Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data

Abstract Background Event-based modeling (EBM) traces sequential progression of events in complex processes like neurodegenerative diseases, adept at handling uncertainties. This study validated an EBM for Alzheimer’s disease (AD) staging designed by EuroPOND, an EU-funded Horizon 2020 project, usin...

Full description

Saved in:
Bibliographic Details
Main Authors: Mandy M. J. Wittens, Diana M. Sima, Arne Brys, Hanne Struyfs, Ellis Niemantsverdriet, Ellen De Roeck, Christine Bastin, Florence Benoit, Bruno Bergmans, Jean-Christophe Bier, Peter Paul de Deyn, Olivier Deryck, Bernard Hanseeuw, Adrian Ivanoiu, Gaëtane Picard, Eric Salmon, Kurt Segers, Anne Sieben, Evert Thiery, Jos Tournoy, Anne-Marie van Binst, Jan Versijpt, Dirk Smeets, Maria Bjerke, Maura Bellio, Neil P. Oxtoby, Daniel C. Alexander, Annemie Ribbens, Sebastiaan Engelborghs
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Alzheimer’s Research & Therapy
Subjects:
Online Access:https://doi.org/10.1186/s13195-025-01788-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332762974093312
author Mandy M. J. Wittens
Diana M. Sima
Arne Brys
Hanne Struyfs
Ellis Niemantsverdriet
Ellen De Roeck
Christine Bastin
Florence Benoit
Bruno Bergmans
Jean-Christophe Bier
Peter Paul de Deyn
Olivier Deryck
Bernard Hanseeuw
Adrian Ivanoiu
Gaëtane Picard
Eric Salmon
Kurt Segers
Anne Sieben
Evert Thiery
Jos Tournoy
Anne-Marie van Binst
Jan Versijpt
Dirk Smeets
Maria Bjerke
Maura Bellio
Neil P. Oxtoby
Daniel C. Alexander
Annemie Ribbens
Sebastiaan Engelborghs
author_facet Mandy M. J. Wittens
Diana M. Sima
Arne Brys
Hanne Struyfs
Ellis Niemantsverdriet
Ellen De Roeck
Christine Bastin
Florence Benoit
Bruno Bergmans
Jean-Christophe Bier
Peter Paul de Deyn
Olivier Deryck
Bernard Hanseeuw
Adrian Ivanoiu
Gaëtane Picard
Eric Salmon
Kurt Segers
Anne Sieben
Evert Thiery
Jos Tournoy
Anne-Marie van Binst
Jan Versijpt
Dirk Smeets
Maria Bjerke
Maura Bellio
Neil P. Oxtoby
Daniel C. Alexander
Annemie Ribbens
Sebastiaan Engelborghs
author_sort Mandy M. J. Wittens
collection DOAJ
description Abstract Background Event-based modeling (EBM) traces sequential progression of events in complex processes like neurodegenerative diseases, adept at handling uncertainties. This study validated an EBM for Alzheimer’s disease (AD) staging designed by EuroPOND, an EU-funded Horizon 2020 project, using research and real-world datasets, a crucial step towards application in multi-center trials. Methods The training dataset comprised 1737 subjects from ADNI-1/GO/2, using the EuroPOND EBM toolbox. Testing datasets included a research cohort from University of Antwerp (controls, CN (n = 46), subjective cognitive decline, SCD (n = 10), mild cognitive impairment, MCI (n = 47), AD dementia, ADD (n = 16)) and a real-world cohort from 9 Belgian Dementia Council memory clinics (CN (n = 91), SCD (n = 66), (non-amnestic) naMCI (n = 54), aMCI (n = 255), and ADD (n = 220). Biomarkers included: 2 clinical scores (Mini Mental State Examination (MMSE), Rey Auditory Verbal Learning Test (RAVLT)); 3 CSF-biomarkers (Aβ1−42, P-tau181, total-Tau); and 4 magnetic resonance imaging (MRI) biomarkers (volumes of the hippocampi, temporal, parietal, and frontal cortices) computed with icobrain dm. The naMCI and aMCI groups were compared by EBM stage proportions, and the model’s effectiveness at patient level was evaluated. Results The research cohort’s maximum likelihood event sequence comprised CSF Aβ1-42, P-tau181, T-tau, RAVLT, MMSE, and cortical volumes. The clinical cohort’s order was frontal cortex volume, MMSE, and remaining cortical regions. aMCI subjects showed higher staging than naMCI, with 54% in the two most advanced stages compared to 38% in naMCI. In the research cohort, 10 outliers were identified with potential mismatches between assigned stages and clinical or biomarker profiles, with CN (n = 4) and SCD (n = 2) subjects assigned in stage 4, one control in stage 9 with abnormal imaging, and three aMCI cases in stage 0 despite clinical or volumetric signs of impairment. Conclusions This study highlights the generalizability of EuroPOND’s AD EBM model across research and real-world clinical datasets, supporting its use in multi-center trials. aMCI subjects generally reside in more advanced stages than naMCI, who may not necessarily have AD, demonstrating utility for precision recruitment/screening.
