Predicting progression of Alzheimer's disease using ordinal regression.

We propose a novel approach to predicting disease progression in Alzheimer's disease (AD)--multivariate ordinal regression--which inherently models the ordered nature of brain atrophy spanning normal aging (CTL) to mild cognitive impairment (MCI) to AD. Ordinal regression provides probabilistic...

Full description

Saved in:
Bibliographic Details
Main Authors: Orla M Doyle, Eric Westman, Andre F Marquand, Patrizia Mecocci, Bruno Vellas, Magda Tsolaki, Iwona Kłoszewska, Hilkka Soininen, Simon Lovestone, Steve C R Williams, Andrew Simmons
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2014-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0105542
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850161777116971008
author Orla M Doyle
Eric Westman
Andre F Marquand
Patrizia Mecocci
Bruno Vellas
Magda Tsolaki
Iwona Kłoszewska
Hilkka Soininen
Simon Lovestone
Steve C R Williams
Andrew Simmons
author_facet Orla M Doyle
Eric Westman
Andre F Marquand
Patrizia Mecocci
Bruno Vellas
Magda Tsolaki
Iwona Kłoszewska
Hilkka Soininen
Simon Lovestone
Steve C R Williams
Andrew Simmons
author_sort Orla M Doyle
collection DOAJ
description We propose a novel approach to predicting disease progression in Alzheimer's disease (AD)--multivariate ordinal regression--which inherently models the ordered nature of brain atrophy spanning normal aging (CTL) to mild cognitive impairment (MCI) to AD. Ordinal regression provides probabilistic class predictions as well as a continuous index of disease progression--the ORCHID (Ordinal Regression Characteristic Index of Dementia) score. We applied ordinal regression to 1023 baseline structural MRI scans from two studies: the US-based Alzheimer's Disease Neuroimaging Initiative (ADNI) and the European based AddNeuroMed program. Here, the acquired AddNeuroMed dataset was used as a completely independent test set for the ordinal regression model trained on the ADNI cohort providing an optimal assessment of model generalizability. Distinguishing CTL-like (CTL and stable MCI) from AD-like (MCI converters and AD) resulted in balanced accuracies of 82% (cross-validation) for ADNI and 79% (independent test set) for AddNeuroMed. For prediction of conversion from MCI to AD, balanced accuracies of 70% (AUC of 0.75) and 75% (AUC of 0.81) were achieved. The ORCHID score was computed for all subjects. We showed that this measure significantly correlated with MMSE at 12 months (ρ =  -0.64, ADNI and ρ =  -0.59, AddNeuroMed). Additionally, the ORCHID score can help fractionate subjects with unstable diagnoses (e.g. reverters and healthy controls who later progressed to MCI), moderately late converters (12-24 months) and late converters (24-36 months). A comparison with results in the literature and direct comparison with a binary classifier suggests that the performance of this framework is highly competitive.
format Article
id doaj-art-ec1a5bb91fe94a48a373320959306bc1
institution OA Journals
issn 1932-6203
language English
publishDate 2014-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-ec1a5bb91fe94a48a373320959306bc12025-08-20T02:22:44ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0198e10554210.1371/journal.pone.0105542Predicting progression of Alzheimer's disease using ordinal regression.Orla M DoyleEric WestmanAndre F MarquandPatrizia MecocciBruno VellasMagda TsolakiIwona KłoszewskaHilkka SoininenSimon LovestoneSteve C R WilliamsAndrew SimmonsWe propose a novel approach to predicting disease progression in Alzheimer's disease (AD)--multivariate ordinal regression--which inherently models the ordered nature of brain atrophy spanning normal aging (CTL) to mild cognitive impairment (MCI) to AD. Ordinal regression provides probabilistic class predictions as well as a continuous index of disease progression--the ORCHID (Ordinal Regression Characteristic Index of Dementia) score. We applied ordinal regression to 1023 baseline structural MRI scans from two studies: the US-based Alzheimer's Disease Neuroimaging Initiative (ADNI) and the European based AddNeuroMed program. Here, the acquired AddNeuroMed dataset was used as a completely independent test set for the ordinal regression model trained on the ADNI cohort providing an optimal assessment of model generalizability. Distinguishing CTL-like (CTL and stable MCI) from AD-like (MCI converters and AD) resulted in balanced accuracies of 82% (cross-validation) for ADNI and 79% (independent test set) for AddNeuroMed. For prediction of conversion from MCI to AD, balanced accuracies of 70% (AUC of 0.75) and 75% (AUC of 0.81) were achieved. The ORCHID score was computed for all subjects. We showed that this measure significantly correlated with MMSE at 12 months (ρ =  -0.64, ADNI and ρ =  -0.59, AddNeuroMed). Additionally, the ORCHID score can help fractionate subjects with unstable diagnoses (e.g. reverters and healthy controls who later progressed to MCI), moderately late converters (12-24 months) and late converters (24-36 months). A comparison with results in the literature and direct comparison with a binary classifier suggests that the performance of this framework is highly competitive.https://doi.org/10.1371/journal.pone.0105542
spellingShingle Orla M Doyle
Eric Westman
Andre F Marquand
Patrizia Mecocci
Bruno Vellas
Magda Tsolaki
Iwona Kłoszewska
Hilkka Soininen
Simon Lovestone
Steve C R Williams
Andrew Simmons
Predicting progression of Alzheimer's disease using ordinal regression.
PLoS ONE
title Predicting progression of Alzheimer's disease using ordinal regression.
title_full Predicting progression of Alzheimer's disease using ordinal regression.
title_fullStr Predicting progression of Alzheimer's disease using ordinal regression.
title_full_unstemmed Predicting progression of Alzheimer's disease using ordinal regression.
title_short Predicting progression of Alzheimer's disease using ordinal regression.
title_sort predicting progression of alzheimer s disease using ordinal regression
url https://doi.org/10.1371/journal.pone.0105542
work_keys_str_mv AT orlamdoyle predictingprogressionofalzheimersdiseaseusingordinalregression
AT ericwestman predictingprogressionofalzheimersdiseaseusingordinalregression
AT andrefmarquand predictingprogressionofalzheimersdiseaseusingordinalregression
AT patriziamecocci predictingprogressionofalzheimersdiseaseusingordinalregression
AT brunovellas predictingprogressionofalzheimersdiseaseusingordinalregression
AT magdatsolaki predictingprogressionofalzheimersdiseaseusingordinalregression
AT iwonakłoszewska predictingprogressionofalzheimersdiseaseusingordinalregression
AT hilkkasoininen predictingprogressionofalzheimersdiseaseusingordinalregression
AT simonlovestone predictingprogressionofalzheimersdiseaseusingordinalregression
AT stevecrwilliams predictingprogressionofalzheimersdiseaseusingordinalregression
AT andrewsimmons predictingprogressionofalzheimersdiseaseusingordinalregression