Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease
Alzheimer’s disease (AD) is a neurodegenerative disorder which spans several years from preclinical manifestations to dementia. In recent years, interest in the application of machine learning (ML) algorithms to personalized medicine has grown considerably, and a major challenge that such models fac...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Big Data |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fdata.2021.661110/full |
id |
doaj-9164991b93b34418b58968b570ee57d0 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Damiano Archetti Alexandra L. Young Alexandra L. Young Neil P. Oxtoby Daniel Ferreira Daniel Ferreira Gustav Mårtensson Eric Westman Daniel C. Alexander Giovanni B. Frisoni Giovanni B. Frisoni Alberto Redolfi for Alzheimer’s Disease Neuroimaging Initiative and EuroPOND Consortium |
spellingShingle |
Damiano Archetti Alexandra L. Young Alexandra L. Young Neil P. Oxtoby Daniel Ferreira Daniel Ferreira Gustav Mårtensson Eric Westman Daniel C. Alexander Giovanni B. Frisoni Giovanni B. Frisoni Alberto Redolfi for Alzheimer’s Disease Neuroimaging Initiative and EuroPOND Consortium Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease Frontiers in Big Data alzheiemer’s disease patient subtyping patient staging SuStain model inter-cohort validation |
author_facet |
Damiano Archetti Alexandra L. Young Alexandra L. Young Neil P. Oxtoby Daniel Ferreira Daniel Ferreira Gustav Mårtensson Eric Westman Daniel C. Alexander Giovanni B. Frisoni Giovanni B. Frisoni Alberto Redolfi for Alzheimer’s Disease Neuroimaging Initiative and EuroPOND Consortium |
author_sort |
Damiano Archetti |
title |
Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease |
title_short |
Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease |
title_full |
Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease |
title_fullStr |
Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease |
title_full_unstemmed |
Inter-Cohort Validation of SuStaIn Model for Alzheimer’s Disease |
title_sort |
inter-cohort validation of sustain model for alzheimer’s disease |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Big Data |
issn |
2624-909X |
publishDate |
2021-05-01 |
description |
Alzheimer’s disease (AD) is a neurodegenerative disorder which spans several years from preclinical manifestations to dementia. In recent years, interest in the application of machine learning (ML) algorithms to personalized medicine has grown considerably, and a major challenge that such models face is the transferability from the research settings to clinical practice. The objective of this work was to demonstrate the transferability of the Subtype and Stage Inference (SuStaIn) model from well-characterized research data set, employed as training set, to independent less-structured and heterogeneous test sets representative of the clinical setting. The training set was composed of MRI data of 1043 subjects from the Alzheimer’s disease Neuroimaging Initiative (ADNI), and the test set was composed of data from 767 subjects from OASIS, Pharma-Cog, and ViTA clinical datasets. Both sets included subjects covering the entire spectrum of AD, and for both sets volumes of relevant brain regions were derived from T1-3D MRI scans processed with Freesurfer v5.3 cross-sectional stream. In order to assess the predictive value of the model, subpopulations of subjects with stable mild cognitive impairment (MCI) and MCIs that progressed to AD dementia (pMCI) were identified in both sets. SuStaIn identified three disease subtypes, of which the most prevalent corresponded to the typical atrophy pattern of AD. The other SuStaIn subtypes exhibited similarities with the previously defined hippocampal sparing and limbic predominant atrophy patterns of AD. Subject subtyping proved to be consistent in time for all cohorts and the staging provided by the model was correlated with cognitive performance. Classification of subjects on the basis of a combination of SuStaIn subtype and stage, mini mental state examination and amyloid-β1-42 cerebrospinal fluid concentration was proven to predict conversion from MCI to AD dementia on par with other novel statistical algorithms, with ROC curves that were not statistically different for the training and test sets and with area under curve respectively equal to 0.77 and 0.76. This study proves the transferability of a SuStaIn model for AD from research data to less-structured clinical cohorts, and indicates transferability to the clinical setting. |
topic |
alzheiemer’s disease patient subtyping patient staging SuStain model inter-cohort validation |
url |
https://www.frontiersin.org/articles/10.3389/fdata.2021.661110/full |
work_keys_str_mv |
