Autonomous intelligent systems are starting to influence clinical practice, as ways to both readily exploit experts'knowledge when contextual conditions demand so, and harness the overwhelming amount of patient related data currently at clinicians'disposal. However, these two approaches are rarely synergistically exploited, and tend to be used without integration. In this paper, we follow recent efforts reported in the literature regarding integration of BDI agency with machine learning based Cognitive Services, by proposing an integration architecture, and by validating such architecture in the complex domain of trauma management. In particular, we show that augmentation of a BDI agent, endowed with predefined plans encoding experts'knowledge, with a Cognitive Service, trained on past observed data, can enhance trauma management by reducing over triage episodes.