Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 16;17(1):134.
doi: 10.1186/s13195-025-01788-6.

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

Mandy M J Wittens  1   2   3 , Diana M Sima  4 , Arne Brys  4 , Hanne Struyfs  1 , Ellis Niemantsverdriet  1 , Ellen De Roeck  1   5 , Christine Bastin  6   7 , Florence Benoit  8 , Bruno Bergmans  9 , Jean-Christophe Bier  10 , Peter Paul de Deyn  11   12 , Olivier Deryck  13 , Bernard Hanseeuw  14   15   16 , Adrian Ivanoiu  15   16 , Gaëtane Picard  17 , Eric Salmon  18 , Kurt Segers  19 , Anne Sieben  20   21   22 , Evert Thiery  23 , Jos Tournoy  24   25 , Anne-Marie van Binst  26 , Jan Versijpt  2   3 , Dirk Smeets  4 , Maria Bjerke  1   3   27 , Maura Bellio  28 , Neil P Oxtoby  28 , Daniel C Alexander  28 , Annemie Ribbens  4 , Sebastiaan Engelborghs  29   30   31
Affiliations

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

Mandy M J Wittens et al. Alzheimers Res Ther. .

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.

Keywords: Alzheimer’s disease; Automated volumetry; Biomarkers; Event-based modelling; Magnetic resonance imaging.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: The REMEMBER study was approved by the ethics committee of University of Antwerp / Universitair Ziekenhuis Antwerpen, Antwerp (N°16/2/18) and by the ethics committees of Algemeen Ziekenhuis Sint-Jan Brugge-Oostende, Brugge (N°1992); Centre Hospitalier Universitaire Brugmann (CHU Brugmann), Brussels (N°2016/84); Centre Hospitalier Universitaire Liège (CHU Liège), Liège (N°2012/274); Cliniques Universitaires de Bruxelles (ULB), Hôpital Erasme, Brussels (N°P2016/187); Cliniques Universitaires Saint-Luc (UCL), Brussels (N°2016/07jui/261); Cliniques St-Pierre Ottignies, Ottignies (N°OM045); Universitair Ziekenhuis Brussel, Brussels (N°2016/183); and Ziekenhuis Netwerk Antwerp (ZNA), Antwerp (N°4730). The research was conducted in accordance with the Declaration of Helsinki and informed written consent was obtained from all participants from the University of Antwerp prospective research cohort, that was approved by the ethics committee of University of Antwerp / Universitair Ziekenhuis Antwerpen, Antwerp (N°15/38/394). icobrain dm is a proprietary software, developed by icometrix for the automated quantification of brain volumes and white matter hyperintensities. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Positional variance diagram - Research cohort. Positional variance plots of the research dataset were visualized, showing the distribution of the maximum likelihood event sequence. Each entry represents the proportion of bootstrapped biomarker samples, color-coded through cell-shading. White indicates 0, which becomes increasingly more shaded with increased proportion of biomarker samples, until, if 1, becoming red (left) or green (right). MMSE = Mini-Mental State Examination. RAVLT = Rey Auditory Verbal Learning Test
Fig. 2
Fig. 2
Distribution for each group per EBM stage – Research cohort. Proportion of subjects from each group per EBM stage, with MCI split as non-amnestic (naMCI) and amnestic (aMCI). Each EBM stage on the x-axis corresponds to the occurrence of a new biomarker transition event. Stage 0 being no events having occurred and stage 9 is when all events have occurred. Events are ordered by the maximum likelihood event sequence for the ADNI population. CN = controls, SCD = subjective cognitive decline, MCI = mild cognitive impairment, aMCI = amnestic mild cognitive impairment, naMCI = non-amnestic mild cognitive impairment, ADD = Alzheimer’s disease dementia
Fig. 3
Fig. 3
Positional variance diagram - Real-world clinical dataset. Positional variance plots of the independent clinical dataset were visualized, showing the distribution of the maximum likelihood event sequence. Each entry represents the proportion of bootstrapped biomarker samples, color-coded through cell-shading. White indicates 0, which becomes increasingly more shaded with increased proportion of biomarker samples, until, if 1, becoming red (left) or green (right). MMSE = Mini-Mental State Examination. RAVLT = Rey Auditory Verbal Learning Test
Fig. 4
Fig. 4
Distribution for each group per EBM stage – Real world clinical dataset. Proportion of subjects from each group per EBM stage, with MCI split as non-amnestic (naMCI) and amnestic (aMCI). Each EBM stage on the x-axis corresponds to the occurrence of a new biomarker transition event. Stage 0 corresponds to no events having occurred and stage 5 is when all events have occurred. Events are ordered by the maximum likelihood event sequence for the ADNI population. CN = controls, SCD = subjective cognitive decline, MCI = mild cognitive impairment, aMCI = amnestic mild cognitive impairment, naMCI = non-amnestic mild cognitive impairment, ADD = Alzheimer’s disease dementia
See this image and copyright information in PMC

References

    1. Collaborators GBDD. Global, regional, and National burden of alzheimer’s disease and other dementias, 1990–2016: a systematic analysis for the global burden of disease study 2016. Lancet Neurol. 2019;18(1):88–106. - PMC - PubMed
    1. Sperling RA, Aisen PS, Beckett LA, Bennett DA, Craft S, Fagan AM, et al. Toward defining the preclinical stages of alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s association workgroups on diagnostic guidelines for alzheimer’s disease. Alzheimers Dement. 2011;7(3):280–92. - PMC - PubMed
    1. Parnetti L, Chipi E, Salvadori N, D’Andrea K, Eusebi P. Prevalence and risk of progression of preclinical alzheimer’s disease stages: a systematic review and meta-analysis. Alzheimers Res Ther. 2019;11(1):7. - PMC - PubMed
    1. Bertens D, Vos S, Kehoe P, Wolf H, Nobili F, Mendonça A, et al. Use of mild cognitive impairment and prodromal AD/MCI due to AD in clinical care: a European survey. Alzheimers Res Ther. 2019;11(1):74. - PMC - PubMed
    1. Blennow K, Zetterberg H. Biomarkers for alzheimer’s disease: current status and prospects for the future. J Intern Med. 2018;284(6):643–63. - PubMed

Publication types

MeSH terms