Referral analytics for community medical imaging
Bellwether reads your monthly referral export and identifies referring clinicians whose volume is declining, while there is still time to act on it.
The platform covers referral volume by clinician and by clinic, six early-warning signals, calibrated churn probability, six-month volume forecasting, an outreach queue with contact history, and a written monthly summary of what changed. It runs on one export a month from the system you already use.
Ranking accuracy 0.90 AUC, watchlist precision 79%, measured out of sample on rolling cut-off dates in the production deployment, where every build re-runs the backtests. The demo is that software running on a synthetic panel. One email gets you a password, and nobody follows up with a pitch.
Access is by email: samuel.putra101@gmail.comRequests are answered by a person within one business day.
How referral loss happens
A referring relationship ends without an event. A clinician retires, an office changes how it routes referrals, or it begins sending to a nearer provider. None of these produce a notification, and the change is visible in a monthly total only after it has been under way for some time.
Below is a single referring clinician over three years. They sent between twelve and twenty a month for two and a half years, then tapered, then stopped. Nothing in a monthly total flags that. It is roughly one percent of a mid-size clinic's volume, right up until the month it is gone for good.
- Recent pace
- ·
- Their baseline
- ·
- At risk, 12mo
- ·
Referring on their usual rhythm.
At-risk is the annualised baseline pace, discounted 32% for the share of relationships that recover without anyone calling. Drag to move through their history. This runs a simplified version of the real signal logic in your browser, without the dispersion, seasonal and peer-context terms the product uses. Nothing is sent anywhere.
The six signals
Each signal was built and backtested against later outcomes before it was included. Thresholds are absolute, never relative to whoever else happens to be on the list this month, so a good month for the panel cannot hide a bad month for one clinician.
Cadence break
Someone who refers on a rhythm has missed it. Their own median gap sets the clock, so a monthly referrer and a quarterly one are judged differently. The clock also reads their calendar: when a clinician's own history shows the same months quiet year after year, silence in those months raises the bar by exactly that overlap, never by more than three months, so an annual break is not flagged mid-break while silence that outlives the usual window still is. baseline anchored to their last active month, so silence cannot decay it; recurring quiet seasons learned from two or more of the clinician's own years
Slippage
Recent volume has fallen below their own established baseline, and stayed there across two consecutive monthly snapshots rather than one noisy reading. requires two snapshots; single-month dips are ignored
Deceleration
The decline is getting steeper rather than levelling off. This one never flags anybody on its own; it only corroborates and sharpens another signal. corroborating only, needs a material below-baseline decline
Below expected
They are running under what their own history predicts for this month, after the season and their clinic's overall movement are both accounted for. exact Poisson / negative-binomial lower tail
Erosion
Still active, still on the books, but running at half their best sustained pace and still falling. This is the slow bleed the churn signals miss, because nobody ever went quiet. 50% of the best 12 of the trailing 24 months, a non-decaying baseline
Sparse break
For the surgeon or physiotherapist who sends one to five a year, monthly cadence is meaningless noise. The open gap is compared against that sender's own gap distribution instead. shrunk empirical q90, gaps weighted toward a volume-band prior
A flagged clinician also carries a read on whether the drop is theirs alone. If their whole clinic dipped together, the entry is pushed down the queue. If they fell while their colleagues held steady, it is pushed up. In backtests, isolated drops preceded real loss about 67% of the time; clinic-wide dips, between 0 and 11%.
Doing this without software
Clinics generally track referrers in one of three ways: not at all, on a spreadsheet kept by an office manager, or through a dashboard built on the same monthly export. All three cost less than this does. Two of them share a specific limitation, described below.
Month-over-month comparison
A doctor who usually sends six a month sends three. On a sheet that is a fifty percent collapse and it goes on the call list. It is also unremarkable: at six a month, three is within their ordinary variation, and the visit is spent on a relationship that was not at risk.
A doctor who usually sends forty sends thirty-two. A twenty percent dip, easy to scroll past, and that one is real. Judged against each clinician's own history and their own variability, the second is a signal and the first is noise. By eye the two look the opposite way round. Across two hundred referrers that is a large amount of arithmetic to hold consistently.
Silence has no row
A clinician who stops referring stops appearing. Absence does not announce itself, so you have to already suspect somebody is gone in order to notice they are missing. Every signal here is built the other way round: the queue is a list of people who are not there.
Name variants cost time to reconcile by hand. The same clinician arrives as Smith, J. / J Smith MD / SMITH JOHN, and until those are one person every total is wrong. Bellwether catches the variants at upload and merges them only when you confirm it.
