Development and Validation of Automated Magnetic Resonance Parkinsonism Index 2.0 to Distinguish Progressive Supranuclear Palsy-Parkinsonism From Parkinson's Disease.
Magnetic Resonance Parkinsonism Index 2.0
Parkinson's disease
automated MRI biomarker
progressive supranuclear palsy-parkinsonism
Journal
Movement disorders : official journal of the Movement Disorder Society
ISSN: 1531-8257
Titre abrégé: Mov Disord
Pays: United States
ID NLM: 8610688
Informations de publication
Date de publication:
06 2022
06 2022
Historique:
revised:
21
02
2022
received:
30
12
2021
accepted:
23
02
2022
pubmed:
12
4
2022
medline:
18
6
2022
entrez:
11
4
2022
Statut:
ppublish
Résumé
Differentiating progressive supranuclear palsy-parkinsonism (PSP-P) from Parkinson's disease (PD) is clinically challenging. This study aimed to develop an automated Magnetic Resonance Parkinsonism Index 2.0 (MRPI 2.0) algorithm to distinguish PSP-P from PD and to validate its diagnostic performance in two large independent cohorts. We enrolled 676 participants: a training cohort (n = 346; 43 PSP-P, 194 PD, and 109 control subjects) from our center and an independent testing cohort (n = 330; 62 PSP-P, 171 PD, and 97 control subjects) from an international research group. We developed a new in-house algorithm for MRPI 2.0 calculation and assessed its performance in distinguishing PSP-P from PD and control subjects in both cohorts using receiver operating characteristic curves. The automated MRPI 2.0 showed excellent performance in differentiating patients with PSP-P from patients with PD and control subjects both in the training cohort (area under the receiver operating characteristic curve [AUC] = 0.93 [95% confidence interval, 0.89-0.98] and AUC = 0.97 [0.93-1.00], respectively) and in the international testing cohort (PSP-P versus PD, AUC = 0.92 [0.87-0.97]; PSP-P versus controls, AUC = 0.94 [0.90-0.98]), suggesting the generalizability of the results. The automated MRPI 2.0 also accurately distinguished between PSP-P and PD in the early stage of the diseases (AUC = 0.91 [0.84-0.97]). A strong correlation (r = 0.91, P < 0.001) was found between automated and manual MRPI 2.0 values. Our study provides an automated, validated, and generalizable magnetic resonance biomarker to distinguish PSP-P from PD. The use of the automated MRPI 2.0 algorithm rather than manual measurements could be important to standardize measures in patients with PSP-P across centers, with a positive impact on multicenter studies and clinical trials involving patients from different geographic regions. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
Sections du résumé
BACKGROUND
Differentiating progressive supranuclear palsy-parkinsonism (PSP-P) from Parkinson's disease (PD) is clinically challenging.
OBJECTIVE
This study aimed to develop an automated Magnetic Resonance Parkinsonism Index 2.0 (MRPI 2.0) algorithm to distinguish PSP-P from PD and to validate its diagnostic performance in two large independent cohorts.
METHODS
We enrolled 676 participants: a training cohort (n = 346; 43 PSP-P, 194 PD, and 109 control subjects) from our center and an independent testing cohort (n = 330; 62 PSP-P, 171 PD, and 97 control subjects) from an international research group. We developed a new in-house algorithm for MRPI 2.0 calculation and assessed its performance in distinguishing PSP-P from PD and control subjects in both cohorts using receiver operating characteristic curves.
RESULTS
The automated MRPI 2.0 showed excellent performance in differentiating patients with PSP-P from patients with PD and control subjects both in the training cohort (area under the receiver operating characteristic curve [AUC] = 0.93 [95% confidence interval, 0.89-0.98] and AUC = 0.97 [0.93-1.00], respectively) and in the international testing cohort (PSP-P versus PD, AUC = 0.92 [0.87-0.97]; PSP-P versus controls, AUC = 0.94 [0.90-0.98]), suggesting the generalizability of the results. The automated MRPI 2.0 also accurately distinguished between PSP-P and PD in the early stage of the diseases (AUC = 0.91 [0.84-0.97]). A strong correlation (r = 0.91, P < 0.001) was found between automated and manual MRPI 2.0 values.
