Congestive heart failure (CHF) remains the primary cause of death in patients suffering from beta-thalassaemia major. Its early detection allows the prompt initiation of aggressive chelation therapy, when the condition can still be reversed. We aimed at identifying echocardiographic indices for the early detection of left ventricular (LV) systolic dysfunction, the physiological abnormality underlying CHF, in these patients. We used Self-Organizing Maps (SOMs)--an artificial neural network--for identifying novel correlations within our Electronic Healthcare Record (EHCR) database on beta-thalassaemia. We sought echocardiographic parameters that are correlated to future deterioration of the LV ejection fraction and therefore constitute early signs of LV systolic dysfunction. At the same time, we evaluated SOMs as tools for exploring clinical datasets and make recommendations on the setup of the SOM algorithm that is appropriate for such tasks. We found that high values of the LV end-systolic diameter index and of the E/A ratio are early indications of LV systolic dysfunction. From a technical point of view, zero-mean unit-variance normalization of the input data, a large initial neighbourhood radius and a rectangular SOM grid produced optimal maps for the purpose of detecting clinical correlations. We have successfully used SOMs for exploring a clinical dataset and for creating novel medical hypotheses. A clinical study has been launched to confirm these hypotheses, and initial results are encouraging.