Why are we investing in structured medical data?
- Cavell
- 1 day ago
- 4 min read
Two years ago, we started with a simple yet powerful belief: healthcare providers should spend less time behind their screens and more time with their patients. This was the first step in the right direction. But not the only one.
The real problem: medical data is unstructured!
Cavell listened during consultations and automatically generated medical reports based on what was said. The healthcare provider conducted the conversation, Cavell wrote, in free text. Afterward, the doctor only had to review and validate. No more typing while the patient talks, no more catching up in the evening.
In our survey of more than 110 healthcare providers, we saw clear results. Four out of five physicians indicated that their patient contact improved. They described their work as "faster," "less demanding," and "administratively lighter."
But the survey of these users also revealed something else: converting a consultation into free text is only half the battle.
More than 80% of all medical data consists of unstructured free text. Clinical notes, discharge letters, consultation reports—all written in plain language, stored in documents that machines can't easily read or process.
This creates a cascade of problems. After all, medical data must be:
Recorded during consultations, after operations, during nursing rounds
Processed when preparing prescriptions, certificates, laboratory requests or discharge letters
Consulted when preparing a consultation, drawing up a treatment plan or reviewing a medical history
As long as all that information is in free text, every step must be performed manually by a human who reads, interprets, and re-enters it. Slow, error-prone, and difficult to scale.
Structured medical data means that clinical information is recorded using international standards, so that systems can automatically read, process and exchange that information.
So what is medical structured data?
There are many important internationally accepted standards. Standards for coding medical concepts, such as SNOMED CT, for example.
SNOMED CT is a comprehensive medical dictionary of over 350,000 clinical terms, each with a unique code. "Type 1 diabetes mellitus" is assigned the code "46635009," and "ex-smoker" becomes "8517006." Every diagnosis, symptom, procedure, or observation has a precise, unambiguous identifier.
In addition, there are also standards that allow us to structure these medical codes, such as FHIR, so that we can create relationships, stories, etc. in these medical codes.
FHIR is a framework for structuring medical data into interconnected resources: Patient, Diagnosis, Observation, Care Plan, Medication, and more.
When these standards are combined, a simple note like "55-year-old patient with stabbing headache, probable diagnosis of migraine, brain CT scheduled" can be converted into a set of structured, machine-readable data points, searchable, reusable and exchangeable across systems.
The benefits of this are clearly significant
Easy to search: find all patients with a specific diagnosis in seconds
Automatically processable: trigger workflows, alerts and prescriptions without manual intervention
Interoperable : share data seamlessly between hospitals, general practitioners and specialists
Ready for research and AI: build population analyses and clinical AI models on consistent, clean data
Why doesn't this happen automatically yet?
These internationally recognized standards have existed for decades. So, the question arises: if the benefits are so clear, why aren't we doing this?
The answer is very simple!
“Manually entering structured data is a nightmare!”, testifies almost every healthcare provider in the world.
SNOMED-CT has 350,000 codes. Correct coding requires specific training that most doctors and nurses have never received. And even if they do, selecting the correct code during a busy consultation adds administrative burden—precisely the kind of friction that kills adoption. Tools exist to address this. Structured forms allow healthcare providers to enter coded data through fixed input fields, but this typically entails more administration, not less. Standard AI scribes reduce the administrative burden for healthcare providers, but often generate little or no structured medical data.
The conclusion is clear : structured data will only be captured on a large scale if this happens automatically, intuitively and without additional burden for the caregiver, during the care moment itself.
And that's exactly why we're taking things a step further with Cavell!
Cavell automatically generates structured and coded medical data from a consultation, without any additional steps from the healthcare provider. But it's not just about generating that data. It's about what happens with it afterward.
From free text to coded data points. For example, when a doctor states, "The patient has had a stabbing headache on the right side for several weeks, most likely a migraine without aura," Cavell processes this not as text for the decision, but as meaning. The system recognizes the diagnosis, links it to the correct SNOMED code, and automatically records it in the appropriate place within the EHR. All formatted according to the FHIR standard. All ready for validation.
Structured data tailored to the EHR. The structured data is directly aligned with the structure of the EHR in which the healthcare provider works. There are many different electronic patient records on the market in Belgium and Europe. Cavell adapts the data model for each context (per specialty, per software environment) so that the necessary information ends up exactly where the EHR expects it. No manual transfer, no loss of structure during import.
What this makes possible. Once the structured data is validated in the EHR, a whole new layer of possibilities opens up. Automatic triggers for follow-up, population analyses across patient groups, self-calculating quality indicators, and so on.
It's clear that there are numerous problems in healthcare today. Many of these problems can be traced back to inadequate structured medical data. Tools like Cavell, which can generate truly valuable structured medical data without placing an additional burden on our healthcare staff, will be the catalyst for more value-driven healthcare.
Comments