Machine learning -driven discovery of Parkinsonian-like phenotypes in idiopathic REM sleep behavior disorder
Neurological Sciences · 2026-04 · 47 (4)
DOI: 10.1007/s10072-026-08945-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurological Sciences, online erschienen am 13.03.2026. Verfasst von D L Giardino und 7 weiteren Autor:innen. Beteiligte Einrichtung: Unidad de Medicina del sueño, Seccion Neurolgia, Centro de Educación Médica e Investigaciones Clínicas "Norberto Quirno" (CEMIC), Buenos Aires, Argen…. Hauptthemen laut MEDLINE: REM Sleep Behavior Disorder, Machine Learning, Parkinson Disease, Parkinsonian Disorders. Die Arbeit nennt 34 Literaturangaben.
Abstract (Originalsprache)
INTRODUCTION: This study harnessed AI-powered tools like principal component analysis (PCA) and multivariate models (PCA-MV) to integrate clinical and laboratory data from Parkinson’s disease (PD) patients, individuals with idiopathic REM sleep behavior disorder (iRBD), and healthy controls. The aim was to identify phenotypic similarities between iRBD and PD and to explore subgroup patterns within the iRBD population. METHODS: Baseline clinical and laboratory data were analyzed from 49 participants: PD (n = 15), iRBD (n = 19), and healthy controls (n = 14). Variables included Hoehn and Yahr scale, UPDRS Part III, MOCA, MMSE, SCOPA-cognitive, SCOPA-Autonomic Test, Beck Depression Inventory, Farnsworth Munsell 100 Hue Test, PSQI, ESS, RBDQ-HKQ, polysomnography/video-polysomnography and plasma microRNA 27/29 levels. PCA was used for dimensionality reduction, followed by supervised machine learning models, including logistic regression and support vector machines (SVM). Model performance was assessed using F1-scores. RESULTS: Supervised classification models effectively differentiated PD patients from healthy controls. The PCA–SVM approach achieved high performance (F1-score = 0.92), with radial basis function kernels providing the best separation. Using this model, 69% of iRBD patients clustered within the Parkinsonian feature space defined by shared clinical and biological characteristics. CONCLUSION: Multivariate machine learning combined with dimensionality reduction enables the integration of heterogeneous clinical and molecular data, improving the identification of similarities and subgroup patterns across neurological conditions. PCA-based models may be useful for stratifying iRBD patients according to their degree of similarity to PD.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Unidad de Medicina del sueño, Seccion Neurolgia, Centro de Educación Médica e Investigaciones Clínicas "Norberto Quirno" (CEMIC), Buenos Aires, Argentina. giardinodaniela@gmail.com.
- Experiment Division, ALBA Synchrotron, Cerdanyola del Valles, Barcelona, Spain.
- Universidad Nacional de San Martin (UNSAM)-CONICET, Buenos Aires, Argentina.
- Instituto de Investigaciones Biotecnológicas-Escuela de Ciencia y Nanotecnologías (EByN), San Martín, Argentina.
- Servicio de Neurologia- CEMIC, CABA, Argentina.
- Hospital Italiano, Medicina del Sueño, CABA, Argentina.
Zitieren
APA
Giardino, D. L., Huck-Iriart, C., Gonzalez, P. M., Aguirre, P. A., Fededa, J. P., Peralta, C., Valiensi, S. M., & Garay, A. (2026). Machine learning -driven discovery of Parkinsonian-like phenotypes in idiopathic REM sleep behavior disorder. Neurological Sciences, 47(4). https://doi.org/10.1007/s10072-026-08945-1
Vancouver
Giardino DL, Huck-Iriart C, Gonzalez PM, Aguirre PA, Fededa JP, Peralta C, et al. Machine learning -driven discovery of Parkinsonian-like phenotypes in idiopathic REM sleep behavior disorder. Neurological Sciences. 2026;47(4). doi:10.1007/s10072-026-08945-1
BibTeX
@article{Giardino2026,
author = {Giardino, D L and Huck-Iriart, C and Gonzalez, P M and Aguirre, P A and Fededa, J P and Peralta, C and Valiensi, S M and Garay, A},
title = {Machine learning -driven discovery of Parkinsonian-like phenotypes in idiopathic REM sleep behavior disorder},
journal = {Neurological Sciences},
year = {2026},
volume = {47},
number = {4},
doi = {10.1007/s10072-026-08945-1}
}
EUVIMED