Two disciplines, one shared belief
Before founding Medip Analytics, we kept encountering the same challenge from two different sides of health economics. The value of a diagnostic test, medical technology, or procedure is never fixed. It depends on the patient population, available capacity, clinical pathway, and the real-world context in which decisions are made.
Our backgrounds were complementary. One centred on health economics, decision modelling, and scientific evidence generation. The other centred on individual-level simulation, software engineering, and interactive data applications. Together, we saw an opportunity to make rigorous models more accessible without compromising their analytical depth.
We shared one belief: health-economic analyses should be dynamic, transparent, and understandable. They should support the people making decisions about innovations, patient pathways, and healthcare resources. A single static analysis is rarely sufficient when value changes across populations and settings.
That combination of evidence expertise and technology became the foundation of Medip Analytics. We wanted to connect the evidence required to demonstrate value with software that could make complex models scalable and interactive.
What if health-economic models could become more realistic, more dynamic, and easier to use?
From concept to first application
Traditional spreadsheet and desktop modelling tools have supported health-economic analysis for decades, but we also saw their limitations. Models can be static, difficult to interpret, and accessible only to the specialists who built them. This restricts their value in multidisciplinary decision-making.
We believed there was a better approach: combine robust disease-area models with dynamic inputs, outputs, and scenarios. Instead of rebuilding the analytical foundation for every project, a validated model could support multiple innovators while preserving the flexibility required for specific technologies and settings.
After completing our PhDs, we founded Medip Analytics on 19 November 2021. We focused first on the analytical architecture, platform technology, and evidence workflows required to turn this idea into a reliable product. Our consulting engagements kept that development grounded in real market-access and health-economic requirements.
This work became the Medip Platform: an environment that turns complex health-economic models into interactive applications teams can use, update, and communicate. We wanted modelling to become a continuous resource for evidence generation, market access, and strategic decision-making rather than a static final report.
Our first technical priorities were computational performance and scale. We needed to accelerate individual-level simulation while enabling many users to work with complex models securely and concurrently.
Our first commercially available solution was the Prostate Diagnostics Application. It is now used by multiple companies to demonstrate the added value of prostate cancer biomarkers and diagnostic technologies.
The underlying model was also used by Radboudumc researchers in a peer-reviewed cost-effectiveness analysis of PSMA-PET/CT for detecting clinically significant prostate cancer: Prive et al. 2025.
From one model to a scalable platform
After launching the first application, we began receiving questions about other disease areas and technology categories. Could the same approach support different clinical pathways, new diagnostic fields, and earlier value exploration while evidence was still developing?
In response, we expanded the platform, developed additional applications, and refined how multidisciplinary teams interact with complex health-economic evidence.
Today, we serve customers in nine countries, while Medip applications are used across more than fifteen countries. For us, this international adoption demonstrates that a common analytical foundation can still support locally relevant decisions.
Medip Analytics has never been only about software or models. We want to help teams ask better questions earlier, examine uncertainty explicitly, and connect evidence development to strategic choices.
For which patients, in which setting, and under which conditions does an innovation create value?
Evidence first, including challenging results
Over the past five years, we have learned that evidence should remain at the centre of every value discussion. All models contain assumptions and uncertainty. Making these explicit strengthens scrutiny, supports informed debate, and increases confidence in the conclusions.
A scenario in which an innovation is not cost-effective can be as informative as one in which it is. It identifies the conditions required to create value and contributes to a more credible evidence strategy. We believe software should make those findings visible rather than hide them.
We are therefore developing Medip Analytics from modelling support into a broader evidence platform. Through Medip Academy, we help users understand the principles behind health economic software and apply them consistently in practice.
At the same time, we continue to expand the Medip Platform into additional disease areas. This broadens access to advanced health-economic methods for established organisations, emerging innovators, and teams working in rare diseases or specialised clinical pathways.
The next chapter
Our roadmap focuses on usability, explainability, and responsible access for non-specialists. We are developing Meddy One, our first domain-aware AI assistant, to help users navigate applications, inputs, assumptions, disease pathways, and the interpretation of results.
This next step builds on a substantial knowledge foundation we have developed over the past five years: disease-area models, structured assumptions, scenario logic, evidence frameworks, and practical experience across technologies, organisations, and markets.
Each application captures detailed knowledge about clinical pathways, patient populations, diagnostic strategies, treatment decisions, costs, outcomes, uncertainty, and value drivers. We believe that combining this structured domain knowledge with AI can make health-economic analysis more accessible while keeping the underlying logic transparent.
The next generation of health economic software should do more than calculate outcomes. It should help users understand why results occur, identify influential assumptions, examine uncertainty, and determine how an innovation may create value in a specific real-world context.
For that reason, we do not see AI as a generic interface placed next to a model. It should be grounded in the model structure, disease pathway, inputs, outputs, and analytical relationships behind the results.
This is the direction we are working towards: more intelligent, transparent, and explainable applications that help teams explore evidence, challenge assumptions, and make better-informed strategic decisions.
Over time, we believe the Medip Platform can become a central evidence environment where teams assess value, align internally, and communicate evidence clearly with healthcare professionals, payers, and national agencies.
We built Medip Analytics to make rigorous health economics more accessible, dynamic, transparent, and useful.