Abstract. Current deep-learning-based methods do not easily integrate into clinical protocols, neither take full advantage of medical knowledge.In this work, we propose and compare several strategies relying on curriculum learning, to support the classification of proximal femur fracturefrom X-ray images, a challenging problem as reflected by existing intra- and inter-expert disagreement. Our strategies are derived from knowledgesuch as medical decision trees and inconsistencies in the annotations of multiple experts, which allows us to assign a degree of diculty to eachtraining sample. We demonstrate that if we start learning \easy" examples and move towards \hard", the model can reach better performance,even with fewer data. The evaluation is performed on the classification of a clinical dataset of about 1000 X-ray images. Our results show that,compared to class-uniform and random strategies, the proposed medical knowledge-based curriculum, performs up to 15% better in terms ofaccuracy, achieving the performance of experienced trauma surgeons. Keywords: Curriculum learning, multi-label classification, bone fractures, computer-aided diagnosis, medical decision tree