Fewer missed appointments. More time for care.

I help healthcare teams use their existing appointment data to spot higher-risk appointments and focus follow-up where it may help. We start by checking whether it makes sense for your organisation.

Talk through your situation First, see the potential impact

Pay only for results

Proven in hospitals and mental health care

Less administrative work

See what the approach achieved at Erasmus MC

Trusted by healthcare organisations including:

Results from earlier projects: a measurable reduction in no-shows at Erasmus MC and Arkin.

Read the Erasmus MC case study

Missed appointments leave time and care capacity unused

One missed appointment can feel like a small setback. Across a busy clinic, the unused time adds up and can make it harder for patients to get the care they need.

Hard to address one appointment at a time

No-shows tend to follow patterns. Your existing appointment data may help show where a timely reminder deserves more attention.

Time and resources still have a cost

When an appointment is missed, the time is hard to reuse at short notice. At Erasmus MC, an analysis identified a substantial amount of unused care capacity.

Existing measures do not always go far enough

Reminders and cancellation policies can help, but teams may still be left reacting to missed appointments. A clearer view of risk can help staff focus their limited follow-up time.

Every organisation is different. Start with your own appointment numbers to estimate the possible impact.

Estimate your organisation’s potential impact

How much revenue do you lose to no-shows each year?

Enter your numbers and instantly see how much revenue you lose each year. Based on real-world data.

What do you already know?

Number of no-shows per month

Average revenue per appointment

Annual loss due to no-shows

€0

Indicative calculation based on the numbers entered and 80% fixed costs

This money does not come back through rescheduling or no-show fees.

In the next step you'll see how much of this can actually be prevented

You can recover €0 – €0 per year

You only pay for no-shows that were actually prevented.

Estimate based on experience with comparable organisations. Not a guarantee.

Find out if this works for you Impact analysis: 15 min • No preparation • No obligation

Without a targeted approach, this loss comes back every year.

You only pay for proven results

A results-based approach informed by work with Erasmus MC and Arkin.

You only pay for no-shows that were actually prevented.

No results = no costs.

First results within 90 days. You see how many no-shows were prevented and what that is worth.

You only pay once results are visible. Example: no-shows prevented in January are not invoiced until the end of February.

See how the results guarantee works

How I prevent no-shows

Step 01

We predict which patients will not show up

Every day we analyse scheduled appointments and flag the ones with an elevated risk.

Step 02

We only call patients with a high no-show risk

Targeted phone reminders make sure appointments still go ahead. This works alongside SMS and email reminders.

Step 03

You see exactly how much revenue was recovered

Insight into prevented no-shows and recovered revenue, fully measurable and transparent in a dashboard. The approach and results are scientifically proven. Read the paper

Designed for healthcare privacy, IT and governance requirements

Supports GDPR-compliant processing and uses data already held by your organisation.

Data remains within your organisation and is processed in your own IT environment.

Fits around existing processes, with no additional routine work for staff.

Designed to run in your existing environment, without introducing a new system.

What this approach has delivered in practice

Results from earlier collaborations with healthcare organisations.

Case study

Erasmus MC - Hospital

6070

no-shows prevented per year

€270k+

revenue recovered

14.3%

fewer no-shows

Using a prediction model and targeted phone reminders, a significant share of no-shows was demonstrably prevented.

View the full case study

Case study

Arkin - Mental health care

2400

no-shows prevented per year

€240k+

revenue recovered

15%

fewer no-shows

In mental health care, too, a share of no-shows turns out to be structurally predictable and preventable, with an immediately visible effect on capacity and scheduling.

View the full case study

Could this be useful for your organisation?

Talk through your situation

Frequently asked questions

Practical information about implementation, data security, costs and results.

Will this work for our organisation? ⌄

If your organisation manages scheduled appointments, the approach may be relevant. No-show risk varies between appointments and can often be predicted from existing data.

In a short initial analysis, we assess whether your data can support useful predictions and estimate the potential financial impact of acting on them.

What does it cost? ⌄

Fees are based on no-shows demonstrably prevented through the solution.

There are no fixed licence fees, no implementation fees and no upfront costs.

There are no licence, implementation or upfront fees. Before proceeding, we prepare a business case to estimate the likely value for your organisation.

When do we pay? ⌄

Payment is always made afterwards, based on no-shows that were demonstrably prevented.

If no no-shows are prevented, nothing is invoiced.

Example: no-shows demonstrably prevented in January are not invoiced until the end of February.

This means there is no financial risk upfront. You only pay for proven results.

Read more about my results guarantee .

What do we need to do ourselves? ⌄

The effort on your side is limited and mostly about explaining how things work.

You explain:

How no-shows are recorded
Where appointment data is stored
Which definitions are used internally

Using this information, I prepare the appointment data needed to build and run the prediction model. This may include factors such as appointment details and no-show history.

The work can be coordinated with your IT team or carried out independently. On-site support is available when needed.

Data never leaves your organisation.

What if it doesn't work? ⌄

No approach can guarantee that every no-show will be prevented. The aim is to identify appointments at higher risk and make timely, targeted contact.

If you decide to work with me, you only pay for no-shows that were actually prevented. If no no-shows are prevented, you pay nothing.

Initial results are expected within 90 days. We then review the measured impact together. If the business case does not stack up, you can stop without being charged for results that were not achieved.

Is this secure and GDPR-compliant? ⌄

Yes. The solution runs within your organisation's existing IT infrastructure. Data does not leave your organisation.

The prediction model works with pseudonymised appointment and patient data. Identifiable data is only used where operationally necessary.

An example DPIA is available on request. The approach has been applied in hospital and mental health care settings and was reviewed with Data Protection Officers.

Why don't SMS/email reminders already solve this? ⌄

SMS and email reminders are a good first step, but they don't prevent all no-shows.

Combining risk predictions with targeted phone reminders can help teams focus their calls on appointments where follow-up is most likely to make a difference.

If you don't use reminders yet, you can expect an even higher return.