An increased understanding of the connection between cardiac ischaemia and changes in the ECG is of great importance clinically, and simulation studies are an integral part of work in this area. This talk will discuss several methods (Gaussian Process emulators, Partial Least Squares Regression and Polynomial Chaos Techniques) that can be used to consider the effect of uncertainty in inputs to cardiac models. Some background will be given for the methods and there will be a discussion about the advantages and disadvantages of each of them. These ideas will be illustrated in the context of modelling sub-endocardial ischaemia, during the ST segment of the ECG, using a halfellipsoidal model of the ventricle.