format Article
id doaj-art-4ac244a8e3514ea89eac381bed6bba63
institution Kabale University
issn 1758-9193
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Alzheimer’s Research & Therapy
spelling doaj-art-4ac244a8e3514ea89eac381bed6bba632025-08-20T03:46:07ZengBMCAlzheimer’s Research & Therapy1758-91932025-06-0117111510.1186/s13195-025-01788-6Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical dataMandy M. J. Wittens0Diana M. Sima1Arne Brys2Hanne Struyfs3Ellis Niemantsverdriet4Ellen De Roeck5Christine Bastin6Florence Benoit7Bruno Bergmans8Jean-Christophe Bier9Peter Paul de Deyn10Olivier Deryck11Bernard Hanseeuw12Adrian Ivanoiu13Gaëtane Picard14Eric Salmon15Kurt Segers16Anne Sieben17Evert Thiery18Jos Tournoy19Anne-Marie van Binst20Jan Versijpt21Dirk Smeets22Maria Bjerke23Maura Bellio24Neil P. Oxtoby25Daniel C. Alexander26Annemie Ribbens27Sebastiaan Engelborghs28Dep. of Biomedical Sciences, University of AntwerpicometrixicometrixDep. of Biomedical Sciences, University of AntwerpDep. of Biomedical Sciences, University of AntwerpDep. of Biomedical Sciences, University of AntwerpCRC Human Imaging , GIGA Research, University of LiègeGeriatrics Department, Brugmann University Hospital, Université Libre de BruxellesNeurology Department, AZ St-Jan Brugge, Ghent University and Ghent University HospitalNeurology Department, H. U. B. - Erasme Hospital, Université Libre de Bruxelles (ULB)Laboratory of Neurochemistry and Behaviour, Experimental Neurobiology unit, Department of Biomedical Sciences, University of AntwerpDepartment of Neurology, AZ Sint-LucasWELBIO department, WEL Research InstituteInstitute of Neuroscience, Université Catholique de LouvainDepartment of Neurology, Clinique Saint-PierreGIGA Cyclotron Research Centre, University of LiegeNeurology & Geriatrics Dpt, Brugmann University HospitalNeuropathology lab, IBB-NeuroBiobank BB190113, Born Bunge InstituteDepartment of Neurology, University Hospital Ghent, Ghent UniversityGerontology & Geriatrics, Department of Public Health and Primary Care, KU LeuvenRadiology department, Universitair Ziekenhuis Brussel (UZ Brussel)Dep. of Neurology, Universitair Ziekenhuis Brussel (UZ Brussel)icometrixDep. of Biomedical Sciences, University of AntwerpDepartment of Computer Science, UCL Hawkes Institute (Centre for Medical Image Computing), University College LondonDepartment of Computer Science, UCL Hawkes Institute (Centre for Medical Image Computing), University College LondonDepartment of Computer Science, UCL Hawkes Institute (Centre for Medical Image Computing), University College LondonicometrixDep. of Biomedical Sciences, University of AntwerpAbstract Background Event-based modeling (EBM) traces sequential progression of events in complex processes like neurodegenerative diseases, adept at handling uncertainties. This study validated an EBM for Alzheimer’s disease (AD) staging designed by EuroPOND, an EU-funded Horizon 2020 project, using research and real-world datasets, a crucial step towards application in multi-center trials. Methods The training dataset comprised 1737 subjects from ADNI-1/GO/2, using the EuroPOND EBM toolbox. Testing datasets included a research cohort from University of Antwerp (controls, CN (n = 46), subjective cognitive decline, SCD (n = 10), mild cognitive impairment, MCI (n = 47), AD dementia, ADD (n = 16)) and a real-world cohort from 9 Belgian Dementia Council memory clinics (CN (n = 91), SCD (n = 66), (non-amnestic) naMCI (n = 54), aMCI (n = 255), and ADD (n = 220). Biomarkers included: 2 clinical scores (Mini Mental State Examination (MMSE), Rey Auditory Verbal Learning Test (RAVLT)); 3 CSF-biomarkers (Aβ1−42, P-tau181, total-Tau); and 4 magnetic resonance imaging (MRI) biomarkers (volumes of the hippocampi, temporal, parietal, and frontal cortices) computed with icobrain dm. The naMCI and aMCI groups were compared by EBM stage proportions, and the model’s effectiveness at patient level was evaluated. Results The research cohort’s maximum likelihood event sequence comprised CSF Aβ1-42, P-tau181, T-tau, RAVLT, MMSE, and cortical volumes. The clinical cohort’s order was frontal cortex volume, MMSE, and remaining cortical regions. aMCI subjects showed higher staging than naMCI, with 54% in the two most advanced stages compared to 38% in naMCI. In the research cohort, 10 outliers were identified with potential mismatches