Machine learning for automated differentiation of parkinson’s disease and its mimics using ¹²³I-mIBG scintigraphy: insights from a multicentre real-world cohort (ITA-mIBG study)
European Journal of Nuclear Medicine and Molecular Imaging · 2026-04 · 53 (5) · 3469-3480
DOI: 10.1007/s00259-025-07729-7 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 02.01.2026. Verfasst von Luca Filippi und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedicine and Prevention, University of Rome 'Tor Vergata', Via Montpellier, 1, 00133, Rome, Italy. luca.filippi@uniroma2.it. Hauptthemen laut MEDLINE: 3-Iodobenzylguanidine, Parkinson Disease, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: This work was partially supported by funding of the Italian Ministry of Health [Ricerca corrente].
Abstract (Originalsprache)
PURPOSE: To assess machine learning (ML) classifiers trained on harmonised multicentre ¹²³I-mIBG planar scintigraphy for differentiating Parkinson's disease (PD) from non-PD parkinsonian syndromes and to determine whether early imaging alone may ensure accurate discrimination. METHODS: This retrospective study included patients with suspected PD who underwent early (~ 15 min) and delayed (~ 240 min) imaging and received a definitive diagnosis after ≥ 12 months. Harmonised region of interest (ROI) placement and ComBat correction were applied. Early and late heart-to-mediastinum (H/M) ratios and washout rate (WR) were calculated. Differences were tested by Mann-Whitney U test, and cut-points identified by ROC analysis. Logistic regression, Gaussian naïve Bayes, and support vector machine were trained on these features with Z-score normalisation and synthetic minority oversampling technique (SMOTE). RESULTS: 127 patients were analysed (85 PD, 42 non-PD). Early and late H/M ratios were significantly lower in PD than non-PD (early H/M 1.45 ± 0.20 vs. 1.80 ± 0.20; late H/M 1.33 ± 0.22 vs. 1.68 ± 0.21; both p < 0.001). WR was modestly higher in PD (8.74 ± 5.76% vs. 6.49 ± 6.19%, p = 0.024). Optimal cut-points for PD were: early H/M ≤ 1.62 (accuracy 80.3%, sensitivity 83.3%, specificity 78.8%, and AUC 0.878), late H/M ≤ 1.52 (83.5%, 83.3%, 83.5% and 0.866) and WR ≥ 6.03% (70.1%, 70.6%, 69.0% and 0.645). ML achieved mean accuracy 78.9-80.7%, sensitivity 81.9-84.0%, specificity 68.6-78.0%, and AUC 0.850-0.875. CONCLUSION: Classifiers trained on ¹²³I-mIBG semi-quantitative indices accurately distinguished PD from non-PD. Early H/M ratio alone provided excellent discrimination, supporting early-imaging; prospective validation is warranted.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biomedicine and Prevention, University of Rome 'Tor Vergata', Via Montpellier, 1, 00133, Rome, Italy. luca.filippi@uniroma2.it.
- Nuclear Medicine Research Unit, IRCCS San Raffaele Roma, Rome, Italy. luca.filippi@uniroma2.it.
- Department of Engineering, Università degli Studi di Perugia, Perugia, Italy.
- Department of Radiological Sciences, Oncology and Anatomical Pathology, Sapienza University of Rome, Rome, Italy.
- Nuclear Medicine Unit, Interdisciplinary Department of Medicine, University "Aldo Moro", Bari, Italy.
- Unit of Nuclear Medicine, Department of Medicine, Surgery and Pharmacy, University of Sassari, Sassari, Italy.
ORCID-Profile: Luca Filippi, Francesco Bianconi
Förderung
- This work was partially supported by funding of the Italian Ministry of Health [Ricerca corrente]
Zitieren
APA
Filippi, L., Bianconi, F., Frantellizzi, V., Ferrari, C., Marongiu, A., De Feo, M. S., Battisti, C., Aghakhanyan, G., Gazzilli, M., Urbano, N., Nuvoli, S., Volterrani, D., Fravolini, M. L., Rubini, G., De Vincentis, G., Spanu, A., & Palumbo, B. (2026). Machine learning for automated differentiation of parkinson’s disease and its mimics using ¹²³I-mIBG scintigraphy: insights from a multicentre real-world cohort (ITA-mIBG study). European Journal of Nuclear Medicine and Molecular Imaging, 53(5), 3469-3480. https://doi.org/10.1007/s00259-025-07729-7
Vancouver
Filippi L, Bianconi F, Frantellizzi V, Ferrari C, Marongiu A, De Feo MS, et al. Machine learning for automated differentiation of parkinson’s disease and its mimics using ¹²³I-mIBG scintigraphy: insights from a multicentre real-world cohort (ITA-mIBG study). European Journal of Nuclear Medicine and Molecular Imaging. 2026;53(5):3469-3480. doi:10.1007/s00259-025-07729-7
BibTeX
@article{Filippi2026,
author = {Filippi, Luca and Bianconi, Francesco and Frantellizzi, Viviana and Ferrari, Cristina and Marongiu, Andrea and De Feo, Maria Silvia and Battisti, Claudia and Aghakhanyan, Gayane and Gazzilli, Maria and Urbano, Nicoletta and Nuvoli, Susanna and Volterrani, Duccio and Fravolini, Mario Luca and Rubini, Giuseppe and De Vincentis, Giuseppe and Spanu, Angela and Palumbo, Barbara},
title = {Machine learning for automated differentiation of parkinson’s disease and its mimics using ¹²³I-mIBG scintigraphy: insights from a multicentre real-world cohort (ITA-mIBG study)},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
year = {2026},
volume = {53},
number = {5},
pages = {3469--3480},
doi = {10.1007/s00259-025-07729-7}
}
EUVIMED