The outreach queue
The queue is ordered by how many referrals are at risk over the next twelve months, discounted by how often declines of this shape actually persisted in past data. We stop where the data stops: your export records that a referral happened, not which procedure was booked, so we will not multiply it by a fee and call the product of two estimates a forecast. If you give us your schedule we will price it for you, clearly labelled.
Measured accuracy
Bellwether publishes how often its own scores have been right. The figures below are measured out of sample, shown on a page inside the product, and updated with every data load.
| Measure | Result | Gate | What it means |
|---|---|---|---|
| Ranking accuracy (AUC) | 0.90 | min 0.85 | Pick a clinician who later went quiet and one who did not. The score orders them correctly 90% of the time. |
| Watchlist precision | 79% | min 70% | Of everyone the queue flagged, this share genuinely declined or went silent. |
| Calibration error | 0.014 | max 0.05 | When it says a 30% chance of going quiet, it happens about 30% of the time. Uncalibrated, that error was 0.19. |
| Volume at risk | r = 0.88 | min 0.60 | Predicted referrals at risk against what was actually lost twelve months later. |
| Forecast error | 11.9% | max 20% | Average miss on the six-month clinic volume forecast. |
Measured on the production deployment: a community imaging clinic in Alberta, roughly a thousand referring clinicians and five years of monthly history, running since 2025. Measured on data through July 2026 and re-run on every drop. Rolling-origin backtest, the model is rebuilt at a series of past cutoff dates and graded only against months it had never seen. The demo runs on a synthetic panel, so the figures on its own screens are illustrative rather than these.
Calibration
A health score out of 100 ranks people well and lies about likelihood. Dividing it by 100 and calling it a probability was wrong by a factor of nearly four at the top end. So the score is fitted against measured outcomes and the number you see is the corrected one. The mapping only stretches the scale, so it never changes who is flagged or in what order. It only makes the percentage honest.
Going quiet and losing volume are different failures. A busy clinician sliding from forty a month to twenty can carry a low chance of going silent and a large volume at risk at the same time. Both numbers are shown, because acting on either alone gets you the wrong week.
The prediction ledger
On each data drop, Bellwether appends its live claims to a ledger: who is flagged, the baseline each was judged against, the churn probability, and the six-month forecast with its bands. That file is written before anyone knows what happens next, and older entries are never rewritten.
Months later, the Brief grades them against what actually occurred: recovered, went quiet, still declining. Because the claims are timestamped before the outcome exists, the grade is the first thing we would ask to see if we were buying this.
Regression gates
In the production deployment, every change runs the backtests in continuous integration, and the build fails if any measure crosses the gate in the table above. A fixed gate only catches a cliff, so a second check compares each result against the last human-approved level and fails on drift, even while a number is still technically passing. Raising that bar is a reviewed commit. No data drop and no code change can lower it on the way past.
A week of use
The output is shaped for the person making the visit: one page, four names, and the reason each one is on it.
Monday, the Brief
What moved since the last data drop. Who newly slipped, who eased off, who came back, and which clinician sent their first ever referral last month.
The queue
Ranked by what is at stake, grouped by clinic when the visit is to an office rather than a person. Mark contacted, snooze, dismiss. The team shares one live list.
The visit briefing
One printed page per office: who is slipping and why, the numbers behind it, the recent contact history, and blank lines for notes.
Next month, the grade
The calls made last quarter come back scored against what actually happened, so the outreach effort has a measured result rather than a feeling.
One export a month
Setup requires no integration project, no interface engine, no on-site server, and no access to patient records at any point.
- →An export from whatever you already run. Long-format claim exports are converted to monthly counts on upload, and we work to your cadence rather than ours.
- →Referring clinician, date, and modality are the only fields used. Nothing patient-identifying is read, stored, or committed.
- →Drag the file onto the update page. You get a full preview of what will change before anything is written, and a backup is kept.
- →Spelling variants of the same clinician are caught at upload and merged only when you confirm it.
- →Your team signs in with one shared password, and the whole thing runs under your own name.
