMC
The final paywalled article:
https://www.nature.com/articles/s41551-026-01660-4
And an evaluation of the idea, using: https://paperclip.gxl.ai/
GXL Paperclip-midjourney-whole-body-ultrasound-evaluation.pdf (195.9 KB)
ordered one of these last week 
The Red Light Therapy Bag - not the mat
Figured if I was going to lay on something for 10 minutes getting both sides done at the same time would eventually pay off LoL! every 6 sessions I save an hour
For sure not perfect but should indicate trends.
I had Perplexity compare this dual frequency BIA, 8 lead scale to the Renpho Morpho BIA dual frequency, 8 lead scale. They both use the same frequency pair of 20 kHz and 100 kHz. It looks to me like the only significant technical difference (besides price) are the possibility of sensor accuracy, and user error.
The Evolt has more reports (algos) on body comp variations than the Renpho, as it is more clinic oriented. This would be where you would want to increase revenue by pointing out small issues the clinic is selling a product or service to solve.
Then they should come up with a new technical term instead of recycling a very well defined term used exclusively for an x-ray system.
You could still use the Tomography part -
Short answer: In medicine, “computed tomography (CT)” is defined as an imaging modality that uses X‑rays plus computer processing to reconstruct tomographic (slice) images, and then often 3D volumes, from multiple projections. That term is not normally applied to arbitrary technologies that simply “combine a group of scans into one image” unless they are tomographic reconstructions, and outside of X‑ray it is conventional to qualify it (e.g., “optical coherence tomography,” “photoacoustic tomography”) rather than just calling it CT
CT scan.pdf (441.4 KB)
From the new Y combinator batch of companies:
Adialante
What it’s building: Mobile MRI clinics for early cancer detection
Why it’s a fav: We know early detection saves lives, but the healthcare system doesn’t have enough MRI machines to screen everyone regularly. They are just too expensive — costing millions to buy and tens of thousands a year to maintain. Adialante is trying to solve this problem. The startup says it has designed a compact MRI unit that can be transported in a small truck. Adialante’s business model is to bring these machines to clinics and charge $250 a scan. The company’s massive but worthwhile ambition is to change MRI scans from being reserved for symptomatic patients into a routine annual screening.
source: The 11 standout startups from YC's Demo Day, according to VCs | TechCrunch
Just heard of a guy using GHK-Cu peptide in an insulin pump so it is continuously dosed lol.
So, I asked Gemini: (note: the response is much longer, this is just a short summary).
What is the scientific and clinical evidence that a selective GalR1 antagonist would be helpful in Alzheimers?
Response:
The therapeutic rationale for deploying a selective Galanin Receptor 1 (GalR1) antagonist in Alzheimer’s disease (AD) centers on a long-standing mechanistic paradox in geroscience: the dramatic hypertrophy and hyper-innervation of galaninergic fibers surrounding surviving cholinergic basal forebrain (CBF) neurons in late-stage AD (Counts et al., 2008).
While early hypotheses debated whether this galanin overexpression is purely neuroprotective or neurodestructive, preclinical and mechanistic evidence strongly indicates that signaling through the GalR1 subtype actively drives cognitive deficits by crushing cholinergic transmission .
I own this device and reached an identical conclusion. Another reason why the subscription value is lacking is the lack of multi user support (for families). The machine (and app) assume all the readings are for the same person.
Breaking news for people who want to look hot, be young and not die. A few years ago, two college dropouts told me they could accelerate longevity by building a faster AI chip. I invested, and they just pulled it off.
What it means:10x more throughput (tokens per second) for the same power footprint
Dramatically lower operational costs for executing today’s frontier models
Run far larger, more capable AI models within the same power and thermal budget, because a transformer-specific chip spends a fraction of the energy per token that a general-purpose GPU does
Rob and Gavin’s approach resonated with me because solving aging is a gigantic combinatorial search problem. The chemical space of small, drug-like molecules has around 10^60 possibilities.
These compounds need to be mapped against a human proteome derived from 20,000 genes, including 1,600 transcription factors, and a dense web of interactions among them. The size of the combinatorial space is problematic. You need to identify which targets to modulate, within specific cellular lineages, at exact dosages, and in optimal temporal sequences. Traditional high precision physics simulations are too slow to brute force the problem. You can shortcut it with AI inference, using frontier neural networks as hyper fast surrogate models to predict biological interactions instantly. By hardwiring transformer logic into silicon, Etched offers the infrastructure needed to run these massive biological foundation models at scale. I’m surprised and impressed they were able to pull this off, and so quickly.
They already have $1B in orders