This objective is highly cross-disciplinary and needs to be performed prior to modelling, but iteratively in parallel to Objective 1. It entails defining the inputs and outputs for the modelling phase. First, the most likely scenarios and use cases for the clinical phases of stroke will be defined. Then, we will identify, rank and weigh input factors of stroke available in our databases in terms of both risk and resilience. The activity will consist of iterations of dialogue between clinicians and modellers. It will also entail experimentation with the data to identify correlations between factors and patient well-being and the use of techniques such as Latent Class Analysis and clustering to identify if masked subgroups (such as early or nonresponders to certain treatments) are present in the harmonized datasets. Defining the outputs for the models, it is crucial to understand how the model output directly links to interventions in patient treatment and how the model fits into the treatment processes within the care setting. Most of our models will provide complex outputs. For some models this added complexity in output is necessary because they explicitly take time scales into account. For other models this added complexity is required to reflect a broader understanding of the factors contributing to resilience and well-being. A central motive of our study is to use a quality-of-life framework as a proxy for resilience and wellbeing. Our models will predict a set of interrelated factors that reflect the variety and evolving factors contributing to an individual’s quality of life. Thus, in this objective the outputs variables will be identified, weighted and integrated in a quality-of-life framework.