CONCLUSIONS
Our study provides an automated, validated, and generalizable magnetic resonance biomarker to distinguish PSP-P from PD. The use of the automated MRPI 2.0 algorithm rather than manual measurements could be important to standardize measures in patients with PSP-P across centers, with a positive impact on multicenter studies and clinical trials involving patients from different geographic regions. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
Identifiants
pubmed: 35403258
doi: 10.1002/mds.28992
pmc: PMC9321546
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1272-1281Informations de copyright
© 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
Références
Mov Disord. 2017 Jun;32(6):853-864
pubmed: 28467028
Radiology. 2008 Jan;246(1):214-21
pubmed: 17991785
Arch Neurol. 1964 Apr;10:333-59
pubmed: 14107684
Mov Disord. 2011 Feb 15;26(3):527-33
pubmed: 21287599
Lancet Neurol. 2017 Jul;16(7):552-563
pubmed: 28653647
Mov Disord. 2010 Feb 15;25(3):357-62
pubmed: 20108379
Neurology. 2016 Feb 9;86(6):566-76
pubmed: 26764028
Parkinsonism Relat Disord. 2018 Jan;46:47-55
pubmed: 29126761
Radiology. 2017 Oct;285(1):197-205
pubmed: 28498794
Arch Neurol. 1999 Jan;56(1):33-9
pubmed: 9923759
Neurology. 1967 May;17(5):427-42
pubmed: 6067254
Mov Disord. 2017 Jul;32(7):995-1005
pubmed: 28500752
Mov Disord. 2019 Aug;34(8):1144-1153
pubmed: 30726566
Mov Disord. 2021 Mar;36(3):681-689
pubmed: 33151015
Brain. 2005 Jun;128(Pt 6):1247-58
pubmed: 15788542
Parkinsonism Relat Disord. 2020 Apr;73:105-116
pubmed: 32487421
Mov Disord. 2019 Apr;34(4):487-495
pubmed: 30759325
AJNR Am J Neuroradiol. 2018 Jun;39(6):1047-1051
pubmed: 29622555
J Med Imaging Radiat Oncol. 2018 Feb;62(1):21-31
pubmed: 28432758
Parkinsonism Relat Disord. 2018 Sep;54:3-8
pubmed: 30068492
Nat Rev Neurol. 2021 Oct;17(10):601-620
pubmed: 34426686
Mov Disord. 2017 Jul;32(7):955-971
pubmed: 28500751
Parkinsonism Relat Disord. 2017 Aug;41:31-36
pubmed: 28487107
Eur Radiol. 2017 Jun;27(6):2665-2675
pubmed: 27761709
Mov Disord. 2011 Feb 1;26(2):247-55
pubmed: 21412831
Mov Disord. 2020 Jun;35(6):976-983
pubmed: 32092195
Parkinsonism Relat Disord. 2020 Mar;72:1-6
pubmed: 32036297
Parkinsonism Relat Disord. 2019 Sep;66:176-181
pubmed: 31420309
Mov Disord. 2008 Nov 15;23(15):2129-70
pubmed: 19025984
PLoS One. 2014 Jan 28;9(1):e85618
pubmed: 24489664
Mov Disord. 2014 Dec;29(14):1758-66
pubmed: 25370486
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Mov Disord. 2020 Aug;35(8):1388-1395
pubmed: 32357259
Brain. 2007 Jun;130(Pt 6):1566-76
pubmed: 17525140
J Neurol Neurosurg Psychiatry. 2020 Jan;91(1):98-103
pubmed: 31527182
Parkinsonism Relat Disord. 2019 May;62:185-191
pubmed: 30558837
JAMA Neurol. 2020 Mar 1;77(3):377-387
pubmed: 31860007
Parkinsonism Relat Disord. 2011 Mar;17(3):172-6
pubmed: 21236720
Parkinsonism Relat Disord. 2016 Jan;22 Suppl 1:S34-6
pubmed: 26421392
Mov Disord. 2019 Aug;34(8):1228-1232
pubmed: 30884545
Front Neurol. 2020 Mar 10;11:180
pubmed: 32218768
Parkinsonism Relat Disord. 2021 Jan;82:87-91
pubmed: 33271461