between assigned stages and clinical or biomarker profiles, with CN (n = 4) and SCD (n = 2) subjects assigned in stage 4, one control in stage 9 with abnormal imaging, and three aMCI cases in stage 0 despite clinical or volumetric signs of impairment. Conclusions This study highlights the generalizability of EuroPOND’s AD EBM model across research and real-world clinical datasets, supporting its use in multi-center trials. aMCI subjects generally reside in more advanced stages than naMCI, who may not necessarily have AD, demonstrating utility for precision recruitment/screening.https://doi.org/10.1186/s13195-025-01788-6Alzheimer’s diseaseBiomarkersMagnetic resonance imagingAutomated volumetryEvent-based modelling
spellingShingle Mandy M. J. Wittens
Diana M. Sima
Arne Brys
Hanne Struyfs
Ellis Niemantsverdriet
Ellen De Roeck
Christine Bastin
Florence Benoit
Bruno Bergmans
Jean-Christophe Bier
Peter Paul de Deyn
Olivier Deryck
Bernard Hanseeuw
Adrian Ivanoiu
Gaëtane Picard
Eric Salmon
Kurt Segers
Anne Sieben
Evert Thiery
Jos Tournoy
Anne-Marie van Binst
Jan Versijpt
Dirk Smeets
Maria Bjerke
Maura Bellio
Neil P. Oxtoby
Daniel C. Alexander
Annemie Ribbens
Sebastiaan Engelborghs
Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
Alzheimer’s Research & Therapy
Alzheimer’s disease
Biomarkers
Magnetic resonance imaging
Automated volumetry
Event-based modelling
title Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
title_full Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
title_fullStr Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
title_full_unstemmed Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
title_short Independent validation and outlier analysis of EuroPOND Alzheimer’s disease staging model using ADNI and real-world clinical data
title_sort independent validation and outlier analysis of europond alzheimer s disease staging model using adni and real world clinical data
topic Alzheimer’s disease
Biomarkers
Magnetic resonance imaging
Automated volumetry
Event-based modelling
url https://doi.org/10.1186/s13195-025-01788-6
work_keys_str_mv AT mandymjwittens independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT dianamsima independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT arnebrys independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT hannestruyfs independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT ellisniemantsverdriet independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT ellenderoeck independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT christinebastin independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT florencebenoit independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT brunobergmans independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT jeanchristophebier independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT peterpauldedeyn independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT olivierderyck independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT bernardhanseeuw independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT adrianivanoiu independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT gaetanepicard independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT ericsalmon independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT kurtsegers independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT annesieben independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT evertthiery independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT jostournoy independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT annemarievanbinst independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT janversijpt independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT dirksmeets independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT mariabjerke independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT maurabellio independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT neilpoxtoby independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT danielcalexander independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT annemieribbens independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata
AT sebastiaanengelborghs independentvalidationandoutlieranalysisofeuropondalzheimersdiseasestagingmodelusingadniandrealworldclinicaldata