.png){kind=icon}
.png){kind=icon}
Return
Integrative deep learning framework for Parkinson’s disease early detection using gait cycle data measured by wearable sensors: a CNN-GRU-GNN approach
.png){kind=icon}
PRE
AI
A
A
DOI：10.1007/s00500-025-10733-6.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Efficient early diagnosis is paramount in addressing the complexities of Parkinson’s disease (PD) because timely intervention can substantially mitigate symptom progression and improve patient outcomes. In this paper, we present a pioneering deep learning architecture tailored for the binary classification of subjects, utilizing gait cycle datasets to facilitate early detection of PD. Our model harnesses the power of 1D-Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Graph Neural Network (GNN) layers, synergistically capturing temporal dynamics and spatial relationships within the data. In this work, 16 wearable sensors located at the end of subjects’ shoes for measuring the vertical Ground Reaction Force (vGRF) are considered as the vertices of a graph, their adjacencies are modelled as edges of this graph, and finally, the measured data of each sensor is considered as the feature vector of its corresponding vertex. Therefore, the GNN layers can extract the relations among these sensors by learning proper representations. Regarding the dynamic nature of these measurements, Gated Recurrent Unit (GRU) and CNN are used to analyze them spatially and temporally and map them to an embedding space. Remarkably, our proposed model achieves exceptional performance metrics, boasting accuracy, precision, recall, and F1 score values of 99.51%, 99.57%, 99.71%, and 99.64%, respectively.
Keywords:
Parkinson’s disease
Vertical ground reaction force
Convolution Neural Network
Graph Neural Network
Gated Recurrent Unit
Journal
IF:
2.5
Papers:
1.0W
Citations:
2.1W
Organization
Cited Papers