Clinical Partner Kit · Sample v0.2
Using Prism body scans in clinical care
A practitioner's guide to what a Prism scan measures, where each number comes from, how far to trust it, and how to get a scan worth interpreting. Written for the people who read results with patients, not for engineers.
Module 1
Quick reference
The one page to keep next to you during a consult. Everything here is expanded in the modules that follow.
The numbers to use
Benchmarked against DXA: within about 3.5 points on average, and more repeatable than DXA itself. Use the value.
Read straight off the 3D model, as close as a trained tape measurer. Under 0.5 is the common target.
The number to watch during weight loss: some lean loss is normal, but fat should fall much faster.
Estimated from body shape, calibrated to DXA. A strong cardiometabolic risk indicator.
Trust a scan when
- The patient wore minimal clothing, or fitted gym wear
- They wore the same type of clothing as at baseline (minimal, or fitted)
- They weighed themselves just before scanning
- The change holds across two or more scans
Discount a scan when
- Clothing was loose or bulky, or a different type from baseline
- Weight wasn't updated
- A single scan jumps against the trend
What to tell patients
- "Your scan is benchmarked against DXA, the clinical reference for body composition."
- "Each scan is useful on its own. Over weeks, it tells us even more."
- "Scan in the same type of clothing, at the same time of day, after weighing yourself."
If a result looks off
Module 2
How a scan works
A patient turns once in front of their phone. Prism's body foundation model reads the video and estimates their body composition and 3D body shape directly from the images.
Capture
About 10 seconds of video. The patient turns 360° in an A-pose, phone at waist height.
Foundation model
Prism's body foundation model reads the frames directly: the body's shape and its surface, skin included.
Estimate
The same model estimates the metrics, from body-fat % to visceral fat and lean mass, trained and validated against DXA.
3D body
It also estimates the body's shape, and the 3D model is built from it. Circumferences are read off it at fixed landmarks.
Report
Values, health bands, and percentiles against population data by age and sex.
The one idea to remember
Almost every number in the report comes from one body-fat estimate. Once body-fat % is known, fat mass, lean mass and muscle follow by arithmetic. Get the scan right and everything downstream is right. Get it wrong (loose clothing, old weight) and every number shifts together.
What the models need from the patient
- Body shape and surface, read from the scan. Ideally as much visible skin as possible: the model reads the skin surface, not just the outline. Clothing that hides the body makes it look bigger than it is.
- Current weight, entered before every scan. Every mass value is a share of this weight.
- Sex, age and height, set once. Health bands and percentiles depend on sex and age.
Module 3
Where the numbers come from
For each metric: what it's built from, what moves it most, and how much weight to give it. The bars show how strongly each input drives the result, relative to the strongest one.
Waist circumference and waist-to-height ratio
MEASUREDRead directly off the 3D model, not estimated. No model sits between the scan and the number. It's also the strongest input to body-fat % and visceral fat.
- Waist is the high waist, just above the navel.
- Stomach (low waist) is the widest point around the navel.
- Waist-to-height ratio is waist divided by height. Under 0.5 is the common target.
- The landmark is placed by the model the same way on every scan. Tape measurements vary with where the tape sits and how tight it's pulled.
Body-fat %
ESTIMATEDA model trained against DXA. It combines two views of the body: one driven by trunk shape relative to height, one anchored to BMI.
Trunk girth (waist, stomach, hips) carries the most weight. When trunk girths rise together, which is what real fat gain looks like, the estimate moves strongly.
| Band | Men | Women |
|---|---|---|
| Minimum | 5 to 10% | 13 to 18% |
| Healthy | 10 to 20% | 18 to 28% |
| High | 20 to 25% | 28 to 32% |
| Very high | 25% and above | 32% and above |
Bands adapted from ACE and ACSM guidelines.
Visceral fat
ESTIMATEDFat around the organs, more closely tied to cardiometabolic risk than total fat. Estimated from body-shape ratios and body-fat %, calibrated to DXA. It is not a CT or MRI measurement.
91
100
·
11
7
Bars are relative to the strongest input for each sex. A dot means the input isn't used.
