Together with many researchers around me, I work on evolutionary machine learning techniques where, unlike many other techniques, we can find multiple optimal answers for difficult clinical problems with relatively little data. We use the available computing power for the (time-consuming) exploration of different solutions for clinical issues that require a balance between multiple clinical goals, such as; treating a disease as well as possible while minimizing side effects. We do this by simultaneously exploring, combining and evaluating thousands of potential solutions. We then present only the most potential solutions that all represent a different trade-off between the established clinical goals. We then leave it to the medical experts to use their knowledge of the patient's background to choose the solution that is the most appropriate trade-off between the goals set. In this way, we hope that these machine learning techniques are an addition to clinical decision-making where computing power is used to search among thousands/millions of different solutions and where the intuition of the medical expert is used to make the best decision within the individual patient's context.