Introduction of an embolus detection system based on analysis of the transcranial Doppler audio-signal

Abstract

A new embolus detection system (EDS) is presented, built with the intention of detecting ongoing cerebral embolization in patients at risk of transient ischaemic attacks or stroke. It is based on the analysis of the audio-Doppler signal of a transcranial Doppler machine. The algorithm of the EDS estimates the intensity, duration and zero-crossing dynamics of the audio signal. The EDS has a multi-layer neural network which classifies events into micro-emboli signals (MES) or artefacts. The decision-making component of the software has been validated against human experts. Data from patients in the post-operative phase of carotid surgery were used for the validation process. The results showed agreement in MES and artefact classification of > 93%. Apart from a monitoring display, the monitoring system includes a verification unit that allows the user to listen and to look at all data of individual MES and artefacts. Moreover, the system allows the user to record, store and re-calculate all data files. Data are stored using European Data Format, which allows data transportation over the Internet. The EDS may have a potential in stroke risk stratification, evaluating the effect of novel anti-thrombotic therapies, and in peri-operative and remote monitoring of carotid endarterectomy.

Validation of the Automated Electronic Microemboli Detection System in Patients Undergoing Carotid Endarterectomy

“…The EDS allows off-line analysis of the intensity, duration and zero crossing index of all recorded MES. [16] The amplitude intensity threshold for recording events was set for a minimum of 2.5 decibel (dB). Technical details of intraoperative [20] and postoperative [21] monitoring have been described previously.…”

“…The HE did not only listen to the actual sound of the recorded events but was supplied with all available data of the audio signal (as zero crossing index (ZCI)) and Fast Fourier transform (FFT) (as duration, intensity, and velocity display). Technical details are described in the introducing study of the automatic EDS [16]. Within the display of the ZCI a zoom function was available to see all details of the event at different time scales.…”

“…The performance of these systems varies: sensitivities ranging from 44 -97 % when compared to an expert panel have been reported [14,15]. One of the latest developments is the 'Versatile Embolic Detection System (EDS; Keunen Medical Software BV, the Netherlands) [16]. Unlike other automatic emboli detection programs, the algorithm of EDS uses the information given by the zero crossing frequency of the audio Doppler signal and only uses the fast Fourier transform (FFT) as visual support for later analysis by human experts.…”

“…Unlike other automatic emboli detection programs, the algorithm of EDS uses the information given by the zero crossing frequency of the audio Doppler signal and only uses the fast Fourier transform (FFT) as visual support for later analysis by human experts. Classification of audio signals is performed within a multi-layer neural network, examining the duration and intensity of the audio signal and the zero-crossing characteristics [16]. All events are recorded and can be viewed and analysed retrospectively.…”

“…This software has been validated in postoperative CEA patients who were conscious and able to follow instructions [16]. Up to now, as we are aware, the EDS software has not yet been validated for perioperative TCD monitoring in which gaseous emboli and procedure related artefacts can be expected.…”