A method, system, stethoscope and server for classifying a cardiovascular sound recorded from a living subject. The method comprises the steps of: identifying diastolic and/or systolic segments of the cardiovascular sound; dividing at least one of the identified diastolic and/or systolic segments into a number of sub-segments comprising at least a first sub-segment and at least a second sub-segment; extracting from the first sub-segment at least a first signal parameter characterizing a first property of the cardiovascular sound, extracting from the second sub-segment at least a second signal parameter characterizing a second property of the cardiovascular sound; and classifying the cardiovascular sound using the at least first signal parameter and the at least second signal parameter in a multivariate classification method.