Our approach is tailored to be easily usable and acceptable by healthcare professionals.
Our data-driven Natural Language Processing models learn from real-life examples. The system learns how the users work, not vice versa.
The initial system is a starting point. The AI models learn from further interactions with healthcare professionals, creating a positive feedback loop.
We focus on interpretable AI, where users can easily understand the AI suggestions and validate or correct based on the presented evidence.
Our Medical Language Processing technology is at the core of the solutions we
build for and together with customers. A modular, container-based architecture
gives us the flexibility to adapt to different needs.
Flexibility also means flexibility in deployment. That's why we offer on-site as well as cloud based deployment solutions. That way, healthcare institutions can be in control of their own data.
Over the years, we have worked on multiple projects (e.g. adverse event detection) and services (e.g. pseudonymization and anonymization). But the following are the projects that have grown into real products:
In the context of migrating to next generation electronic health record systems, hospitals are looking to add value from the new possibilities offered by SNOMED CT based functionality.Learn more
ICD-10 coding is essential in the administrative processes of hospitals in many countries. We are working with Belgian hospitals to streamline the ICD-10 coding for the obligatory MZG registration.Learn more
Our collaborative annotation tool allows efficient annotation of patient records with the relevant SNOMED CT concepts.
We provide a range of models and tools that can be combined to streamline the ICD-10/MZG coding environment.