Flat monthly fee, published
The fee is flat. It is not a share of billings and not a charge per referral, so the price does not change as your referral volume changes.
| Plan | Founding rate | List rate | Who it is for |
|---|---|---|---|
| One location | $495/mo | A single imaging site. Less per month than five abdominal ultrasounds. | |
| 2 to 4 locations | $995/mo | One deployment covering every site, with referrers pooled across the group. | |
| 5 to 9 locations | $1,495/mo | The point at which no single person still holds the whole referrer list in their head. | |
| 10 or more | quoted | · | Priced on locations and the size of your referring panel, because both are what the work scales with. Per-site filters and a site league table are built with the first multi-site client and quoted alongside that work, not promised ahead of it. |
| Setup | waived | Import mapping, validation against your own history, and the first drop. Waived for founding clients through December 2026; from $6,000 for a multi-site rollout. |
Founding rates are for the first three clients and are locked for as long as you stay. After that the list price applies, which is why both are printed here. Twelve month term. Where a setup fee is actually charged you have sixty days to get it back for any reason, and for a founding client it is waived, so there is nothing to refund and nothing to claw back. A quarterly readout is included at founding rates, and we will run your monthly drop for you for $150 if you would rather not. All prices are in Canadian dollars and do not include GST.
The arithmetic
A referrer sending twelve a month who stops is roughly 144 studies a year. On the published schedule that is about $5,200 a year at the chest X-ray rate ($36.41), or about $15,200 at the complete abdominal ultrasound rate ($105.62). The one-location founding rate is $5,940 a year. This is arithmetic on published fee-schedule rates and a stated example, not a forecast of what outreach recovers.
Questions
How long until it is running?
About two weeks from the day you send the first export. Most of that is us checking the import against your own data rather than anything you have to do.
Do we have to change systems?
No. Bellwether reads an export from whatever you already run, whether that is your billing system, your RIS or your PACS reporting module. The requirement is deliberately tiny: two columns, who referred and when. Modality is used when it is there, to compare a clinician against others sending the same kind of work, and ignored when it is not. Nothing else is read and nothing else is kept, which is why almost any system qualifies. one system ingested in production; yours is matched against your own file at setup, before you pay
How often do we send it, and can you just pull it?
Whatever suits you. Monthly is the usual rhythm and matches how the models think, but weekly or fortnightly is the same operation, and some offices prefer the shorter loop. A month that is still in progress is detected at upload, held out of every model, and labelled on screen, so sending mid-month never quietly distorts a number. If your system exposes an API we will pull on your schedule instead, and building that connector is setup work we look at and quote before you commit rather than something we promise sight unseen.
Do you ever see patient information?
No. Long-format exports are aggregated to monthly counts per referring clinician at the moment of upload, before anything is stored, so no patient field reaches the system even in transit through it. The only columns used are referring clinician, date and modality.
Where does our data live, and can we get it back?
In your own deployment, not a shared database with other clinics. The infrastructure is Vercel and GitHub in the United States, with the shared call list on Convex, also in the United States; what crosses the border is monthly referral counts per clinician, because no patient field exists in the system to cross it. It is a small set of monthly count files, so an export is immediate and complete, and deletion on request is the same thing in reverse.
Do the accuracy numbers hold on our data?
They are re-measured on your own history at setup, and you see the result before you commit. If the models cannot clear their gates on your data we will tell you.
Why has nobody bigger built this?
The American versions exist and are sold to hospital groups. They are built on purchased all-payer claims data, and that dataset has no Canadian equivalent to buy: per-physician billing records sit with the provinces and with CIHI, where access runs through a request into a secure environment, only aggregate results may leave it, and commercial use needs written authorisation. The usual way into this market is closed, so the answer has to be built from a clinic's own export instead. the same reason we can only ever show you your own referrers, never benchmark you against the clinic down the road
Who is behind it?
Bellwether is built and run by Samuel Putra. One community imaging clinic in Alberta has run it in production since 2025. The founding cohort is three clients because one person can onboard three clinics properly.
What this is not
The list below is what Bellwether does not do, and what it does not yet claim.
- ✕Not an EMR or a booking system. It reads an export and it never writes back to your clinical systems.
- ✕Not a patient data product. The importer aggregates to monthly counts at the door, so no patient field ever reaches storage.
- ✕Not a chatbot. Nothing here generates prose about your business. The sentences are templates filled from measured numbers.
- ✕Not priced per referral. A flat monthly fee. We should not earn more when your volume grows, or less when we help.
- ✕Not yet proven to change outcomes. Bellwether is measured at finding and ranking risk. Whether outreach recovers a relationship is a claim that needs a held-out group and a year, and we would rather build that evidence than assert it now.
The demo is the product, with the data swapped out.
Same models, same thresholds, same code. A synthetic panel of 165 referring clinicians across sixteen offices, so you can click anything without looking at somebody's real book of business.