Jehovah's witnesses (JW) belong to a religious group refusing to accept blood transfusion Surgical treatment remains a challenge in this subset of patients. From 1945, JW introduced a ban on accepting blood transfusions, even in life-threatening situations while autologous blood must also be refused if it is predeposited-thus excluding preoperative autodonation. However, autologous blood is acceptable if it is not separated from the patients' circulation at any time. The invasive nature of coronary artery bypass grafting (CABG), the associated decrease of body temperature and the use of cardiopulmonary bypass (CPB) are major reasons for increased blood loss and high incidence for blood transfusions during and after this procedures. Allogenic blood transfusions are often given and considered necessary in such operations, in spite of increased mortality, morbidity and major adverse outcomes resulting from transfusion. Reduction in the use of blood products should therefore be a general desire for every patient due to the associated risk factors. The evolution of less invasive cardiac surgical approaches, such as CABG without CPB (OPCAB) may contribute to a further reduction of blood transfusion and although these minimally invasive techniques may benefit every patient, they might be particularly valuable for JW. In this report, we present our initial experience in JW patient undergoing OPCAB and the way to use patient blood management for improved surgical outcome in such patient.

This paper presents a visual/motor behavior learning approach, based on neural networks. We propose Behavior Chain Model (BCM) in order to create a way of behavior learning. Our behavior-based system evolution task is a mobile robot detecting a target and driving/acting towards it. First, the mapping relations between the image feature domain of the object and the robot action domain are derived. Second, a multilayer neural network for offline learning of the mapping relations is used. This learning structure through neural network training process represents a connection between the visual perceptions and motor sequence of actions in order to grip a target. Last, using behavior learning through a noticed action chain, we can predict mobile robot behavior for a variety of similar tasks in similar environment. Prediction results suggest that the methodology is adequate and could be recognized as an idea for designing different mobile robot behaviour assistance.