In women, waist dominates. In men, the model reads the contrast between stomach and waist: a belly that protrudes below the waist line pushes the estimate up.
Fat mass and lean mass
ESTIMATEDA direct split of body weight. No second model.
Lean mass = weight minus fat mass (muscle, water, organs, bone)
Both inherit the accuracy of body-fat %, and both depend on the weight entered that day. For weight-loss programs, lean mass is the number to watch: some lean loss is normal, and the outcome you want is fat falling much faster than lean mass.
Limb lean mass and skeletal muscle
ESTIMATEDAppendicular lean mass (arms and legs) is predicted from body-fat %, BMI and body roundness, trained on DXA. Skeletal muscle mass is then a near-linear function of it.
Body roundness index (BRI) describes how round, rather than tall and narrow, the body is, using waist and height. Two people with the same BMI can have very different BRI.
Reported in kg, and as an index (mass ÷ height²) with a low, healthy or high category and an age and sex percentile. Muscle here is inferred from body shape and fat, not imaged directly.
Metabolic age
DERIVEDBody-fat % translated into an age: the average age of people in a ~20,000-person US population survey (NHANES) with similar body fat.
A communication device, not an independent biomarker. It makes adiposity easier for patients to relate to. The underlying signal is body-fat % and its percentile. The display is capped at 15 years either side of real age.
BMR and daily energy needs
DERIVEDResting energy expenditure estimated from lean mass, then scaled to a daily total at a sedentary activity level.
Intentionally basic: a sensible starting point, not an indirect calorimetry result. Calorie recommendations never go below 1,200 kcal a day.
Module 4
How accurate it is
Two questions matter clinically. Is the number close to the reference method (accuracy)? And does it give the same answer twice (repeatability)? For tracking a patient over time, repeatability matters most.
Waist circumference
vs a multi-camera 3D body scanner · n = 78
As close to the reference as a trained tape measurer. On a 100 cm waist, repeat scans agree to within about 0.6 cm.
Body-fat %
vs DXA · n = 271
On average within about 3.5 points of DXA, close enough to use the value in a consult. And repeat Prism scans agree far more closely than repeat DXA scans, so it's also very good at tracking change.
Visceral fat
vs DXA · n = 226
Very stable from scan to scan, so a sustained change in direction is meaningful.
Limb lean mass
vs DXA · n = 185
Good for direction of travel during weight loss. For a muscle-loss question that needs an exact value, DXA remains the reference.
Group figures, not guarantees
Accuracy is an average across a study population. An individual patient can sit further from DXA than the average.
The same on any phone
Results are consistent across current iPhone and Android devices, so patients don't need special hardware.
Every method has error
DXA, BIA and tape all disagree with each other. Pick one method per patient and track it, rather than comparing numbers across methods.
Module 5
Where it works, where it fails
Every body composition method has blind spots. These are Prism's, with what you'll see in the results and what to do about it.
Works best for
Adults with overweight or obesity tracking change over a weight-management program. That's the population and use case the models were built and validated on.
Hardest for
Bodies far from the average shape: very muscular builds, very lean people, and people with low muscle at a normal weight. Their measurements (waist, hips, every circumference) stay accurate. It's the body composition estimates built from them that need more caution.
Loose or bulky clothing
The scan measures the outer outline. Fabric adds centimetres.
Body-fat % too high, lean mass too low.
Ask for a rescan in minimal clothing or fitted gym wear.
Clothing type changes between scans
The most common trap. Patients often start in looser clothing and switch to fitted or minimal clothing later.
Body-fat % falling faster than real change, and lean mass that looks better preserved than it is.
Agree the clothing type at baseline (minimal, or fitted). It doesn't need to be the same outfit. If the type changes, treat the next scan as a new baseline.
Weight not updated
Every mass value is a share of the weight entered.
Body composition that doesn't fit the change. If the patient lost weight but the old weight was entered, the scan sees the smaller body but splits the old total, so fat mass or lean mass reads too high, depending on how their body changed.
Weigh on the same scale just before every scan.
One scan against the trend
Day-to-day differences are mostly noise.
