In this paper we introduce a novel approach for diagnosis and monitoring of ulnar nerve lesions, affecting the coordination of movement of the ring and little finger of the human hand. Symptoms to be observed are static and dynamic anomalies in movement pattern. Based on data generated by ultrasound measurements, we developed suitable preprocessing methods for automatic extraction of relevant features from the movement pattern to be examined. The partial absence of class information even for the patterns in the training set requires the use of unsupervised methods for the learning and class assignment procedures, since common classification or decision tree methods are not applicable. For that reason, we use a new dynamic and hierarchic neural network for the analysis of the generated pattern vectors.The property of topology preservation as well as the dynamically structured architecture of the network make it suited for the special needs of this medical task, such as providing variable levels of generalization and 163 Brought to you by | New York University Bobst Library Technical Services Authenticated Download Date | 5/30/15 11:59 PM Volume 8, Nos. 1-2 Diagnosis of Finger Dysfunction Caused by Ulnar Nerve Lesion efficient retrieval of similar cases for diagnosis purposes. We present a visualization of the clustering structure and classification results.