EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Detection and Severity Assessment of Parkinson’s Disease Through Analyzing Wearable Sensor Data Using Gramian Angular Fields and Deep Convolutional Neural Networks

Sayyed Mostafa Mostafavi, Shovito Barua Soumma iD, Daniel Peterson iD, Shyamal H Mehta iD, Hassan Ghasemzadeh iD

Sensors · 29.05.2025 · 25 (11) · 3421

DOI: 10.3390/s25113421 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2025. Verfasst von Sayyed Mostafa Mostafavi und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA. Hauptthemen laut MEDLINE: Parkinson Disease, Wearable Electronic Devices, Neural Networks, Computer. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Parkinson’s disease (PD) is the second-most common neurodegenerative disease. With more than 20,000 new diagnosed cases each year, PD affects millions of individuals worldwide and is most prevalent in the elderly population. The current clinical methods for the diagnosis and severity assessment of PD rely on the visual and physical examination of subjects and identifying key disease motor signs and symptoms such as bradykinesia, rigidity, tremor, and postural instability. In the present study, we developed a method for the diagnosis and severity assessment of PD using Gramian Angular Fields (GAFs) in combination with deep Convolutional Neural Networks (CNNs). Our model was applied to PD gait signals captured using pressure sensors embedded into insoles. Our results indicated an accuracy of 98.6%, a true positive rate (TPR) of 99.2%, and a true negative rate (TNR) of 98.5%, showcasing superior classification performance for PD diagnosis compared to the methods used in recent studies in the literature. The estimation of disease severity scores using gait signals showed a high accuracy for the Hoehn and Yahr score as well as the Timed Up and Go (TUG) test score (R2 > 0.8), while we achieved a lower prediction performance for the Unified Parkinson’s Disease Rating Scale (UPDRS) and its motor component (UPDRSM) scores (R2 < 0.2). These results were achieved using gait signals recorded in time windows as small as 10 s, which may pave the way for shorter, more accessible assessment tools for diagnosis and severity assessment of PD.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseaseWearable Electronic DevicesNeural Networks, ComputerHumansGaitSeverity of Illness IndexMaleAgedFemaleConvolutional Neural Networks

Stichwörter der Autor:innen

Gramian angular fieldParkinson’s diagnosis and prognosisParkinson’s diseaseconvolutional neural networkgait

Autor:innen und Institutionen

  • College of Health Solutions, Arizona State University, Phoenix, AZ 85004, USA.
  • Department of Neurology, Mayo Clinic College of Medicine, Mayo Clinic Arizona, Scottsdale, AZ 85259, USA.

ORCID-Profile: Shovito Barua Soumma, Daniel Peterson, Shyamal H Mehta, Hassan Ghasemzadeh

Zitieren

APA

Mostafavi, S. M., Soumma, S. B., Peterson, D., Mehta, S. H., & Ghasemzadeh, H. (2025). Detection and Severity Assessment of Parkinson’s Disease Through Analyzing Wearable Sensor Data Using Gramian Angular Fields and Deep Convolutional Neural Networks. Sensors, 25(11), 3421. https://doi.org/10.3390/s25113421

Vancouver

Mostafavi SM, Soumma SB, Peterson D, Mehta SH, Ghasemzadeh H. Detection and Severity Assessment of Parkinson’s Disease Through Analyzing Wearable Sensor Data Using Gramian Angular Fields and Deep Convolutional Neural Networks. Sensors. 2025;25(11):3421. doi:10.3390/s25113421

BibTeX
@article{Mostafavi2025,
  author = {Mostafavi, Sayyed Mostafa and Soumma, Shovito Barua and Peterson, Daniel and Mehta, Shyamal H and Ghasemzadeh, Hassan},
  title = {Detection and Severity Assessment of Parkinson’s Disease Through Analyzing Wearable Sensor Data Using Gramian Angular Fields and Deep Convolutional Neural Networks},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {11},
  pages = {3421},
  doi = {10.3390/s25113421}
}
Kostenlos starten →