e-ASPECTS software is non-inferior to neuroradiologists in applying the ASPECT score to computed tomography scans of acute ischemic stroke patients

被引：158

作者：

Nagel, Simon ^{[1
]}

Sinha, Devesh ^{[2
]}

Day, Diana ^{[3
]}

Reith, Wolfgang ^{[4
]}

Chapot, Rene ^{[5
]}

Papanagiotou, Panagiotis ^{[6
]}

Warburton, Elizabeth A. ^{[7
]}

Guyler, Paul ^{[2
]}

Tysoe, Sharon ^{[2
]}

Fassbender, Klaus ^{[8
]}

Walter, Silke ^{[8
,9
]}

Essig, Marco ^{[10
]}

Heidenrich, Jens ^{[11
]}

Konstas, Angelos A. ^{[12
]}

Harrison, Michael ^{[13
]}

Papadakis, Michalis ^{[14
]}

Greveson, Eric ^{[14
]}

Joly, Olivier ^{[14
]}

Gerry, Stephen ^{[15
]}

Maguire, Holly ^{[16
]}

Roffe, Christine ^{[16
]}

Hampton-Till, James ^{[13
]}

Buchan, Alastair M. ^{[9
]}

Grunwald, Iris Q. ^{[2
,14
,17
]}

机构：

[1] Univ Hosp Heidelberg, Dept Neurol, Heidelberg, Germany

[2] Southend Univ Hosp NHS, Westcliff On Sea, Essex, England

[3] Addenbrookes Hosp NHS, Cambridge, England

[4] Saarland Univ Hosp, Dept Neuroradiol, Homburg, Germany

[5] Alfred Krupp Krankenhaus, Dept Neuroradiol, Essen, Germany

[6] Bremen Hosp, Dept Neuroradiol, Bremen, Germany

[7] Univ Cambridge, Dept Clin Neurosci, Cambridge, England

[8] Saarland Univ Hosp, Dept Neurol, Homburg, Germany

[9] Univ Oxford, Radcliffe Dept Med, Oxford, England

[10] Univ Manitoba, Dept Radiol, Winnipeg, MB, Canada

[11] Dalhousie Univ, Dept Diagnost Radiol, Halifax, NS, Canada

[12] Huntington Mem Hosp, Dept Radiol, Pasadena, CA USA

[13] Anglia Ruskin Univ, Clin Trials Unit, Cambridge, Essex, England

[14] Brainomix Ltd, Oxford, England

[15] Univ Oxford, Ctr Stat Med, Oxford, England

[16] North Staffordshire Combined Healthcare NHS Trust, Stroke Res, Stoke On Trent, Staffs, England

[17] Anglia Ruskin Univ, Neurosci Dept, Cambridge, Essex, England

来源：

INTERNATIONAL JOURNAL OF STROKE | 2017年 / 12卷 / 06期

关键词：

Alberta Stroke Program Early Computed Tomography Score; computed tomography; ischemic stroke; machine learning; THROMBECTOMY; TRIALS; PREDICTION; OUTCOMES;

D O I：

10.1177/1747493016681020

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

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 x 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, inter-quartile 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.

引用

页码：615 / 622

页数：8

共 17 条

[1] A systematic review and meta-analysis of randomized controlled trials of endovascular thrombectomy compared with best medical treatment for acute ischemic stroke [J].

Balami, Joyce S. ;

Sutherland, Brad A. ;

Edmunds, Laurel D. ;

Grunwald, Iris Q. ;

Neuhaus, Ain A. ;

Hadley, Gina ;

Karbalai, Hasneen ;

Metcalf, Kneale A. ;

DeLuca, Gabriele C. ;

Buchan, Alastair M. .

INTERNATIONAL JOURNAL OF STROKE, 2015, 10 (08) :1168-1178

[2] Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapy [J].

Barber, PA ;

Demchuk, AM ;

Zhang, JJ ;

Buchan, AM .

LANCET, 2000, 355 (9216) :1670-1674

[3] Prediction of stroke thrombolysis outcome using CT brain machine learning [J].

Bentley, Paul ;

Ganesalingam, Jeban ;

Jones, Anoma Lalani Carlton ;

Mahady, Kate ;

Epton, Sarah ;

Rinne, Paul ;

Sharma, Pankaj ;

Halse, Omid ;

Mehta, Amrish ;

Rueckert, Daniel .

NEUROIMAGE-CLINICAL, 2014, 4 :635-640

[4] Adjusted Wald Confidence Interval for a Difference of Binomial Proportions Based on Paired Data [J].

Bonett, Douglas G. ;

Price, Robert M. .

JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS, 2012, 37 (04) :479-488

[5] Endovascular stent thrombectomy: the new standard of care for large vessel ischaemic stroke [J].

Campbell, Bruce C. V. ;

Donnan, Geoffrey A. ;

Lees, Kennedy R. ;

Hacke, Werner ;

Khatri, Pooja ;

Hill, Michael D. ;

Goyal, Mayank ;

Mitchell, Peter J. ;

Saver, Jeffrey L. ;

Diener, Hans-Christoph ;

Davis, Stephen M. .

LANCET NEUROLOGY, 2015, 14 (08) :846-854

[6] Methods for Calculating Sensitivity and Specificity of Clustered Data: A Tutorial [J].

Genders, Tessa S. S. ;

Spronk, Sandra ;

Stijnen, Theo ;

Steyerberg, Ewout W. ;

Lesaffre, Emmanuel ;

Hunink, M. G. Myriam .

RADIOLOGY, 2012, 265 (03) :910-916

[7] Randomized Assessment of Rapid Endovascular Treatment of Ischemic Stroke [J].

Goyal, M. ;

Demchuk, A. M. ;

Menon, B. K. ;

Eesa, M. ;

Rempel, J. L. ;

Thornton, J. ;

Roy, D. ;

Jovin, T. G. ;

Willinsky, R. A. ;

Sapkota, B. L. ;

Dowlatshahi, D. ;

Frei, D. F. ;

Kamal, N. R. ;

Montanera, W. J. ;

Poppe, A. Y. ;

Ryckborst, K. J. ;

Silver, F. L. ;

Shuaib, A. ;

Tampieri, D. ;

Williams, D. ;

Bang, O. Y. ;

Baxter, B. W. ;

Burns, P. A. ;

Choe, H. ;

Heo, J. -H. ;

Holmstedt, C. A. ;

Jankowitz, B. ;

Kelly, M. ;

Linares, G. ;

Mandzia, J. L. ;

Shankar, J. ;

Sohn, S. -I. ;

Swartz, R. H. ;

Barber, P. A. ;

Coutts, S. B. ;

Smith, E. E. ;

Morrish, W. F. ;

Weill, A. ;

Subramaniam, S. ;

Mitha, A. P. ;

Wong, J. H. ;

Lowerison, M. W. ;

Sajobi, T. T. ;

Hill, M. D. .

NEW ENGLAND JOURNAL OF MEDICINE, 2015, 372 (11) :1019-1030

[8] Stroke Neurologist's Perspective on the New Endovascular Trials [J].

Grotta, James C. ;

Hacke, Werner .

STROKE, 2015, 46 (06) :1447-1452

[9]

Hampton-Till James, 2015, EMJ NEUROL, V3, P69, DOI DOI 10.33590/EMJNEUROL/10314991

[10] Performance of e-ASPECTS software in comparison to that of stroke physicians on assessing CT scans of acute ischemic stroke patients [J].

Herweh, Christian ;

Ringleb, Peter A. ;

Rauch, Geraldine ;

Gerry, Steven ;

Behrens, Lars ;

Moehlenbruch, Markus ;

Gottorf, Rebecca ;

Richter, Daniel ;

Schieber, Simon ;

Nagel, Simon .

INTERNATIONAL JOURNAL OF STROKE, 2016, 11 (04) :438-445

← 1 2 →