A single jump or drop that the next scan doesn't confirm.
Act on changes that hold across two or more scans.
Very muscular builds
Large circumferences from muscle look like large circumferences from fat.
Body-fat % reads high.
Measurements still hold. Lean on waist and the trend for body-fat %. Prism's Athlete Mode can be enabled for these patients.
Low muscle at a normal weight
Sometimes called "skinny fat". Shape changes little as muscle is lost.
Body-fat % can read low; circumferences barely move.
A normal result doesn't rule out low muscle. Pair it with strength, function and history.
Very lean patients
Below roughly 15% body fat, body shape tells the models less.
Larger error relative to the value.
Measurements still hold. Don't use small body-fat differences in this range to make decisions.
Not validated
Pregnancy, patients who can't stand unaided and turn, limb amputation, conditions that change limb shape (lipedema, significant edema).
Numbers that look normal but have no validation behind them.
Use waist trends only, or another method.
Benchmarked against DXA
Close to DXA on average. One patient can sit further from DXA than the average, so don't present it as a DXA result.
Future body predictions are motivational
Prism's "Future Me" shows an average weight-loss trajectory, not a forecast for this patient on this treatment.
Module 6
Clinical scan protocol
The scan is a measurement procedure. How it's taken decides how good the numbers are. For clinical use, ask patients to scan the way they would prepare for any body measurement: in minimal clothing.
Minimal clothing: fitted swimwear or underwear
- The scan sees the true body outline, with nothing adding volume
- Prism reads the body from the image, not only its outline. Visible skin gives the models the most detail to work with, and readings get more accurate as the models improve
- Frame it like changing into a gown before imaging: part of the procedure
Fitted gym wear
- Compression leggings or fitted shorts, fitted sports top
- For patients who prefer not to scan in minimal clothing
- Works well, as long as the patient stays in fitted gym wear every time
Loose clothing hides the body
Fabric adds centimetres to every circumference, so body-fat % reads high and lean mass reads low.
It doesn't need to be the exact same outfit. Switching between minimal and fitted clothing is a change in baseline.
Same scale, just before the scan. Weight feeds every mass value.
Same time of day, ideally in the morning before eating. Scan every one to two weeks.
Ready-to-use patient instructions
"Your body scan is a measurement, like a blood pressure reading, so we want it taken the same way every time. Please scan in swimwear or fitted underwear if you're comfortable, or fitted gym wear if not, and stick with the same type of clothing each time. Weigh yourself just before you scan, ideally in the morning before breakfast. Each scan gives us a reading, and over the weeks we'll see how your numbers are changing."
Module 7
Reading change over time
Each scan is a usable reading, and the series tells you even more. Some lean mass loss is normal during weight loss: what matters is that fat falls much faster than lean. Three illustrative patterns, with how to read each one. The data shown is illustrative, not from real patients.
Weight down, mostly from fat
Everything goes down, which is normal. But fat falls about three times faster than lean mass, so body-fat % improves and waist follows weight down.
This is the outcome to reinforce. Some lean loss comes with any weight loss; the ratio is the sign of good-quality loss. Lean mass holding flat, or rising with resistance training, is even better but less common.
Healthy changeWeight down, lean falling as fast as fat
The same weight loss, but lean mass falls as fast as fat. Body-fat % barely improves, even though the scale looks great.
Worth a conversation about protein intake and resistance training, especially on rapid-loss treatment.
Watch lean massA step drop with steady weight
Body-fat % drops sharply between two scans while weight barely moves. Real fat loss doesn't look like a step.
Ask what the patient wore. If the clothing changed, treat the new scan as the new baseline.
Check the protocolModule 8
Practitioner FAQ
The questions patients and practitioners ask most, with answers you can use directly.
My patient's gym scale or InBody says their body fat is lower. Which is right?
Different methods give different numbers, and published studies show bioimpedance devices tend to read lower than DXA. Pick one method for this patient and stay with it. Every method has a precision range: repeat Prism scans agree within about half a point of body fat (±0.41 in validation), against about ±2 points for DXA and wider for BIA. So a change Prism shows is well above its own noise.
