12% Medicare Advantage denies one in eight admissions
Two-thirds of facilities face MA denials weekly or daily. Two-thirds also report plans ending coverage against medical advice.
Healthcare · UK & Europe
Nine out of ten denied claims are never appealed. Ninety-five percent of the ones that are get overturned.
Your team is not wrong about the denials. They just do not have four hours per appeal to prove it.
11.5%
of denied skilled nursing admission requests are ever appealed, despite a 95% overturn rate on those that are.
In the UK and Europe
This is what it actually runs on here.
Platforms in this market
- Person Centred Software
- Nourish
- Access Care Planning
- Radar Healthcare
Rules that apply here
- CQC fundamental standards
- UK GDPR
- the Care Act 2014
- local authority funding rules
We read the rule before the call. It is the cheapest way to prove we did the work.
What is happening
Nine in ten denials are never appealed. Not because they were right.
2-4 hrs Every appeal means reading the chart
The evidence sits in nursing narrative, therapy notes and the MDS. Your billing platform submits claims. It cannot argue one.
$30-35 Per patient day lost to MDS undercoding
Speech components carry a 38% error rate, non-therapy ancillary 31%, nursing 27%. Therapy, which is counted in minutes rather than described in words, sits at 2%.
18 hrs Average referral response time
Top performers answer in 15 to 30 minutes. Responding inside the first hour doubles conversion. Around 30% of referrals are lost to slow response alone.
Reporting stops at the building
Your EHR reports per facility. Leadership rebuilds the portfolio view in a spreadsheet every Monday, by which point the numbers are three days old.
However hard, whatever it is
Denials are one example. Bring the one actually costing you money.
We wrote this about appeals nobody has hours for. If yours is coding, census or a survey finding, the method does not change.
-
01 We sit with you
Days where the work happens, not a workshop in a meeting room. We watch the job get done and write down the shortcuts nobody wrote down.
-
02 We read everything
Your data, your rules, your vendors and their documentation, and the published research on your sector. We report what is actually in there.
-
03 We break it to first principles
Not which tool fixes this. What is actually causing it, taken apart until we reach the piece that cannot be divided further.
-
04 Then we build
Weeks, not quarters. By this point we are not guessing what to build, and guessing is the thing that makes projects long.
Where we sit
Your clinical system stays. We build the appeal that never gets written.
4
What you get
- Denials worked Every denial gets a decision, not a shrug
- Revenue recovered Money you already earned, collected
- Capture rate MDS gaps flagged before the window closes
3
Built new for you — none of this exists in your stack today
- An appeal pack built from the chart in minutes, not days
- A denial board the team works from every morning
- A one-tap check that a care task really happened
2
The appeal layer Reads the chart and the remittance. Submits nothing without sign-off.
Connectors, one agreed meaning per field, and a model reading what no
field holds. Accuracy measured on your own records.
1
- Person Centred Software
- Nourish
- Access Care Planning
- Radar Healthcare
What you already run — unchanged, and still yours
If the chart or the remittance holds it, we can reach it. FHIR where it exists, a scanned denial letter, a fixed-width payer file. We have built against all three.
-
No API -
No documentation -
A terminal from 1994 -
It arrives as paper -
The vendor said no -
It reports nothing
Not a list of limits. Name yours on the call.
And once we can reach it, a model can read it. Most of the value here is in the sources nobody ever structured — the note, the letter, the screen.
Intelligence, plumbed in
The condition was in the nursing note. Now it reaches the MDS.
We build retrieval over the chart, one coding vocabulary in the layer, and an eval set of assessments already audited.
How we make AI survive real data-
Connectors -
A semantic layer -
Evals you can check
What changes
Judge us on this, not on what we built.
Denials worked Every denial gets a decision, not a shrug
Denials surfaced, aged, assigned and packaged with the clinical evidence already assembled. Deadlines tracked through redetermination and reconsideration.
Revenue recovered Money you already earned, collected
We can work this on contingency. A share of what is recovered, and nothing if nothing is recovered.
Capture rate MDS gaps flagged before the window closes
The qualifying condition is usually already in the nursing note. It simply never reached the assessment. We reconcile the two.
One view Census across every building, live
Occupancy, payer mix, admissions and discharges reconciled to what each facility reports. No Monday rebuild.
Who this is for
The people who feel this first
-
Chief Operating Officer -
VP of Revenue Cycle -
Director of Clinical Services -
Regional Director of Operations -
CFO
Straight answers
The questions you would ask on the call
-
Can you integrate with PointClickCare?
Yes. We have built production integrations against PointClickCare and eClinicalWorks, including the parts that are not in the documentation. In March 2025 a Fourth Circuit ruling confirmed that blocking third-party API access counts as information blocking under the Cures Act. That puts you on stronger ground when you ask for your own data.
-
How do you price denial recovery?
Two ways. A fixed-price build starting at $25,000, or contingency — a share of what we actually recover, and nothing if we recover nothing. Most operators start with contingency because it removes the risk of finding out.
-
How long before we see anything?
A few weeks. We take read-only access. We come back with what is really in your system, the three questions you cannot answer today, and a dollar figure on the biggest leak. That is yours whether or not we carry on.
-
Do you handle PHI, and are you HIPAA compliant?
Yes. We sign a Business Associate Agreement before any access. PHI is encrypted at rest and in transit, access is logged per record, and infrastructure sits in US regions.
-
Can AI find what the nursing note says and the MDS missed?
Yes. That is retrieval over the chart, scored against assessments already audited. The coder decides; the system only points.
Do you know the rules that apply in the United Kingdom, Ireland and the European Union?
For skilled nursing that means CQC fundamental standards, UK GDPR, the Care Act 2014 and local authority funding rules. We read the rule before the call, so the first meeting is about your operation rather than about us catching up.
Whatever skilled nursing needs here, we can make it.
What you already run stays where it is. Around it we build software, hardware and the process itself. Here that means an appeal pack built from the chart in minutes, not days.
See everything we build-
Software -
Hardware -
Ways of working -
Whole ventures
Honest about the numbers
The figure above is from KFF on Medicare Advantage post-acute denial rates, for skilled nursing.
We have not localised it, because a number nobody can check is worth less than a real one plus this sentence. The pattern travels. The size of it in your market is a question for the call.
Same industry, other markets