Development and Validation of the Automated Imaging Differentiation in Parkinsonism (AID-P): A Multi-Site Machine Learning Study.
Journal
The Lancet. Digital health
ISSN: 2589-7500
Titre abrégé: Lancet Digit Health
Pays: England
ID NLM: 101751302
Informations de publication
Date de publication:
09 2019
09 2019
Historique:
entrez:
8
4
2020
pubmed:
8
4
2020
medline:
8
4
2020
Statut:
ppublish
Résumé
There is a critical need to develop valid, non-invasive biomarkers for Parkinsonian syndromes. The current 17-site, international study assesses whether non-invasive diffusion MRI (dMRI) can distinguish between Parkinsonian syndromes. We used dMRI from 1002 subjects, along with the Movement Disorders Society Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS III), to develop and validate disease-specific machine learning comparisons using 60 template regions and tracts of interest in Montreal Neurological Institute (MNI) space between Parkinson's disease (PD) and Atypical Parkinsonism (multiple system atrophy - MSA, progressive supranuclear palsy - PSP), as well as between MSA and PSP. For each comparison, models were developed on a training/validation cohort and evaluated in a test cohort by quantifying the area under the curve (AUC) of receiving operating characteristic (ROC) curves. In the test cohort for both disease-specific comparisons, AUCs were high in the dMRI + MDS-UPDRS (PD vs. Atypical Parkinsonism: 0·962; MSA vs. PSP: 0·897) and dMRI Only (PD vs. Atypical Parkinsonism: 0·955; MSA vs. PSP: 0·926) models, whereas the MDS-UPDRS III Only models had significantly lower AUCs (PD vs. Atypical Parkinsonism: 0·775; MSA vs. PSP: 0·582). This study provides an objective, validated, and generalizable imaging approach to distinguish different forms of Parkinsonian syndromes using multi-site dMRI cohorts. The dMRI method does not involve radioactive tracers, is completely automated, and can be collected in less than 12 minutes across 3T scanners worldwide. The use of this test could thus positively impact the clinical care of patients with Parkinson's disease and Parkinsonism as well as reduce the number of misdiagnosed cases in clinical trials.
Sections du résumé
Background
There is a critical need to develop valid, non-invasive biomarkers for Parkinsonian syndromes. The current 17-site, international study assesses whether non-invasive diffusion MRI (dMRI) can distinguish between Parkinsonian syndromes.
Methods
We used dMRI from 1002 subjects, along with the Movement Disorders Society Unified Parkinson's Disease Rating Scale part III (MDS-UPDRS III), to develop and validate disease-specific machine learning comparisons using 60 template regions and tracts of interest in Montreal Neurological Institute (MNI) space between Parkinson's disease (PD) and Atypical Parkinsonism (multiple system atrophy - MSA, progressive supranuclear palsy - PSP), as well as between MSA and PSP. For each comparison, models were developed on a training/validation cohort and evaluated in a test cohort by quantifying the area under the curve (AUC) of receiving operating characteristic (ROC) curves.
Findings
In the test cohort for both disease-specific comparisons, AUCs were high in the dMRI + MDS-UPDRS (PD vs. Atypical Parkinsonism: 0·962; MSA vs. PSP: 0·897) and dMRI Only (PD vs. Atypical Parkinsonism: 0·955; MSA vs. PSP: 0·926) models, whereas the MDS-UPDRS III Only models had significantly lower AUCs (PD vs. Atypical Parkinsonism: 0·775; MSA vs. PSP: 0·582).
Interpretations
This study provides an objective, validated, and generalizable imaging approach to distinguish different forms of Parkinsonian syndromes using multi-site dMRI cohorts. The dMRI method does not involve radioactive tracers, is completely automated, and can be collected in less than 12 minutes across 3T scanners worldwide. The use of this test could thus positively impact the clinical care of patients with Parkinson's disease and Parkinsonism as well as reduce the number of misdiagnosed cases in clinical trials.
Identifiants
pubmed: 32259098
doi: 10.1016/s2589-7500(19)30105-0
pmc: PMC7111208
mid: NIHMS1545872
doi:
Types de publication
Journal Article
Multicenter Study
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Validation Study
Langues
eng
Pagination
e222-e231Subventions
Organisme : NINDS NIH HHS
ID : T32 NS082168
Pays : United States
Organisme : NINDS NIH HHS
ID : R01 NS052318
Pays : United States
Organisme : NINDS NIH HHS
ID : U01 NS102038
Pays : United States
Organisme : NINDS NIH HHS
ID : P50 NS091856
Pays : United States
Organisme : NIH HHS
ID : S10 OD021726
Pays : United States
Références
Cereb Cortex. 2018 May 1;28(5):1685-1699
pubmed: 28334314
Neurology. 2017 Mar 7;88(10):930-937
pubmed: 28179466
Mov Disord. 2016 Mar;31(3):325-34
pubmed: 26676922
Lancet Neurol. 2010 Feb;9(2):149-58
pubmed: 20061183
Mov Disord. 2018 Oct;33(10):1551-1554
pubmed: 30288780
J Neurol Neurosurg Psychiatry. 1992 Mar;55(3):181-4
pubmed: 1564476
Neuroimage. 2016 Jan 1;124(Pt A):724-732
pubmed: 26385011
Brain. 2016 Feb;139(Pt 2):495-508
pubmed: 26705348
Neuroimage. 2009 Jul 1;46(3):786-802
pubmed: 19195496
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Brain Pathol. 2007 Jan;17(1):74-82
pubmed: 17493041
Neurology. 1996 Jul;47(1):1-9
pubmed: 8710059
Neurology. 2014 Jul 29;83(5):406-12
pubmed: 24975862
Cold Spring Harb Perspect Med. 2012 Aug 01;2(8):
pubmed: 22908195
Magn Reson Med. 2009 Sep;62(3):717-30
pubmed: 19623619
Neurology. 2008 Aug 26;71(9):670-6
pubmed: 18725592
Arch Neurol. 1997 Aug;54(8):937-44
pubmed: 9267967
Neurology. 2015 Aug 4;85(5):404-12
pubmed: 26138942
Ann Neurol. 2014 Dec;76(6):769-83
pubmed: 25363872
Neuroimage. 2017 Nov 1;161:149-170
pubmed: 28826946
J Magn Reson B. 1996 Jun;111(3):209-19
pubmed: 8661285
Neurology. 2016 Mar 29;86(13):1242-9
pubmed: 26935895
Mov Disord. 2012 Sep 1;27(10):1239-42
pubmed: 22886777
Neuroimage. 2019 Jan 1;184:801-812
pubmed: 30267859
Neuroimage. 2012 Aug 15;62(2):782-90
pubmed: 21979382
Brain. 2002 Apr;125(Pt 4):861-70
pubmed: 11912118
Neuroimage. 2019 Oct 15;200:302-312
pubmed: 31260838
Arch Neurol. 2000 Mar;57(3):369-72
pubmed: 10714663
J Nucl Med. 2016 Jan;57(1):60-6
pubmed: 26449840