A recent research highlighted the potential for communicating about care risks through visual means rather than only words or numbers to convey likelihood or seriousness of possible harm. Analysis of a situation and prediction of the level of associated harm is conducted by humans who assess the situation by gathering information and relating this to experience, research and theory to make a judgement. However the relevant research data is very diverse, and difficult to access. Computational intelligence seeks to develop models that can reason, understand or learn like a human. The ability to spot patterns, adapt to new and unusual data, account for uncertainty, and to be robust to non-perfect and incomplete data are hallmarks of computational intelligence methods. This project aims to introduce computational intelligence approaches to data analysis, to predict an associate harm level and hence provide decision support for the health and social care professional in communicating about risk.