Identifying Pathophysiological Intracranial Pressure Waveforms via Fully Convolutional Classification

It is generally assumed that the analysis of intracranial pressure (ICP) waveforms could be used for the detection of multiple cerebral pathophysiologies. In this study we will demonstrate that ICP waveform analysis utilizing a convolutional neural network (CNN) can be used to distinguish between an intact cerebral compliance and a diminished one. A main obstacle for the analysis of ICP waveforms is given by the large variation of their generating signal, the arterial blood pressure (ABP). Using extended principal component analysis (PCA) we will demonstrate that it is possible to distinguish between ICP waveforms generated by pathophysiological ABP wave forms, for example in case of a heart failure, without loosing the information about the state of the cerebral compliance.