Stroke damage detection using classification trees on electrical bioimpedance cerebral spectroscopy measurements.

Seyed Atefi,Fernando Seoane,Kaj Lindecrantz,Thorleif Thorlin

doi:10.3390/s130810074

Abstract

After cancer and cardio-vascular disease, stroke is the third greatest cause of death worldwide. Given the limitations of the current imaging technologies used for stroke diagnosis, the need for portable non-invasive and less expensive diagnostic tools is crucial. Previous studies have suggested that electrical bioimpedance (EBI) measurements from the head might contain useful clinical information related to changes produced in the cerebral tissue after the onset of stroke. In this study, we recorded 720 EBI Spectroscopy (EBIS) measurements from two different head regions of 18 hemispheres of nine subjects. Three of these subjects had suffered a unilateral haemorrhagic stroke. A number of features based on structural and intrinsic frequency-dependent properties of the cerebral tissue were extracted. These features were then fed into a classification tree. The results show that a full classification of damaged and undamaged cerebral tissue was achieved after three hierarchical classification steps. Lastly, the performance of the classification tree was assessed using Leave-One-Out Cross Validation (LOO-CV). Despite the fact that the results of this study are limited to a small database, and the observations obtained must be verified further with a larger cohort of patients, these findings confirm that EBI measurements contain useful information for assessing on the health of brain tissue after stroke and supports the hypothesis that classification features based on Cole parameters, spectral information and the geometry of EBIS measurements are useful to differentiate between healthy and stroke damaged brain tissue.

Highlights

Stroke is the third greatest cause of death worldwide [1] and the cause of severe suffering to the surviving individuals with neurological deficits and a significant economic burden to society
Several previous studies have demonstrated the ability of electrical bioimpedance measurements at a single frequency of 50 kHz to detect haematoma and oedema as the principal indicators of stroke [33,34]
Several previous studies have shown that EBI Spectroscopy (EBIS) measurements contain useful information on tissue characteristics and structure, providing features suitable for an automated classification of healthy/damaged tissue and, in particular, cerebral tissue [37,46,54]

Summary

Introduction

Stroke is the third greatest cause of death worldwide [1] and the cause of severe suffering to the surviving individuals with neurological deficits and a significant economic burden to society. Stroke patients usually require the prompt intervention of clinical staff to prevent permanent lesions from developing. A time window of 3–4.5 h is usually required for certain treatments after the onset of stroke to maximise the treatment benefits and avoid permanent neurological impairment [4,5]. Every effort should be made to shorten the delay of the onset of therapy following stroke. Many diagnostic tools, such as magnetic resonance imaging, X-ray or computer tomography are not accessible until patients reach a hospital, delaying the initiation of proper neural rescue therapies

Methods

Results

Conclusion