Key result
Spectral clustering of Transcranial Doppler waveforms identified four distinct morphological clusters, with types III and IV primarily deriving from patients with Large Vessel Occlusion.
Why the study?
TIBI flow grades for cerebrovascular occlusion require subjective assessment by expert evaluators to be reliable, prompting evaluation of an objective, unsupervised machine learning approach for TCD waveform categorization.
Does automated classification of Transcranial Doppler waveform morphology via spectral clustering identify Large Vessel Occlusion in subjects at risk for acute ischemic stroke?
Observational (n=106)
Yes
Does automated classification of Transcranial Doppler waveform morphology via spectral clustering identify Large Vessel Occlusion in subjects at risk for acute ischemic stroke?
Unsupervised machine learning can objectively classify Transcranial Doppler waveforms into distinct flow types that correlate with Large Vessel Occlusion, potentially improving automated real-time stroke assessment.
TCD waveform clustering was associated with LVO; hypothesis-generating and requires prospective validation before clinical use.
Cerebral Blood Flow Velocity waveforms acquired via Transcranial Doppler (TCD) can provide evidence for cerebrovascular occlusion and stenosis. Thrombolysis in Brain Ischemia (TIBI) flow grades are widely used for this purpose, but require subjective assessment by expert evaluators to be reliable. In this work we seek to determine whether TCD morphology can be objectively assessed using an unsupervised machine learning approach to waveform categorization. TCD beat waveforms were recorded at multiple depths from the Middle Cerebral Arteries of 106 subjects; 33 with CTA-confirmed Large Vessel Occlusion (LVO). From each waveform, three morphological variables were extracted, quantifying absolute peak onset, number/prominence of auxiliary peaks, and systolic canopy length. Spectral clustering identified groups implicit in the resultant three-dimensional feature space, with gap-statistic criteria establishing the optimal cluster number. We found that gap-statistic disparity was maximized at four clusters, referred to as flow types I, II, III, and IV. Types I and II were primarily composed of control subject waveforms, whereas types III and IV derived mainly from LVO patients. Cluster morphologies for types I and IV aligned clearly with Normal and Blunted TIBI flows, respectively. Types II and III represented commonly observed flow-types not delineated by TIBI, which nonetheless deviate quantifiably from normal and blunted flows. We conclude that important morphological variability exists beyond that currently quantified by TIBI in populations experiencing or at-risk for acute ischemic stroke, and posit that the observed flow-types provide the foundation for objective methods of real-time automated flow type classification.
No takes yet. Share an insight, caveat, or question.
Thorpe et al. (2019) conducted an observational in Large Vessel Occlusion (n=106). Spectral clustering of TCD waveforms vs. Control subjects was evaluated on Optimal number of clusters based on gap-statistic criteria. Spectral clustering of Transcranial Doppler waveforms identified four distinct morphological clusters, with types III and IV primarily deriving from patients with Large Vessel Occlusion.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: