AustralieFrV1, PascalFrancis, Corpus, bibRecord, 003210

Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method

Identifieur interne : 003210 ( PascalFrancis/Corpus ); précédent : 003209; suivant : 003211

Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method

Auteurs : Stefan Klöppel ; Cynthia M. Stonnington ; Josephine Barnes ; Frederick Chen ; Carlton Chu ; Catriona D. Good ; Irina Mader ; L. Anne Mitchell ; Ameet C. Patel ; Catherine C. Roberts ; Nick C. Fox ; Clifford R. Jr Jack ; John Ashburner ; Richard S. J. Frackowiak

Source :

Brain [ 0006-8950 ] ; 2008.

RBID : Pascal:08-0521915

Descripteurs français

Pascal (Inist)
- Démence, Pathologie du système nerveux, Précision, Diagnostic, Etude comparative, Radiologue, Imagerie RMN, Vecteur.

English descriptors

KwdEn :
- Accuracy, Comparative study, Dementia, Diagnosis, Nervous system diseases, Nuclear magnetic resonance imaging, Radiologist, Vector.

Abstract

There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0006-8950`
A03		`1`		`@0 Brain`
A05				`@2 131`
A06				`@3 p. 11`
A08	`01`	`1`	`ENG`	`@1 Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method`
A11	`01`	`1`		`@1 KLÖPPEL (Stefan)`
A11	`02`	`1`		`@1 STONNINGTON (Cynthia M.)`
A11	`03`	`1`		`@1 BARNES (Josephine)`
A11	`04`	`1`		`@1 CHEN (Frederick)`
A11	`05`	`1`		`@1 CHU (Carlton)`
A11	`06`	`1`		`@1 GOOD (Catriona D.)`
A11	`07`	`1`		`@1 MADER (Irina)`
A11	`08`	`1`		`@1 MITCHELL (L. Anne)`
A11	`09`	`1`		`@1 PATEL (Ameet C.)`
A11	`10`	`1`		`@1 ROBERTS (Catherine C.)`
A11	`11`	`1`		`@1 FOX (Nick C.)`
A11	`12`	`1`		`@1 JACK (Clifford R. JR)`
A11	`13`	`1`		`@1 ASHBURNER (John)`
A11	`14`	`1`		`@1 FRACKOWIAK (Richard S. J.)`
A14	`01`			`@1 Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg @2 Freiburg @3 DEU @Z 1 aut.`
A14	`02`			`@1 Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London @2 London @3 GBR @Z 1 aut. @Z 2 aut. @Z 5 aut. @Z 13 aut. @Z 14 aut.`
A14	`03`			`@1 Department of Psychiatry and Psychology, Mayo Clinic @2 Scottsdale, AZ @3 USA @Z 2 aut.`
A14	`04`			`@1 Dementia Research Centre, University College London, Institute of Neurology @2 London @3 GBR @Z 3 aut. @Z 8 aut. @Z 11 aut.`
A14	`05`			`@1 Department of Radiology, Mayo Clinic @2 Scottsdale, AZ @3 USA @Z 4 aut. @Z 9 aut. @Z 10 aut.`
A14	`06`			`@1 Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath @2 West Sussex @3 GBR @Z 6 aut.`
A14	`07`			`@1 Department of Neuroradiology, University Clinic Freiburg @2 Freiburg @3 DEU @Z 7 aut.`
A14	`08`			`@1 Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg @2 Freiburg @3 DEU @Z 7 aut.`
A14	`09`			`@1 Department of Radiology, Austin Health @2 Heidelberg @3 DEU @Z 8 aut.`
A14	`10`			`@1 Department of Radiology, University of Melbourne @2 Melbourne @3 AUS @Z 8 aut.`
A14	`11`			`@1 Department of Radiology, Mayo Clinic @2 Rochester @3 USA @Z 12 aut.`
A14	`12`			`@1 Département d'études cognitives, Ecole Normale Supérieure @2 Paris @3 FRA @Z 14 aut.`
A14	`13`			`@1 Laboratory of Neuroimaging, IRCCS Santa Lucia @2 Roma @3 ITA @Z 14 aut.`
A20				`@1 2969-2974`
A21				`@1 2008`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 998 @5 354000184307520160`
A44				`@0 0000 @1 © 2008 INIST-CNRS. All rights reserved.`
A45				`@0 3/4 p.`
A47	`01`	`1`		`@0 08-0521915`
A60				`@1 P`
A61				`@0 A`
A64	`01`	`1`		`@0 Brain`
A66	`01`			`@0 GBR`
C01	`01`		`ENG`	@0 There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.
C02	`01`	`X`		`@0 002B17`
C02	`02`	`X`		`@0 002B17G`
C03	`01`	`X`	`FRE`	`@0 Démence @5 01`
C03	`01`	`X`	`ENG`	`@0 Dementia @5 01`
C03	`01`	`X`	`SPA`	`@0 Demencia @5 01`
C03	`02`	`X`	`FRE`	`@0 Pathologie du système nerveux @5 02`
C03	`02`	`X`	`ENG`	`@0 Nervous system diseases @5 02`
C03	`02`	`X`	`SPA`	`@0 Sistema nervioso patología @5 02`
C03	`03`	`X`	`FRE`	`@0 Précision @5 09`
C03	`03`	`X`	`ENG`	`@0 Accuracy @5 09`
C03	`03`	`X`	`SPA`	`@0 Precisión @5 09`
C03	`04`	`X`	`FRE`	`@0 Diagnostic @5 10`
C03	`04`	`X`	`ENG`	`@0 Diagnosis @5 10`
C03	`04`	`X`	`SPA`	`@0 Diagnóstico @5 10`
C03	`05`	`X`	`FRE`	`@0 Etude comparative @5 11`
C03	`05`	`X`	`ENG`	`@0 Comparative study @5 11`
C03	`05`	`X`	`SPA`	`@0 Estudio comparativo @5 11`
C03	`06`	`X`	`FRE`	`@0 Radiologue @5 12`
C03	`06`	`X`	`ENG`	`@0 Radiologist @5 12`
C03	`06`	`X`	`SPA`	`@0 Radiólogo @5 12`
C03	`07`	`X`	`FRE`	`@0 Imagerie RMN @5 13`
C03	`07`	`X`	`ENG`	`@0 Nuclear magnetic resonance imaging @5 13`
C03	`07`	`X`	`SPA`	`@0 Imaginería RMN @5 13`
C03	`08`	`X`	`FRE`	`@0 Vecteur @5 14`
C03	`08`	`X`	`ENG`	`@0 Vector @5 14`
C03	`08`	`X`	`SPA`	`@0 Vector @5 14`
C07	`01`	`X`	`FRE`	`@0 Maladie dégénérative @5 37`
C07	`01`	`X`	`ENG`	`@0 Degenerative disease @5 37`
C07	`01`	`X`	`SPA`	`@0 Enfermedad degenerativa @5 37`
N21				`@1 343`
N44	`01`			`@1 OTO`
N82				`@1 OTO`

Format Inist (serveur)

NO :	PASCAL 08-0521915 INIST
ET :	Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method
AU :	KLÖPPEL (Stefan); STONNINGTON (Cynthia M.); BARNES (Josephine); CHEN (Frederick); CHU (Carlton); GOOD (Catriona D.); MADER (Irina); MITCHELL (L. Anne); PATEL (Ameet C.); ROBERTS (Catherine C.); FOX (Nick C.); JACK (Clifford R. JR); ASHBURNER (John); FRACKOWIAK (Richard S. J.)
AF :	Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg/Freiburg/Allemagne (1 aut.); Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London/London/Royaume-Uni (1 aut., 2 aut., 5 aut., 13 aut., 14 aut.); Department of Psychiatry and Psychology, Mayo Clinic/Scottsdale, AZ/Etats-Unis (2 aut.); Dementia Research Centre, University College London, Institute of Neurology/London/Royaume-Uni (3 aut., 8 aut., 11 aut.); Department of Radiology, Mayo Clinic/Scottsdale, AZ/Etats-Unis (4 aut., 9 aut., 10 aut.); Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath/West Sussex/Royaume-Uni (6 aut.); Department of Neuroradiology, University Clinic Freiburg/Freiburg/Allemagne (7 aut.); Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg/Freiburg/Allemagne (7 aut.); Department of Radiology, Austin Health/Heidelberg/Allemagne (8 aut.); Department of Radiology, University of Melbourne/Melbourne/Australie (8 aut.); Department of Radiology, Mayo Clinic/Rochester/Etats-Unis (12 aut.); Département d'études cognitives, Ecole Normale Supérieure/Paris/France (14 aut.); Laboratory of Neuroimaging, IRCCS Santa Lucia/Roma/Italie (14 aut.)
DT :	Publication en série; Niveau analytique
SO :	Brain; ISSN 0006-8950; Royaume-Uni; Da. 2008; Vol. 131; No. p. 11; Pp. 2969-2974; Bibl. 3/4 p.
LA :	Anglais
EA :	There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.
CC :	002B17; 002B17G
FD :	Démence; Pathologie du système nerveux; Précision; Diagnostic; Etude comparative; Radiologue; Imagerie RMN; Vecteur
FG :	Maladie dégénérative
ED :	Dementia; Nervous system diseases; Accuracy; Diagnosis; Comparative study; Radiologist; Nuclear magnetic resonance imaging; Vector
EG :	Degenerative disease
SD :	Demencia; Sistema nervioso patología; Precisión; Diagnóstico; Estudio comparativo; Radiólogo; Imaginería RMN; Vector
LO :	INIST-998.354000184307520160
ID :	08-0521915

Links to Exploration step

Pascal:08-0521915

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method</title>
<author><name sortKey="Kloppel, Stefan" sort="Kloppel, Stefan" uniqKey="Kloppel S" first="Stefan" last="Klöppel">Stefan Klöppel</name>
<affiliation><inist:fA14 i1="01"><s1>Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Stonnington, Cynthia M" sort="Stonnington, Cynthia M" uniqKey="Stonnington C" first="Cynthia M." last="Stonnington">Cynthia M. Stonnington</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="03"><s1>Department of Psychiatry and Psychology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Barnes, Josephine" sort="Barnes, Josephine" uniqKey="Barnes J" first="Josephine" last="Barnes">Josephine Barnes</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Chen, Frederick" sort="Chen, Frederick" uniqKey="Chen F" first="Frederick" last="Chen">Frederick Chen</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Chu, Carlton" sort="Chu, Carlton" uniqKey="Chu C" first="Carlton" last="Chu">Carlton Chu</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Good, Catriona D" sort="Good, Catriona D" uniqKey="Good C" first="Catriona D." last="Good">Catriona D. Good</name>
<affiliation><inist:fA14 i1="06"><s1>Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath</s1>
<s2>West Sussex</s2>
<s3>GBR</s3>
<sZ>6 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Mader, Irina" sort="Mader, Irina" uniqKey="Mader I" first="Irina" last="Mader">Irina Mader</name>
<affiliation><inist:fA14 i1="07"><s1>Department of Neuroradiology, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="08"><s1>Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Mitchell, L Anne" sort="Mitchell, L Anne" uniqKey="Mitchell L" first="L. Anne" last="Mitchell">L. Anne Mitchell</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="09"><s1>Department of Radiology, Austin Health</s1>
<s2>Heidelberg</s2>
<s3>DEU</s3>
<sZ>8 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="10"><s1>Department of Radiology, University of Melbourne</s1>
<s2>Melbourne</s2>
<s3>AUS</s3>
<sZ>8 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Patel, Ameet C" sort="Patel, Ameet C" uniqKey="Patel A" first="Ameet C." last="Patel">Ameet C. Patel</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Roberts, Catherine C" sort="Roberts, Catherine C" uniqKey="Roberts C" first="Catherine C." last="Roberts">Catherine C. Roberts</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Fox, Nick C" sort="Fox, Nick C" uniqKey="Fox N" first="Nick C." last="Fox">Nick C. Fox</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Jack, Clifford R Jr" sort="Jack, Clifford R Jr" uniqKey="Jack C" first="Clifford R. Jr" last="Jack">Clifford R. Jr Jack</name>
<affiliation><inist:fA14 i1="11"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Rochester</s2>
<s3>USA</s3>
<sZ>12 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Ashburner, John" sort="Ashburner, John" uniqKey="Ashburner J" first="John" last="Ashburner">John Ashburner</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Frackowiak, Richard S J" sort="Frackowiak, Richard S J" uniqKey="Frackowiak R" first="Richard S. J." last="Frackowiak">Richard S. J. Frackowiak</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="12"><s1>Département d'études cognitives, Ecole Normale Supérieure</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="13"><s1>Laboratory of Neuroimaging, IRCCS Santa Lucia</s1>
<s2>Roma</s2>
<s3>ITA</s3>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">08-0521915</idno>
<date when="2008">2008</date>
<idno type="stanalyst">PASCAL 08-0521915 INIST</idno>
<idno type="RBID">Pascal:08-0521915</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">003210</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method</title>
<author><name sortKey="Kloppel, Stefan" sort="Kloppel, Stefan" uniqKey="Kloppel S" first="Stefan" last="Klöppel">Stefan Klöppel</name>
<affiliation><inist:fA14 i1="01"><s1>Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Stonnington, Cynthia M" sort="Stonnington, Cynthia M" uniqKey="Stonnington C" first="Cynthia M." last="Stonnington">Cynthia M. Stonnington</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="03"><s1>Department of Psychiatry and Psychology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Barnes, Josephine" sort="Barnes, Josephine" uniqKey="Barnes J" first="Josephine" last="Barnes">Josephine Barnes</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Chen, Frederick" sort="Chen, Frederick" uniqKey="Chen F" first="Frederick" last="Chen">Frederick Chen</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Chu, Carlton" sort="Chu, Carlton" uniqKey="Chu C" first="Carlton" last="Chu">Carlton Chu</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Good, Catriona D" sort="Good, Catriona D" uniqKey="Good C" first="Catriona D." last="Good">Catriona D. Good</name>
<affiliation><inist:fA14 i1="06"><s1>Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath</s1>
<s2>West Sussex</s2>
<s3>GBR</s3>
<sZ>6 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Mader, Irina" sort="Mader, Irina" uniqKey="Mader I" first="Irina" last="Mader">Irina Mader</name>
<affiliation><inist:fA14 i1="07"><s1>Department of Neuroradiology, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="08"><s1>Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Mitchell, L Anne" sort="Mitchell, L Anne" uniqKey="Mitchell L" first="L. Anne" last="Mitchell">L. Anne Mitchell</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="09"><s1>Department of Radiology, Austin Health</s1>
<s2>Heidelberg</s2>
<s3>DEU</s3>
<sZ>8 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="10"><s1>Department of Radiology, University of Melbourne</s1>
<s2>Melbourne</s2>
<s3>AUS</s3>
<sZ>8 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Patel, Ameet C" sort="Patel, Ameet C" uniqKey="Patel A" first="Ameet C." last="Patel">Ameet C. Patel</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Roberts, Catherine C" sort="Roberts, Catherine C" uniqKey="Roberts C" first="Catherine C." last="Roberts">Catherine C. Roberts</name>
<affiliation><inist:fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Fox, Nick C" sort="Fox, Nick C" uniqKey="Fox N" first="Nick C." last="Fox">Nick C. Fox</name>
<affiliation><inist:fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Jack, Clifford R Jr" sort="Jack, Clifford R Jr" uniqKey="Jack C" first="Clifford R. Jr" last="Jack">Clifford R. Jr Jack</name>
<affiliation><inist:fA14 i1="11"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Rochester</s2>
<s3>USA</s3>
<sZ>12 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Ashburner, John" sort="Ashburner, John" uniqKey="Ashburner J" first="John" last="Ashburner">John Ashburner</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Frackowiak, Richard S J" sort="Frackowiak, Richard S J" uniqKey="Frackowiak R" first="Richard S. J." last="Frackowiak">Richard S. J. Frackowiak</name>
<affiliation><inist:fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="12"><s1>Département d'études cognitives, Ecole Normale Supérieure</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
<affiliation><inist:fA14 i1="13"><s1>Laboratory of Neuroimaging, IRCCS Santa Lucia</s1>
<s2>Roma</s2>
<s3>ITA</s3>
<sZ>14 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Brain</title>
<title level="j" type="abbreviated">Brain</title>
<idno type="ISSN">0006-8950</idno>
<imprint><date when="2008">2008</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Brain</title>
<title level="j" type="abbreviated">Brain</title>
<idno type="ISSN">0006-8950</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Accuracy</term>
<term>Comparative study</term>
<term>Dementia</term>
<term>Diagnosis</term>
<term>Nervous system diseases</term>
<term>Nuclear magnetic resonance imaging</term>
<term>Radiologist</term>
<term>Vector</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Démence</term>
<term>Pathologie du   système nerveux</term>
<term>Précision</term>
<term>Diagnostic</term>
<term>Etude comparative</term>
<term>Radiologue</term>
<term>Imagerie RMN</term>
<term>Vecteur</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0006-8950</s0>
</fA01>
<fA03 i2="1"><s0>Brain</s0>
</fA03>
<fA05><s2>131</s2>
</fA05>
<fA06><s3>p. 11</s3>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>KLÖPPEL (Stefan)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>STONNINGTON (Cynthia M.)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>BARNES (Josephine)</s1>
</fA11>
<fA11 i1="04" i2="1"><s1>CHEN (Frederick)</s1>
</fA11>
<fA11 i1="05" i2="1"><s1>CHU (Carlton)</s1>
</fA11>
<fA11 i1="06" i2="1"><s1>GOOD (Catriona D.)</s1>
</fA11>
<fA11 i1="07" i2="1"><s1>MADER (Irina)</s1>
</fA11>
<fA11 i1="08" i2="1"><s1>MITCHELL (L. Anne)</s1>
</fA11>
<fA11 i1="09" i2="1"><s1>PATEL (Ameet C.)</s1>
</fA11>
<fA11 i1="10" i2="1"><s1>ROBERTS (Catherine C.)</s1>
</fA11>
<fA11 i1="11" i2="1"><s1>FOX (Nick C.)</s1>
</fA11>
<fA11 i1="12" i2="1"><s1>JACK (Clifford R. JR)</s1>
</fA11>
<fA11 i1="13" i2="1"><s1>ASHBURNER (John)</s1>
</fA11>
<fA11 i1="14" i2="1"><s1>FRACKOWIAK (Richard S. J.)</s1>
</fA11>
<fA14 i1="01"><s1>Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA14 i1="02"><s1>Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>5 aut.</sZ>
<sZ>13 aut.</sZ>
<sZ>14 aut.</sZ>
</fA14>
