Stem cells represent an invaluable source of cells for tissue regeneration, thanks to their ability to self-renewal and differentiate into functional cells of the tissues. The studies and results related to stem cell differentiation are diverse and sometimes contradictory due to the different stem cell types and the numerous variables involved in the differentiation process. In this paper a new methodology is proposed in order to select the relevant factors involved in stem cell differentiation into myocardial lineage and forecast its behaviour and response in the differentiation process. We have built a database from the results of experiments regarding cardiomyocytic differentiation of stem cells and using this database we have applied state-of-the-art classification and predictive techniques such as support vector machine and decision trees, as well as several feature selection techniques. The results obtained are very promising and demonstrate that with only a reduced subset of variables high prediction rates are possible.