This monograph is an up-to-date, in-depth and more advanced continuation of its accompanying monograph entitled Brain-Body Interactions: Contemporary Outcome Prediction in Aneurysmal Subarachnoid Hemorrhage using Bayesian Neural Networks and Fuzzy Logic. The current monograph is divided into five sections. The first section synthesises the most current evidence of underlying pathophysiologic mechanisms of brain-body associations in aneurysmal subarachnoid hemorrhage. It also describes pathophysiologic manifestations of central autonomic nervous system dysfunctions in ischemic stroke, intracerebral hemorrhage and aneurysmal subarachnoid hemorrhage. The second section synthesises and critically appraises the methodologic quality of existing studies (including prospective and retrospective cohort studies and randomised controlled trials) that derive clinical predictor tools and clinical predictors used to determine outcome prognosis in patients with aneurysmal subarachnoid hemorrhage. The third section makes use of two aneurysmal subarachnoid hemorrhage databases incorporating advances in the treatment of aneurysmal subarachnoid hemorrhage. Both single prognostic factors and brain-body interactions are explored to make several novel observations which significantly influence clinical outcome in patients with ruptured cerebral aneurysms. In its fourth section, clinical prognostic decision-making tools are created using classification and regression tree analysis. Prognostic subgroups demonstrate the interplay of various underlying pathophysiologic mechanisms which, together, adversely influence long-term neurologic and functional outcomes in those with aneurysmal subarachnoid hemorrhage. Finally, in Section Five, exploratory analyses are conducted using artificial neural networks to further explore the brain-body interface in aneurysmal subarachnoid hemorrhage, with in-depth discussions of the autonomic nervous system and its dysfunction in pathologic states. Using these clinical prognostic models, the clinician can tailor individual-specific treatment efforts to prevent and treat various alterations in the brain-body interface in order to maximise the chances of survival and recovery after aneurysmal subarachnoid haemorrhage.

This monograph serves as an in-depth guide to the use of the innovative combination of Bayesian analysis, artificial neural networks and fuzzy logic to create an individualized clinical prediction model applicable to many areas in medicine. This guide assumes no prior knowledge of advanced statistics or clinical medicine. Both the applied research scientist and clinician will be able to follow the clinical case of outcome prediction in ruptured brain aneurysms and apply this innovative prognostication model to different areas in medicine. By using Bayesian neural networks with fuzzy logic inferences, the practitioner can create a system that incorporates one's own experience (Bayesian concepts), recognizes unknown areas in medicine (artificial neural networks) and grey zones in diagnoses and prognoses (fuzzy logic inferences). This monograph also profiles contemporary research advances in the diagnosis and treatment of aneurysmal subarachnoid hemorrhage. Application of this clinical prediction modelling system to the case of ruptured brain aneurysms has led to clarification of clinical prognostication in this area, as well as discovery of brain-body interactions that are important in influencing outcome in these patients. The potential impact of such monograph is to demonstrate how to create such clinical outcome prediction model, as well to help find new prognostic factors and brain-body interactions, that when recognized and treated early, can lead to better clinical outcome for the patient.