TY - JOUR
T1 - e-ASPECTS software is non-inferior to neuroradiologists in applying the ASPECT score to computed tomography scans of acute ischemic stroke patients
AU - Nagel, Simon
AU - Sinha, Devesh
AU - Day, Diana
AU - Reith, Wolfgang
AU - Chapot, René
AU - Papanagiotou, Panagiotis
AU - Warburton, Elizabeth A.
AU - Guyler, Paul
AU - Tysoe, Sharon
AU - Fassbender, Klaus
AU - Walter, Silke
AU - Essig, Marco
AU - Heidenrich, Jens
AU - Konstas, Angelos A.
AU - Harrison, Michael
AU - Papadakis, Michalis
AU - Greveson, Eric
AU - Joly, Olivier
AU - Gerry, Stephen
AU - Maguire, Holly
AU - Roffe, Christine
AU - Hampton-Till, James
AU - Buchan, Alastair M.
AU - Grunwald, Iris Q.
N1 - Publisher Copyright:
© 2016, © 2016 World Stroke Organization.
PY - 2017/8/1
Y1 - 2017/8/1
N2 - Background: The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is an established 10-point quantitative topographic computed tomography scan score to assess early ischemic changes. We performed a non-inferiority trial between the e-ASPECTS software and neuroradiologists in scoring ASPECTS on non-contrast enhanced computed tomography images of acute ischemic stroke patients.Methods: In this multicenter study, e-ASPECTS and three independent neuroradiologists retrospectively and blindly assessed baseline non-contrast enhanced computed tomography images of 132 patients with acute anterior circulation ischemic stroke. Follow-up scans served as ground truth to determine the definite area of infarction. Sensitivity, specificity, and accuracy for region- and score-based analysis, receiver-operating characteristic curves, Bland-Altman plots and Matthews correlation coefficients relative to the ground truth were calculated and comparisons were made between neuroradiologists and different pre-specified e-ASPECTS operating points. The non-inferiority margin was set to 10% for both sensitivity and specificity on region-based analysis.Results: In total 2640 (132 patients × 20 regions per patient) ASPECTS regions were scored. Mean time from onset to baseline computed tomography was 146 ± 124 min and median NIH Stroke Scale (NIHSS) was 11 (6–17, interquartile range). Median ASPECTS for ground truth on follow-up imaging was 8 (6.5–9, interquartile range). In the region-based analysis, two e-ASPECTS operating points (sensitivity, specificity, and accuracy of 44%, 93%, 87% and 44%, 91%, 85%) were statistically non-inferior to all three neuroradiologists (all p-values <0.003). Both Matthews correlation coefficients for e-ASPECTS were higher (0.36 and 0.34) than those of all neuroradiologists (0.32, 0.31, and 0.3).Conclusions: e-ASPECTS was non-inferior to three neuroradiologists in scoring ASPECTS on non-contrast enhanced computed tomography images of acute stroke patients.
AB - Background: The Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is an established 10-point quantitative topographic computed tomography scan score to assess early ischemic changes. We performed a non-inferiority trial between the e-ASPECTS software and neuroradiologists in scoring ASPECTS on non-contrast enhanced computed tomography images of acute ischemic stroke patients.Methods: In this multicenter study, e-ASPECTS and three independent neuroradiologists retrospectively and blindly assessed baseline non-contrast enhanced computed tomography images of 132 patients with acute anterior circulation ischemic stroke. Follow-up scans served as ground truth to determine the definite area of infarction. Sensitivity, specificity, and accuracy for region- and score-based analysis, receiver-operating characteristic curves, Bland-Altman plots and Matthews correlation coefficients relative to the ground truth were calculated and comparisons were made between neuroradiologists and different pre-specified e-ASPECTS operating points. The non-inferiority margin was set to 10% for both sensitivity and specificity on region-based analysis.Results: In total 2640 (132 patients × 20 regions per patient) ASPECTS regions were scored. Mean time from onset to baseline computed tomography was 146 ± 124 min and median NIH Stroke Scale (NIHSS) was 11 (6–17, interquartile range). Median ASPECTS for ground truth on follow-up imaging was 8 (6.5–9, interquartile range). In the region-based analysis, two e-ASPECTS operating points (sensitivity, specificity, and accuracy of 44%, 93%, 87% and 44%, 91%, 85%) were statistically non-inferior to all three neuroradiologists (all p-values <0.003). Both Matthews correlation coefficients for e-ASPECTS were higher (0.36 and 0.34) than those of all neuroradiologists (0.32, 0.31, and 0.3).Conclusions: e-ASPECTS was non-inferior to three neuroradiologists in scoring ASPECTS on non-contrast enhanced computed tomography images of acute stroke patients.
KW - Alberta Stroke Program Early Computed Tomography Score
KW - computed tomography
KW - ischemic stroke
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85025454076&partnerID=8YFLogxK
U2 - 10.1177/1747493016681020
DO - 10.1177/1747493016681020
M3 - Article
C2 - 27899743
AN - SCOPUS:85025454076
SN - 1747-4930
VL - 12
SP - 615
EP - 622
JO - International Journal of Stroke
JF - International Journal of Stroke
IS - 6
ER -