Why did body-fat % go up when weight went down?
Usually one of two things. Lean mass was lost faster than fat (see pattern 2 in Module 7), or the scan conditions changed: looser clothing, or weight not updated. Check the protocol first, then look at lean mass.
Can I use Prism to decide eligibility for treatment?
Prism measurements can inform your clinical assessment, the same way a tape-measured waist or a BIA reading would. Waist circumference is Prism's most accurate measure and is a reasonable input to a cardiometabolic risk assessment. The decision stays with the practitioner. Prism is not a diagnostic device.
How often should patients scan?
Every one to two weeks during active weight management, under the same conditions each time. More often adds little, because week-to-week change is small compared with noise.
Does the patient's phone matter?
No. Results are consistent across current iPhone and Android phones.
Why do you recommend minimal clothing?
The scan measures the outline of the body. Anything that adds volume, even fitted fabric, moves the outline away from the skin. Minimal clothing gives the truest outline and the most consistent one over time. Prism also reads the body from the image itself, so visible skin gives the models more to work with, and accuracy improves as the models do. Fitted gym wear is an acceptable alternative.
My patient is very muscular. Can I trust their result?
Their measurements, including waist, are as accurate as for anyone. Body-fat % tends to read high in muscular builds, so lean more on the trend for that one. Prism offers an Athlete Mode tuned for very lean and very muscular builds.
Does Prism show patients an image of their body?
Only if you choose to. The partner controls what patients see: numbers only, an anonymised avatar, or a textured 3D model. Many weight-management programs start with numbers only.
Module 9
Evidence
Full validation figures and the peer-reviewed work behind them. The live, sortable dataset is at validation.prismlabs.tech (last validation run May 5, 2026).
Validation figures
| Metric | Prism vs reference | Reference method's own variation | Prism scan to scan | n |
|---|---|---|---|---|
| Body-fat % | ±3.56 pts vs DXA | DXA test-retest ±2.00 pts | ±0.41 pts | 271 |
| Visceral fat | ±0.23 pts vs DXA | DXA test-retest ±0.10 pts | ±0.02 pts | 226 |
| Limb lean mass | ±1.61 pts vs DXA | DXA test-retest ±0.40 pts | ±0.20 pts | 185 |
| Waist | ±1.36% vs 3D scanner | Trained tape measurer ±1.50% | ±0.60% | 78 |
| Chest | ±1.49% vs 3D scanner | Trained tape measurer ±1.50% | ±0.57% | 78 |
| BMI | ±2.82% vs 3D scanner | Self-reported BMI ±5.00% | ±0.83% | 78 |
Publications
| Year | Study | Where | n | Finding |
|---|---|---|---|---|
| 2026 | Body composition: a consistent, accurate alternative to DXA | White paper | 273 | Tracks DXA closely across body fat, visceral fat and limb lean mass |
| 2024 | Accurate metabolic disease-risk phenotyping | Obesity Science and Practice | 44 | Scan measurements highly correlated with a trained anthropometrist's tape |
| 2024 | Accuracy validation of Prism mobile scanning vs DXA | Frontiers in Medicine | 131 | Suitable as a rapid, accessible alternative to DXA |
| 2024 | Body composition via US Army method from 3D mobile scan | British Journal of Nutrition | 96 | Acceptable group-level performance |
| 2024 | Precision validation of Prism mobile scanning | European Journal of Clinical Nutrition | 46 | As precise as large multi-camera 3D scanners |
| 2023 | Precision and accuracy validation of Prism mobile scanning | White paper | Superior precision to other systems; good accuracy vs DXA | |
| 2023 | Precision validation of single-camera non-rigid method | Clinical Nutrition Open Science | 69 | More precise than multi-camera 3D scanners |
| 2020 | Three commercial body scanners vs Prism Gen-1 | European Journal of Clinical Nutrition | 179 | Precise anthropometric estimates across scanners |
| 2019 | Accuracy and precision of the Prism Gen-1 scanner | European Journal of Clinical Nutrition | 90 | Good correlation with tape and DXA, no significant bias |