A Data-Driven Approach to Transfer Function Analysis for Superior Discriminative Power: Optimized Assessment of Dynamic Cerebral Autoregulation.

Transfer function analysis (TFA) is extensively used to assess human physiological functions. However, extracting parameters from TFA is not usually optimized for detecting impaired function. In this study, we propose to use data-driven approaches to improve the performance of TFA in assessing blood flow control in the brain (dynamic cerebral autoregulation, dCA). Data were collected from two distinct groups of subjects deemed to have normal and impaired dCA. Continuous arterial blood pressure (ABP) and cerebral blood flow velocity (CBFV) were simultaneously recorded for approximately 10 mins in 82 subjects (including 41 healthy controls) to give 328 labeled samples of the TFA variables. The recordings were further divided into 4,294 short data segments to generate 17,176 unlabeled samples of the TFA variables. We optimized TFA post-processing with a generic semi-supervised learning strategy and a novel semi-supervised stacked ensemble learning (SSEL) strategy for classification into normal and impaired dCA. The generic strategy led to a performance with no significant difference to that of the conventional dCA analysis methods, whereas the proposed new strategy boosted the performance of TFA to an accuracy of 93.3%. To our knowledge, this is the best dCA discrimination performance obtained to date and the first attempt at optimizing TFA through machine learning techniques. Equivalent methods can potentially also be applied to assessing a wide spectrum of other human physiological functions.

Xenon-enhanced CT assessment of cerebral blood flow in stroke-in-progress patients with unilateral internal carotid artery or middle cerebral artery stenosis.

Carotid or cerebral artery stenosis resulting in low perfusion is a major cause of ischemic stroke. Understanding the unique hemodynamic features in each patient undergoing a stroke-in-progress (SIP) and the correlation between progression and cerebral blood flow (CBF) status would help in the diagnosis and treatment of individual patients. We used xenon-enhanced CT (Xe-CT) to examine cerebral perfusion in patients with or without SIP (30 patients/group), recruited from October 2009 to October 2010. Only SIP patients with unilateral stenosis in the internal or middle cerebral artery were recruited. The occurrence of watershed infarction was higher in the SIP group than in the non-SIP group (P <0.05). In the SIP group, larger hypoperfused areas were found around the lesions than in the non-SIP group. In the SIP group, the CBF values in the ipsilateral areas were significantly lower than those in corresponding regions on the contralateral side. CBF values in the contralateral hemisphere were significantly lower in the SIP group than in the non-SIP group. In SIP patients, infarctions were surrounded by larger hypoperfused areas than in non-SIP patients. These larger hypoperfused areas may result in pathological damage to the brain that is responsible for the progression of stroke.