AT damianoarchetti intercohortvalidationofsustainmodelforalzheimersdisease AT alexandralyoung intercohortvalidationofsustainmodelforalzheimersdisease AT alexandralyoung intercohortvalidationofsustainmodelforalzheimersdisease AT neilpoxtoby intercohortvalidationofsustainmodelforalzheimersdisease AT danielferreira intercohortvalidationofsustainmodelforalzheimersdisease AT danielferreira intercohortvalidationofsustainmodelforalzheimersdisease AT gustavmartensson intercohortvalidationofsustainmodelforalzheimersdisease AT ericwestman intercohortvalidationofsustainmodelforalzheimersdisease AT danielcalexander intercohortvalidationofsustainmodelforalzheimersdisease AT giovannibfrisoni intercohortvalidationofsustainmodelforalzheimersdisease AT giovannibfrisoni intercohortvalidationofsustainmodelforalzheimersdisease AT albertoredolfi intercohortvalidationofsustainmodelforalzheimersdisease AT foralzheimersdiseaseneuroimaginginitiativeandeuropondconsortium intercohortvalidationofsustainmodelforalzheimersdisease |
_version_ |
1721435582681317376 |
spelling |
doaj-9164991b93b34418b58968b570ee57d02021-05-20T07:20:53ZengFrontiers Media S.A.Frontiers in Big Data2624-909X2021-05-01410.3389/fdata.2021.661110661110Inter-Cohort Validation of SuStaIn Model for Alzheimer’s DiseaseDamiano Archetti0Alexandra L. Young1Alexandra L. Young2Neil P. Oxtoby3Daniel Ferreira4Daniel Ferreira5Gustav Mårtensson6Eric Westman7Daniel C. Alexander8Giovanni B. Frisoni9Giovanni B. Frisoni10Alberto Redolfi11for Alzheimer’s Disease Neuroimaging Initiative and EuroPOND ConsortiumLaboratory of Neuroinformatics, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyDepartment of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United KingdomDepartment of Computer Science, UCL Centre for Medical Image Computing, London, United KingdomDepartment of Computer Science, UCL Centre for Medical Image Computing, London, United KingdomDivision of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, SwedenDepartment of Radiology, Mayo Clinic, Rochester, MN, United StatesDivision of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, SwedenDivision of Clinical Geriatrics, Center for Alzheimer Research, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, SwedenDepartment of Computer Science, UCL Centre for Medical Image Computing, London, United KingdomMemory Clinic and LANVIE - Laboratory of Neuroimaging of Aging, University Hospitals and University of Geneva, Geneva, SwitzerlandLaboratory of Alzheimer’s Neuroimaging and Epidemiology - LANE, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyLaboratory of Neuroinformatics, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli, Brescia, ItalyAlzheimer’s disease (AD) is a neurodegenerative disorder which spans several years from preclinical manifestations to dementia. In recent years, interest in the application of machine learning (ML) algorithms to personalized medicine has grown considerably, and a major challenge that such models face is the transferability from the research settings to clinical practice. The objective of this work was to demonstrate the transferability of the Subtype and Stage Inference (SuStaIn) model from well-characterized research data set, employed as training set, to independent less-structured and heterogeneous test sets representative of the clinical setting. The training set was composed of MRI data of 1043 subjects from the Alzheimer’s disease Neuroimaging Initiative (ADNI), and the test set was composed of data from 767 subjects from OASIS, Pharma-Cog, and ViTA clinical datasets. Both sets included subjects covering the entire spectrum of AD, and for both sets volumes of relevant brain regions were derived from T1-3D MRI scans processed with Freesurfer v5.3 cross-sectional stream. In order to assess the predictive value of the model, subpopulations of subjects with stable mild cognitive impairment (MCI) and MCIs that progressed to AD dementia (pMCI) were identified in both sets. SuStaIn identified three disease subtypes, of which the most prevalent corresponded to the typical atrophy pattern of AD. The other SuStaIn subtypes exhibited similarities with the previously defined hippocampal sparing and limbic predominant atrophy patterns of AD. Subject subtyping proved to be consistent in time for all cohorts and the staging provided by the model was correlated with cognitive performance. Classification of subjects on the basis of a combination of SuStaIn subtype and stage, mini mental state examination and amyloid-β1-42 cerebrospinal fluid concentration was proven to predict conversion from MCI to AD dementia on par with other novel statistical algorithms, with ROC curves that were not statistically different for the training and test sets and with area under curve respectively equal to 0.77 and 0.76. This study proves the transferability of a SuStaIn model for AD from research data to less-structured clinical cohorts, and indicates transferability to the clinical setting.https://www.frontiersin.org/articles/10.3389/fdata.2021.661110/fullalzheiemer’s diseasepatient subtypingpatient stagingSuStain modelinter-cohort validation |