EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Decoding Parkinson’s progression: A multi-modal SuStaIn ensemble approach validated on real-world PPMI data

Moad Hani, Saïd Mahmoudi, Mohammed Benjelloun

Neurobiology of Disease · 2026-07 · 225 · 107435

DOI: 10.1016/j.nbd.2026.107435 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Neurobiology of Disease, 2026-07. Verfasst von Moad Hani und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer and Management Engineering Department, Faculty of Engineering, University of Mons, 7000 Mons, Belgium. Electronic address: moad.hani@umons.a…. Hauptthemen laut MEDLINE: Parkinson Disease, Disease Progression. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Université de Mons.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Parkinson's disease (PD) exhibits substantial heterogeneity in clinical presentation and longitudinal progression, complicating prognosis, trial design, and precision therapeutics. While the Subtype and Stage Inference (SuStaIn) algorithm family offers probabilistic disease progression modeling, comprehensive comparative analyses and real-world validation remain limited. OBJECTIVE: To systematically compare major SuStaIn variants for PD progression modeling and validate their stability and prognostic utility using both controlled simulated data and real-world Parkinson's Progression Markers Initiative (PPMI) cohorts. METHODS: We constructed a biologically grounded simulated PD cohort (n=400; 5 visits over 4 years; 12 motor and non-motor biomarkers) with three predefined progression subtypes reflecting realistic noise, missingness (7.7%), and effect sizes informed by PPMI literature. Six SuStaIn variants were benchmarked: Z-score, Ordinal, Event-based Mixture, Missing Data, s-SuStaIn, and Temporal SuStaIn. We then applied identical variants to baseline PPMI data (N=624; PD=427; prodromal=197) using MDS-UPDRS I-IV, MoCA, GDS, STAI, SCOPA-AUT, RBD screening, ESS, and UPSIT. We assessed cross-sectional subtype structure, test-retest stability (Cohen's κ), and prognostic performance for motor worsening, cognitive decline, dyskinesia, and advanced therapy using Cox models with concordance indices and 95% confidence intervals. RESULTS: Simulation analyses revealed six clinically interpretable biomarker domains (motor complications, olfactory, cognitive-sleep, neuropsychiatric/autonomic, early non-motor, motor-depression) and three progression subtypes (slow 26.5%, intermediate 46.8%, fast 26.8%). Temporal and s-SuStaIn variants achieved optimal balance of accuracy (ARI: 0.058 and 0.047), stability, and cluster separation (silhouette: 0.284 and 0.267). In PPMI validation, all variants converged on three subtypes: benign motor-predominant (30.0%, age 61.4 ± 9.2 years), intermediate mixed (42.9%, age 64.8 ± 8.7 years), and diffuse-malignant (27.1%, age 67.3 ± 7.9 years, PIGD-dominant). Augmenting clinical covariates with ensemble SuStaIn subtypes improved motor progression prediction (c-index: 0.674 [0.648-0.701] to 0.741 [0.718-0.765], Δc=+0.067, p

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseaseDisease ProgressionHumansMaleFemaleMiddle AgedAgedAlgorithmsPrognosisCohort StudiesBiomarkers

Stichwörter der Autor:innen

Biomarker analysisDisease progression modelingMachine learningPPMI cohortParkinson’s diseasePatient stratificationPrognostic validationSuStaIn algorithm

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Computer and Management Engineering Department, Faculty of Engineering, University of Mons, 7000 Mons, Belgium. Electronic address: moad.hani@umons.ac.be.
  • Computer and Management Engineering Department, Faculty of Engineering, University of Mons, 7000 Mons, Belgium. Electronic address: said.mahmoudi@umons.ac.be.
  • Computer and Management Engineering Department, Faculty of Engineering, University of Mons, 7000 Mons, Belgium. Electronic address: mohammed.benjelloun@umons.ac.be.

Förderung

  • Université de Mons

Zitieren

APA

Hani, M., Mahmoudi, S., & Benjelloun, M. (2026). Decoding Parkinson’s progression: A multi-modal SuStaIn ensemble approach validated on real-world PPMI data. Neurobiology of Disease, 225, 107435. https://doi.org/10.1016/j.nbd.2026.107435

Vancouver

Hani M, Mahmoudi S, Benjelloun M. Decoding Parkinson’s progression: A multi-modal SuStaIn ensemble approach validated on real-world PPMI data. Neurobiology of Disease. 2026;225:107435. doi:10.1016/j.nbd.2026.107435

BibTeX
@article{Hani2026,
  author = {Hani, Moad and Mahmoudi, Saïd and Benjelloun, Mohammed},
  title = {Decoding Parkinson’s progression: A multi-modal SuStaIn ensemble approach validated on real-world PPMI data},
  journal = {Neurobiology of Disease},
  year = {2026},
  volume = {225},
  pages = {107435},
  doi = {10.1016/j.nbd.2026.107435}
}
Kostenlos starten →