Neuropsychological rehabilitation seeks to reduce cognitive disability after acquired brain injury. However, until now, there is not enough data to allow exercise of neuropsychological rehabilitation based on scientific Class I evidence. From the medical point of view, the purpose of this work is to develop a classificatory tool to identify different populations of patients based on the characteristics of deficit and response to treatment. This Knowledge Discovery problem has been faced by using exogenous clustering based on rules, an hybrid AI and Statistics technique, which combines some Inductive Learning (from AI) with clustering (from Statistics) to extract knowledge from certain complex domains in form of typical profiles. In this paper, the results of applying this technique to a sample of patients with Traumatic Brain Injury are presented and their advantages with regards to other more classical analysis approaches are discussed.