Objective Assessment of Beat Quality in Transcranial Doppler Measurement of Blood Flow Velocity in Cerebral Arteries

Abstract

ObjectiveTranscranial Doppler (TCD) ultrasonography measures pulsatile cerebral blood flow velocity in the arteries and veins of the head and neck. Similar to other real-time measurement modalities, especially in healthcare, the identification of high quality signals is essential for clinical interpretation. Our goal is to identify poor quality beats and remove them prior to further analysis of the TCD signal. MethodsWe selected objective features for this purpose including Euclidean distance between individual and average beat waveform, cross-correlation between individual and average beat waveform, ratio of the high frequency power to the total beat power, beat length, and variance of the diastolic portion of the beat waveform. We developed an iterative outlier detection algorithm to identify and remove the beats that are different from others in a recording. Finally, we tested the algorithm on a dataset consisting of more than 16 hours of TCD data recorded from 48 stroke and 35 in-hospital control subjects. ResultsWe assessed the performance of the algorithm in estimating clinically important TCD parameters by comparison to those identified from beats hand-annotated by an expert. The results show that there is strong correlation between the two that delineates the algorithm has successfully recovered clinically important features. We obtained significant improvement in estimating the TCD parameters using the algorithm accepted beats compared to using all beats (r>0.78, p<0.01). SignificanceOur algorithm provides a valuable tool to the clinicians for automated detection of the reliable portion of the data. Moreover, it can be used as a pre-processing tool to improve the data quality for machine learning algorithms for automated diagnosis of pathologic beat waveform.