<fA14 i1="03"><s1>Department of Psychiatry and Psychology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
</fA14>
<fA14 i1="04"><s1>Dementia Research Centre, University College London, Institute of Neurology</s1>
<s2>London</s2>
<s3>GBR</s3>
<sZ>3 aut.</sZ>
<sZ>8 aut.</sZ>
<sZ>11 aut.</sZ>
</fA14>
<fA14 i1="05"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Scottsdale, AZ</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>9 aut.</sZ>
<sZ>10 aut.</sZ>
</fA14>
<fA14 i1="06"><s1>Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath</s1>
<s2>West Sussex</s2>
<s3>GBR</s3>
<sZ>6 aut.</sZ>
</fA14>
<fA14 i1="07"><s1>Department of Neuroradiology, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</fA14>
<fA14 i1="08"><s1>Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg</s1>
<s2>Freiburg</s2>
<s3>DEU</s3>
<sZ>7 aut.</sZ>
</fA14>
<fA14 i1="09"><s1>Department of Radiology, Austin Health</s1>
<s2>Heidelberg</s2>
<s3>DEU</s3>
<sZ>8 aut.</sZ>
</fA14>
<fA14 i1="10"><s1>Department of Radiology, University of Melbourne</s1>
<s2>Melbourne</s2>
<s3>AUS</s3>
<sZ>8 aut.</sZ>
</fA14>
<fA14 i1="11"><s1>Department of Radiology, Mayo Clinic</s1>
<s2>Rochester</s2>
<s3>USA</s3>
<sZ>12 aut.</sZ>
</fA14>
<fA14 i1="12"><s1>Département d'études cognitives, Ecole Normale Supérieure</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>14 aut.</sZ>
</fA14>
<fA14 i1="13"><s1>Laboratory of Neuroimaging, IRCCS Santa Lucia</s1>
<s2>Roma</s2>
<s3>ITA</s3>
<sZ>14 aut.</sZ>
</fA14>
<fA20><s1>2969-2974</s1>
</fA20>
<fA21><s1>2008</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>998</s2>
<s5>354000184307520160</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2008 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>3/4 p.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>08-0521915</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Brain</s0>
</fA64>
<fA66 i1="01"><s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>002B17</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>002B17G</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Démence</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Dementia</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Demencia</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Pathologie du   système nerveux</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Nervous system diseases</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Sistema nervioso patología</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Précision</s0>
<s5>09</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Accuracy</s0>
<s5>09</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Precisión</s0>
<s5>09</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Diagnostic</s0>
<s5>10</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Diagnosis</s0>
<s5>10</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Diagnóstico</s0>
<s5>10</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Etude comparative</s0>
<s5>11</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Comparative study</s0>
<s5>11</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Estudio comparativo</s0>
<s5>11</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Radiologue</s0>
<s5>12</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Radiologist</s0>
<s5>12</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Radiólogo</s0>
<s5>12</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Imagerie RMN</s0>
<s5>13</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Nuclear magnetic resonance imaging</s0>
<s5>13</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Imaginería RMN</s0>
<s5>13</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Vecteur</s0>
<s5>14</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Vector</s0>
<s5>14</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Vector</s0>
<s5>14</s5>
</fC03>
<fC07 i1="01" i2="X" l="FRE"><s0>Maladie dégénérative</s0>
<s5>37</s5>
</fC07>
<fC07 i1="01" i2="X" l="ENG"><s0>Degenerative disease</s0>
<s5>37</s5>
</fC07>
<fC07 i1="01" i2="X" l="SPA"><s0>Enfermedad degenerativa</s0>
<s5>37</s5>
</fC07>
<fN21><s1>343</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
<server><NO>PASCAL 08-0521915 INIST</NO>
<ET>Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method</ET>
<AU>KLÖPPEL (Stefan); STONNINGTON (Cynthia M.); BARNES (Josephine); CHEN (Frederick); CHU (Carlton); GOOD (Catriona D.); MADER (Irina); MITCHELL (L. Anne); PATEL (Ameet C.); ROBERTS (Catherine C.); FOX (Nick C.); JACK (Clifford R. JR); ASHBURNER (John); FRACKOWIAK (Richard S. J.)</AU>
