EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Early Detection of Parkinson’s Disease Using Automatic Classification of Single-photon Emission Computed Tomography Images

Jihad Boucherouite, Abdelilah Jilbab, Atman Jbari

Healthcare Informatics Research · 31.07.2026 · 32 (3) · 274-284

DOI: 10.4258/hir.2026.32.3.274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Informatics Research, erschienen am 31.07.2026. Verfasst von Jihad Boucherouite und 2 weiteren Autor:innen. Beteiligte Einrichtung: Electrical, Electronic Systems, Sensors and Nanobiotechnologies (E2SN) research laboratory, National Higher School of Arts and Crafts (ENSAM), Mohamm…. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Parkinson’s disease (PD) is a chronic neurodegenerative disorder characterized by central nervous system dysfunction. Early identification may enable prompt treatment and help slow the progression of disabling symptoms. Previous studies have reported that clinical assessments based on visual interpretation may be insufficiently accurate and often miss early PD. Therefore, this study aimed to develop an automated single-photon emission computed tomography-based model for binary classification of healthy controls and patients with early PD.

Methods

We analyzed 514 DaTSCAN images from the Parkinson’s Progression Markers Initiative database, using one unique scan per individual. The workflow comprised three main stages: image processing; computation of 23 features, including radial, threshold, boundary, and striatal binding ratio features; and image classification using machine learning algorithms.

Results

The medium Gaussian support vector machine achieved an accuracy of 97.09% ± 1.53% (95% confidence interval, 95.11%–99.07%), sensitivity of 98.18% ± 1.48%, specificity of 93.85% ± 3.44%, and area under the receiver operating characteristic curve of 98.49% ± 1.31%. This performance was significantly higher than that of the three-dimensional convolutional neural network baseline model (accuracy, 94.55% ± 2.98%; p = 0.045), while requiring substantially less training time.

Conclusions

In this dataset, carefully designed feature engineering combined with classical machine learning outperformed the deep-learning baseline when the training data were limited and the selected features aligned with clinical diagnostic criteria. This approach achieved high accuracy for early PD detection and may provide computational efficiency and interpretability suitable for clinical implementation.

Schlagwörter

Stichwörter der Autor:innen

Computer-AssistedEarly DiagnosisImage ProcessingParkinson DiseaseSupport Vector MachineTomography

Autor:innen und Institutionen

  • Electrical, Electronic Systems, Sensors and Nanobiotechnologies (E2SN) research laboratory, National Higher School of Arts and Crafts (ENSAM), Mohammed V University of Rabat, Rabat, Morocco. jihad_boucherouite@um5.ac.ma.
  • Electrical, Electronic Systems, Sensors and Nanobiotechnologies (E2SN) research laboratory, National Higher School of Arts and Crafts (ENSAM), Mohammed V University of Rabat, Rabat, Morocco.

Zitieren

APA

Boucherouite, J., Jilbab, A., & Jbari, A. (2026). Early Detection of Parkinson’s Disease Using Automatic Classification of Single-photon Emission Computed Tomography Images. Healthcare Informatics Research, 32(3), 274-284. https://doi.org/10.4258/hir.2026.32.3.274

Vancouver

Boucherouite J, Jilbab A, Jbari A. Early Detection of Parkinson’s Disease Using Automatic Classification of Single-photon Emission Computed Tomography Images. Healthcare Informatics Research. 2026;32(3):274-284. doi:10.4258/hir.2026.32.3.274

BibTeX
@article{Boucherouite2026,
  author = {Boucherouite, Jihad and Jilbab, Abdelilah and Jbari, Atman},
  title = {Early Detection of Parkinson’s Disease Using Automatic Classification of Single-photon Emission Computed Tomography Images},
  journal = {Healthcare Informatics Research},
  year = {2026},
  volume = {32},
  number = {3},
  pages = {274--284},
  doi = {10.4258/hir.2026.32.3.274}
}
Kostenlos starten →