A data-driven approach for detecting gait events during turning in people with Parkinson's disease and freezing of gait

Filtjens, Benjamin; Nieuwboer, Alice; DʼCruz, Nicholas; Spildooren, Joke; Slaets, Peter; Vanrumste, Bart

doi:10.1016/j.gaitpost.2020.05.026

Cited by 26 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Clinical studies can refer to a video recorded for the patient while performing physical activities such as a PD bed test. As mentioned, in [ 18 , 43 , 70 , 87 ], a neural network was able to identify the symptoms of PD through a video sample of the patient. In the future, the clinical studies may analyze any video recorded in the hospital for other patients, for example, during therapy sessions, and predict if this patient is suspected of having PD in the future.…”

Section: Discussionmentioning

confidence: 99%

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

et al. 2021

View full text Add to dashboard Cite

Background: Parkinson’s Disease (PD) is a chronic neurodegenerative disorder that has been ranked second after Alzheimer’s disease worldwide. Early diagnosis of PD is crucial to combat against PD to allow patients to deal with it properly. However, there is no medical test(s) available to diagnose PD conclusively. Therefore, computer-aided diagnosis (CAD) systems offered a better solution to make the necessary data-driven decisions and assist the physician. Numerous studies were conducted to propose CAD to diagnose PD in the early stages. No comprehensive reviews have been conducted to summarize the role of AI tools to combat PD. Objective: The study aimed to explore and summarize the applications of neural networks to diagnose PD. Methods: PRISMA Extension for Scoping Reviews (PRISMA-ScR) was followed to conduct this scoping review. To identify the relevant studies, both medical databases (e.g., PubMed) and technical databases (IEEE) were searched. Three reviewers carried out the study selection and extracted the data from the included studies independently. Then, the narrative approach was adopted to synthesis the extracted data. Results: Out of 1061 studies, 91 studies satisfied the eligibility criteria in this review. About half of the included studies have implemented artificial neural networks to diagnose PD. Numerous studies included focused on the freezing of gait (FoG). Biomedical voice and signal datasets were the most commonly used data types to develop and validate these models. However, MRI- and CT-scan images were also utilized in the included studies. Conclusion: Neural networks play an integral and substantial role in combating PD. Many possible applications of neural networks were identified in this review, however, most of them are limited up to research purposes.

show abstract

Section: Discussionmentioning

confidence: 99%

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Both technologies are receiving increased attention due to the potential to assess FOG not only in the lab, but also in an at-home environment and thereby better capture daily-life FOG severity. Furthermore, up til now deep learning based gait assessment [81], [82], [83], including our own [84], did not yet exploit the inherent graph structured data. The established breakthrough in FOG assessment by this research might, therefore, signify further breakthroughs in deep learning-based gait assessment in general.…”

Section: Discussionmentioning

confidence: 99%

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks

Filtjens¹,

Ginis²,

Nieuwboer³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Freezing of gait (FOG) is a common and debilitating gait impairment in Parkinson's disease. Further insight in this phenomenon is hampered by the difficulty to objectively assess FOG. To meet this clinical need, this paper proposes a motion capture-based FOG assessment method driven by a novel deep neural network. The proposed network, termed multi-stage graph convolutional network (MS-GCN), combines the spatial temporal graph convolutional network (ST-GCN) and the multi-stage temporal convolutional network (MS-TCN). The ST-GCN captures the hierarchical motion among the optical markers inherent to motion capture, while the multi-stage component reduces oversegmentation errors by refining the predictions over multiple stages. The proposed model was validated on a dataset of fourteen freezers, fourteen non-freezers, and fourteen healthy control subjects. The experiments indicate that the proposed model outperforms state-of-the-art baselines. An in-depth quantitative and qualitative analysis demonstrates that the proposed model is able to achieve clinician-like FOG assessment. The proposed MS-GCN can provide an automated and objective alternative to labor-intensive clinician-based FOG assessment. I. INTRODUCTION C OMPARED to other neurological disorders, Parkinson's disease (PD) has a fast growing prevalence, doubling every 20-30 years [1]. Freezing of gait (FOG) is a common and debilitating gait impairment of PD. Up to 80% of the people with Parkinson's disease (PwPD) will develop FOG during the course of the disease [2], [3]. FOG leads to sudden blocks in walking and is clinically defined as a "brief, episodic absence or marked reduction of forward progression of the feet despite the intention to walk and reach a destination" [4]. The PwPD themselves describe freezing of gait as "the feeling that their feet are glued to the ground" [5]. Freezing episodes most frequently occur while traversing under environmental constraints, during emotional stress, during cognitive overload by means of dual-tasking, and when initiating gait [6], [7]. Though, turning hesitation was found to be the most frequent trigger of FOG [8], [9]. Subjects with FOG experience more anxiety [10], have a lower quality of life [11], and are at a much higher risk of falls [12], [13], [14], [15], [16]. Given the severe adverse effects associated with FOG, there is B. Filtjens and B. Vanrumste are with the

show abstract

“…As the MS-GCN architecture combines the best practices from MS-TCN and ST-GCN, we include these as a baseline. We additionally include a bidirectional long short term memory-based network (LSTM) [19], and temporal convolutional neural networkbased network (TCN) [12], as they are often considered an important baseline in action segmentation of MoCap data [20]- [22]. The implementation details of the employed models are visualized in Figure 3.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

“…These time-consuming tasks motivate the search for algorithms to automatically delineate the gait cycle phases and FOG episodes. State-of-the-art deep learning models tackle the gait segmentation task with TCN or LSTM-based models [20], [25]. A proprietary MoCap dataset of seven PwPD and FOG that froze during the protocol was used [30].…”

Section: Gait Phase and Freezing Of Gait Segmentation (Fog-gait)mentioning

confidence: 99%

Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks

Filtjens¹,

Vanrumste²,

Slaets³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The ability to identify and temporally segment finegrained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture longterm temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we present multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework decouples the architecture of the initial prediction generation stage from the refinement stages. Specifically, we replace the initial stage of temporal convolutions with spatial-temporal graph convolutions, which better exploit the spatial configuration of the joints and their temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework achieves state-of-the-art performance.

show abstract

A data-driven approach for detecting gait events during turning in people with Parkinson's disease and freezing of gait

Cited by 26 publications

References 23 publications

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

The Role of Neural Network for the Detection of Parkinson’s Disease: A Scoping Review

Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks

Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks

Contact Info

Product

Resources

About