Assured Analytics for Digital Health
Digital health systems range from complex evolving networks of digitally augmented health providers to more specific digital service interventions that target specific health outcomes. Understanding this complexity and evaluating effectiveness requires high-resolution models that are both assured and accurate. The models themselves are often generated using machine learning and underpinned by ontological representations of the real-world. Executing models as simulations, linking them together, and experimenting with many scenarios will generate substantial amounts of data. The challenge is how to analyse this data, often with machine learning, and make meaningful decisions.
We have developed several methods to address these challenges with machine learning, analytics, and immersive visualisations.