<AF>Department of Psychiatry and Psychotherapy and Freiburg Brain Imaging, University Clinic Freiburg/Freiburg/Allemagne (1 aut.); Wellcome Trust Centre for Neuroimaging, Institute of Neurology, University College London/London/Royaume-Uni (1 aut., 2 aut., 5 aut., 13 aut., 14 aut.); Department of Psychiatry and Psychology, Mayo Clinic/Scottsdale, AZ/Etats-Unis (2 aut.); Dementia Research Centre, University College London, Institute of Neurology/London/Royaume-Uni (3 aut., 8 aut., 11 aut.); Department of Radiology, Mayo Clinic/Scottsdale, AZ/Etats-Unis (4 aut., 9 aut., 10 aut.); Department of Neuroradiology, Hurstwood Park Neurosciences Centre, Brighton & Sussex Universities Hospital NHS Trust, Haywards Heath/West Sussex/Royaume-Uni (6 aut.); Department of Neuroradiology, University Clinic Freiburg/Freiburg/Allemagne (7 aut.); Department of Neurology, Freiburg Brain Imaging, Neurocenter, University Clinic Freiburg/Freiburg/Allemagne (7 aut.); Department of Radiology, Austin Health/Heidelberg/Allemagne (8 aut.); Department of Radiology, University of Melbourne/Melbourne/Australie (8 aut.); Department of Radiology, Mayo Clinic/Rochester/Etats-Unis (12 aut.); Département d'études cognitives, Ecole Normale Supérieure/Paris/France (14 aut.); Laboratory of Neuroimaging, IRCCS Santa Lucia/Roma/Italie (14 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>Brain; ISSN 0006-8950; Royaume-Uni; Da. 2008; Vol. 131; No. p. 11; Pp. 2969-2974; Bibl. 3/4 p.</SO>
<LA>Anglais</LA>
<EA>There has been recent interest in the application of machine learning techniques to neuroimaging-based diagnosis. These methods promise fully automated, standard PC-based clinical decisions, unbiased by variable radiological expertise. We recently used support vector machines (SVMs) to separate sporadic Alzheimer's disease from normal ageing and from fronto-temporal lobar degeneration (FTLD). In this study, we compare the results to those obtained by radiologists. A binary diagnostic classification was made by six radiologists with different levels of experience on the same scans and information that had been previously analysed with SVM. SVMs correctly classified 95% (sensitivity/specificity: 95/95) of sporadic Alzheimer's disease and controls into their respective groups. Radiologists correctly classified 65-95% (median 89%; sensitivity/specificity: 88/90) of scans. SVM correctly classified another set of sporadic Alzheimer's disease in 93% (sensitivity/specificity: 100/86) of cases, whereas radiologists ranged between 80% and 90% (median 83%; sensitivity/specificity: 80/85). SVMs were better at separating patients with sporadic Alzheimer's disease from those with FTLD (SVM 89%; sensitivity/specificity: 83/95; compared to radiological range from 63% to 83%; median 71%; sensitivity/specificity: 64/76). Radiologists were always accurate when they reported a high degree of diagnostic confidence. The results show that well-trained neuroradiologists classify typical Alzheimer's disease-associated scans comparable to SVMs. However, SVMs require no expert knowledge and trained SVMs can readily be exchanged between centres for use in diagnostic classification. These results are encouraging and indicate a role for computerized diagnostic methods in clinical practice.</EA>
<CC>002B17; 002B17G</CC>
<FD>Démence; Pathologie du   système nerveux; Précision; Diagnostic; Etude comparative; Radiologue; Imagerie RMN; Vecteur</FD>
<FG>Maladie dégénérative</FG>
<ED>Dementia; Nervous system diseases; Accuracy; Diagnosis; Comparative study; Radiologist; Nuclear magnetic resonance imaging; Vector</ED>
<EG>Degenerative disease</EG>
<SD>Demencia; Sistema nervioso patología; Precisión; Diagnóstico; Estudio comparativo; Radiólogo; Imaginería RMN; Vector</SD>
<LO>INIST-998.354000184307520160</LO>
<ID>08-0521915</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/PascalFrancis/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003210 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 003210 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Asie
   |area=    AustralieFrV1
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:08-0521915
   |texte=   Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method
}}

This area was generated with Dilib version V0.6.33.
Data generation: Tue Dec 5 10:43:12 2017. Site generation: Tue Mar 5 14:07:20 2024

	Serveur d'exploration sur les relations entre la France et l'Australie
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur les relations entre la France et l'Australie

Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method

Accuracy of dementia diagnosis-a direct comparison between radiologists and a computerized method

Source :

Descripteurs français

English descriptors

Abstract

Notice en format standard (ISO 2709)

Format Inist (serveur)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri