Decision trees have been already successfully used in medicine, but as in traditional statistics, some hard real world problems cannot be solved successfully using the traditional way of induction. In our experiments, we tested various methods for building univariate decision trees in order to find the best induction strategy. On a hard real world problem of the orthopaedic fracture data with 2637 cases, described by 23 attributes and a decision with 3 possible values, we built decision trees with four classical approaches, one hybrid approach where we combined neural networks and decision trees, and with evolutionary approach. The results show, that all approaches had problems with accuracy, sensitivity, or decision tree size. The comparison shows that the best compromise in hard real world problem decision trees building is the evolutionary approach.