Development and validation of the automated imaging differentiation in parkinsonism (AID-P): a multicentre machine learning study

Derek B Archer, PhD; Justin T Bricker, MS; Winston T Chu, BS; Roxana G Burciu, PhD; Johanna L McCracken, BS; Song Lai, ProfPhD; Stephen A Coombes, PhD; Ruogu Fang, PhD; Angelos Barmpoutis, PhD; Daniel M Corcos, PhD; Ajay S Kurani, PhD; Trina Mitchell, MS; Mieniecia L Black, MPH; Ellen Herschel, BS; Tanya Simuni, ProfMD; Todd B Parrish, ProfPhD; Cynthia Comella, ProfMD; Tao Xie, MD; Klaus Seppi, ProfMD; Nicolaas I Bohnen, ProfMD; Martijn LTM Müller, PhD; Roger L Albin, ProfMD; Florian Krismer, MD; Guangwei Du, MD; Mechelle M Lewis, PhD; Xuemei Huang, ProfMD; Hong Li, PhD; Ofer Pasternak, PhD; Nikolaus R McFarland, MD; Michael S Okun, ProfMD; David E Vaillancourt, ProfPhD

The Lancet: Digital Health (Sep 2019)

Development and validation of the automated imaging differentiation in parkinsonism (AID-P): a multicentre machine learning study

Derek B Archer, PhD,
Justin T Bricker, MS,
Winston T Chu, BS,
Roxana G Burciu, PhD,
Johanna L McCracken, BS,
Song Lai, ProfPhD,
Stephen A Coombes, PhD,
Ruogu Fang, PhD,
Angelos Barmpoutis, PhD,
Daniel M Corcos, PhD,
Ajay S Kurani, PhD,
Trina Mitchell, MS,
Mieniecia L Black, MPH,
Ellen Herschel, BS,
Tanya Simuni, ProfMD,
Todd B Parrish, ProfPhD,
Cynthia Comella, ProfMD,
Tao Xie, MD,
Klaus Seppi, ProfMD,
Nicolaas I Bohnen, ProfMD,
Martijn LTM Müller, PhD,
Roger L Albin, ProfMD,
Florian Krismer, MD,
Guangwei Du, MD,
Mechelle M Lewis, PhD,
Xuemei Huang, ProfMD,
Hong Li, PhD,
Ofer Pasternak, PhD,
Nikolaus R McFarland, MD,
Michael S Okun, ProfMD,
David E Vaillancourt, ProfPhD

