University of Twente Student Theses
Detection of Freezing of Gait in patients with Parkinson's Disease using a deep learning approach
Heijink, Irene (2022) Detection of Freezing of Gait in patients with Parkinson's Disease using a deep learning approach.
|
PDF
6MB |
| Abstract: | Introduction: Freezing of gait (FOG) is one of the debilitating symptoms experienced by patients with Parkinson’s Disease, and the most common cause of falls in these patients. External cueing can help to overcome FOG. In order to enhance the user experience of cueing devices and to diminish intrusiveness and habituation to cues, on-demand cueing is desired. In addition, objective FOG detection enables monitoring and objective assessment of therapy. Therefore, automatic detection of FOG needs to be developed. In this research, the performance on the detection of FOG of three deep learning classifiers based on inertial measurement unit (IMU) data is studied. Methods: Data from four studies with walking tasks ranging from straight walking, turning and obstacle course was combined. The dataset contains over 300 000 windows of which 8% was labelled as FOG. All experiments were recorded for video annotation of FOG. IMU measurements were performed using hardware and software of Xsens 3D motion tracking technology. The data was tested on three classification models: a CNN, MiniRocket and InceptionTime. Five fold cross-validation was applied to estimate an unbiased model performance. The models were evaluated using a receiver operating characteristic (ROC) curve. The model with the highest area under the ROC curve (AUC-ROC) was selected and a sensor evaluation was performed on this model. Sensors that were evaluated include the accelerometers of the upper legs, lower legs and feet. The best model in combination with the best sensor selection was trained on the training + validation set and tested on the hold out test set. Results: In total, 71 unique participants were included in this study. The highest AUC-ROC was reached for the CNN trained on the acceleration data of the lower legs and feet with an AUC-ROC of 0.72, sensitivity of 73.7% (72.5 - 75.0%) and specificity of 60.8% (60.3 - 61.3%) on the test set. The mean AUC-ROC of MiniRocket was 0.10 smaller than the AUC-ROC of the CNN, and the mean AUC-ROC of InceptionTime was 0.04 smaller than the CNN. The difference in mean AUC-ROC for the sensor combinations was 0.01. Conclusion: The classification algorithm has potential to be implemented in on-demand cueing devices and home monitoring applications for objective FOG detection. Further research is needed to optimize the model and improve the performance. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 44 medicine, 50 technical science in general |
| Programme: | Technical Medicine MSc (60033) |
| Link to this item: | https://purl.utwente.nl/essays/93483 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page