Affiliations

Derek B Archer, PhD: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Justin T Bricker, MS: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Winston T Chu, BS: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA; J Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
Roxana G Burciu, PhD: Department of Kinesiology and Applied Physiology, University of Delaware, Newark, DE, USA
Johanna L McCracken, BS: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Song Lai, ProfPhD: Department of Radiation Oncology, University of Florida, Gainesville, FL, USA; CTSI Human Imaging Core, University of Florida, Gainesville, FL, USA
Stephen A Coombes, PhD: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Ruogu Fang, PhD: J Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
Angelos Barmpoutis, PhD: J Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA; Digital Worlds Institute, University of Florida, Gainesville, FL, USA
Daniel M Corcos, PhD: Department of Neurological Sciences, Rush University Medical Center, Chicago, IL, USA
Ajay S Kurani, PhD: Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
Trina Mitchell, MS: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Mieniecia L Black, MPH: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA
Ellen Herschel, BS: Department of Neurology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
Tanya Simuni, ProfMD: Department of Neurology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
Todd B Parrish, ProfPhD: Department of Radiology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA
Cynthia Comella, ProfMD: Department of Neurological Sciences, Rush University Medical Center, Chicago, IL, USA
Tao Xie, MD: Department of Neurology, University of Chicago, Chicago, IL, USA
Klaus Seppi, ProfMD: Neuroimaging Research Core Facility, Department of Neurology, Medical University Innsbruck, Innsbruck, Austria
Nicolaas I Bohnen, ProfMD: Department of Radiology, University of Michigan, Ann Arbor, MI, USA; Department of Neurology, University of Michigan, Ann Arbor, MI, USA; Neurology Service and Geriatrics Research, Education, and Clinical Center, VA Ann Arbor Healthcare System, Ann Arbor, MI, USA; Udall Center of Excellence for Parkinson's Disease Research, University of Michigan, Ann Arbor, MI, USA
Martijn LTM Müller, PhD: Department of Radiology, University of Michigan, Ann Arbor, MI, USA; Udall Center of Excellence for Parkinson's Disease Research, University of Michigan, Ann Arbor, MI, USA
Roger L Albin, ProfMD: Department of Neurology, University of Michigan, Ann Arbor, MI, USA; Neurology Service and Geriatrics Research, Education, and Clinical Center, VA Ann Arbor Healthcare System, Ann Arbor, MI, USA; Udall Center of Excellence for Parkinson's Disease Research, University of Michigan, Ann Arbor, MI, USA
Florian Krismer, MD: Neuroimaging Research Core Facility, Department of Neurology, Medical University Innsbruck, Innsbruck, Austria
Guangwei Du, MD: Department of Neurology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA
Mechelle M Lewis, PhD: Department of Neurology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA; Department of Pharmacology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA
Xuemei Huang, ProfMD: Department of Neurology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA; Department of Pharmacology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA; Department of Neurosurgery, Penn State Milton S Hershey Medical Center, Hershey, PA, USA; Department of Radiology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA; Department of Kinesiology, Penn State Milton S Hershey Medical Center, Hershey, PA, USA
Hong Li, PhD: Department of Public Health Sciences, Medical College of South Carolina, Charleston, SC, USA
Ofer Pasternak, PhD: Department of Psychiatry and Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
Nikolaus R McFarland, MD: Fixel Institute for Neurological Disease, University of Florida, Gainesville, FL, USA; Department of Neurology, McKnight Brain Institute, University of Florida, Gainesville, FL, USA
Michael S Okun, ProfMD: Fixel Institute for Neurological Disease, University of Florida, Gainesville, FL, USA; Department of Neurology, McKnight Brain Institute, University of Florida, Gainesville, FL, USA; Department of Neurosurgery, McKnight Brain Institute, University of Florida, Gainesville, FL, USA
David E Vaillancourt, ProfPhD: Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL, USA; J Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA; Fixel Institute for Neurological Disease, University of Florida, Gainesville, FL, USA; Department of Neurology, McKnight Brain Institute, University of Florida, Gainesville, FL, USA; Correspondence to: Prof David E Vaillancourt, Laboratory for Rehabilitation Neuroscience, Department of Applied Physiology and Kinesiology, University of Florida, Gainesville, FL 32611-8205, USA

Journal volume & issue: Vol. 1, no. 5
pp. e222 – e231

Abstract

Read online

Summary: Background: Development of valid, non-invasive biomarkers for parkinsonian syndromes is crucially needed. We aimed to assess whether non-invasive diffusion-weighted MRI can distinguish between parkinsonian syndromes using an automated imaging approach. Methods: We did an international study at 17 MRI centres in Austria, Germany, and the USA. We used diffusion-weighted MRI from 1002 patients and 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 space between Parkinson's disease and atypical parkinsonism (multiple system atrophy and progressive supranuclear palsy) and between multiple system atrophy and progressive supranuclear palsy. For each comparison, models were developed on a training and validation cohort and evaluated in an independent test cohort by quantifying the area under the curve (AUC) of receiving operating characteristic curves. The primary outcomes were free water and free-water-corrected fractional anisotropy across 60 different template regions. Findings: In the test cohort for disease-specific comparisons, the diffusion-weighted MRI plus MDS-UPDRS III model (Parkinson's disease vs atypical parkinsonism had an AUC 0·962; multiple system atrophy vs progressive supranuclear palsy AUC 0·897) and diffusion-weighted MRI only model had high AUCs (Parkinson's disease vs atypical parkinsonism AUC 0·955; multiple system atrophy vs progressive supranuclear palsy AUC 0·926), whereas the MDS-UPDRS III only models had significantly lower AUCs (Parkinson's disease vs atypical parkinsonism 0·775; multiple system atrophy vs progressive supranuclear palsy 0·582). These results indicate that a non-invasive imaging approach is capable of differentiating forms of parkinsonism comparable to current gold standard methods. Interpretations: This study provides an objective, validated, and generalisable imaging approach to distinguish different forms of parkinsonian syndromes using multisite diffusion-weighted MRI cohorts. The diffusion-weighted MRI method does not involve radioactive tracers, is completely automated, and can be collected in less than 12 min across 3T scanners worldwide. The use of this test could positively affect the clinical care of patients with Parkinson's disease and parkinsonism and reduce the number of misdiagnosed cases in clinical trials. Funding: National Institutes of Health and Parkinson's Foundation.

Published in The Lancet: Digital Health

ISSN: 2589-7500 (Online)
Publisher: Elsevier
Country of publisher: United Kingdom
LCC subjects: Medicine: Medicine (General): Computer applications to medicine. Medical informatics
Website: https://www.thelancet.com/journals/landig/home

About the journal