A Public Data Set of Videos, Inertial Measurement Unit, and Clinical Scales of Freezing of Gait in Individuals With Parkinson's Disease During a Turning-In-Place Task

Souza, Caroline Ribeiro de; Miao, Runfeng; Oliveira, Júlia Ávila de; Lima‐Pardini, Andrea Cristina de; Campos, Débora Fragoso De; Silva‐Batista, Carla; Teixeira, Luís Augusto; Shokur, Solaiman; Bouri, Mohamed; Coelho, Daniel Boari

doi:10.3389/fnins.2022.832463

Cited by 9 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LN-inception network differs from the Inception network as it only employs two parallel convolutional operations in order to prevent overfitting. A public dataset was added to the DaphNet dataset, containing the IMU data of 38 people with PD who were turning on the spot ( 34 ). The data contained 173 FOG episodes ( 19 , 34 ).…”

Section: Discussionmentioning

confidence: 99%

Comparison of state-of-the-art deep learning architectures for detection of freezing of gait in Parkinson’s disease

Klaver,

Heijink,

Silvestri

et al. 2023

Front. Neurol.

View full text Add to dashboard Cite

IntroductionFreezing of gait (FOG) is one of the most debilitating motor symptoms experienced by patients with Parkinson’s disease (PD). FOG detection is possible using acceleration data from wearable sensors, and a convolutional neural network (CNN) is often used to determine the presence of FOG epochs. We compared the performance of a standard CNN for the detection of FOG with two more complex networks, which are well suited for time series data, the MiniRocket and the InceptionTime.MethodsWe combined acceleration data of people with PD across four studies. The final data set was split into a training (80%) and hold-out test (20%) set. A fifth study was included as an unseen test set. The data were windowed (2 s) and five-fold cross-validation was applied. The CNN, MiniRocket, and InceptionTime models were evaluated using a receiver operating characteristic (ROC) curve and its area under the curve (AUC). Multiple sensor configurations were evaluated for the best model. The geometric mean was subsequently calculated to select the optimal threshold. The selected model and threshold were evaluated on the hold-out and unseen test set.ResultsA total of 70 participants (23.7 h, 9% FOG) were included in this study for training and testing, and in addition, 10 participants provided an unseen test set (2.4 h, 11% FOG). The CNN performed best (AUC = 0.86) in comparison to the InceptionTime (AUC = 0.82) and MiniRocket (AUC = 0.76) models. For the CNN, we found a similar performance for a seven-sensor configuration (lumbar, upper and lower legs and feet; AUC = 0.86), six-sensor configuration (upper and lower legs and feet; AUC = 0.87), and two-sensor configuration (lower legs; AUC = 0.86). The optimal threshold of 0.45 resulted in a sensitivity of 77% and a specificity of 58% for the hold-out set (AUC = 0.72), and a sensitivity of 85% and a specificity of 68% for the unseen test set (AUC = 0.90).ConclusionWe confirmed that deep learning can be used to detect FOG in a large, heterogeneous dataset. The CNN model outperformed more complex networks. This model could be employed in future personalized interventions, with the ultimate goal of using automated FOG detection to trigger real-time cues to alleviate FOG in daily life.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of state-of-the-art deep learning architectures for detection of freezing of gait in Parkinson’s disease

Klaver,

Heijink,

Silvestri

et al. 2023

Front. Neurol.

View full text Add to dashboard Cite

show abstract

“…The patients involved are scored with H&Y scale. Ribeiro De Souza et al ( 2022 ), on the contrary, chose to merge the vision-based system with IMU sensors. Walking and turning videos along with the lower limb movements of 35 PD patients were recorded by an RGB camera and a shank-mounted IMU.…”

Section: Toward Automatic Recognition In Pd Based On Gait Datamentioning

confidence: 99%

Detection and assessment of Parkinson's disease based on gait analysis: A survey

Guo

Yang

Liu

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Neurological disorders represent one of the leading causes of disability and mortality in the world. Parkinson's Disease (PD), for example, affecting millions of people worldwide is often manifested as impaired posture and gait. These impairments have been used as a clinical sign for the early detection of PD, as well as an objective index for pervasive monitoring of the PD patients in daily life. This review presents the evidence that demonstrates the relationship between human gait and PD, and illustrates the role of different gait analysis systems based on vision or wearable sensors. It also provides a comprehensive overview of the available automatic recognition systems for the detection and management of PD. The intervening measures for improving gait performance are summarized, in which the smart devices for gait intervention are emphasized. Finally, this review highlights some of the new opportunities in detecting, monitoring, and treating of PD based on gait, which could facilitate the development of objective gait-based biomarkers for personalized support and treatment of PD.

show abstract

“…Often, loss of balance during RBT is caused by external perturbations; perturbations can be provided manually by a therapist [3,4], or using a device such as a programmable treadmill [5,6], moving platform [7,8], or custom slip/trip walkway [9]. To determine generalizability of RBT, reactive balance control should be assessed using a different balance perturbation method than that used in training [10].…”

Section: Introductionmentioning

confidence: 99%

The effect of reactive balance training on responses to novel unexpected balance perturbations: a feasibility study

Huntley,

Schinkel-Ivy,

Mansfield

2024

Preprint

View full text Add to dashboard Cite

Trial design: Pilot study embedded within an assessor-blinded parallel randomized controlled trial. Objective: To determine the feasibility of using unexpected and novel balance perturbations to assess the efficacy of reactive balance training. Methods: Participants: Community-dwelling adults with chronic stroke who could walk independently without a gait aid for at least 10 m. Interventions: Reactive balance training, using manual and internal perturbations, or 'traditional' balance training (control group). Training took place for one hour per session, twice per week for six weeks. Outcome: Proportion of unexpected slips triggered as intended; state anxiety, perceptions of situations, and participants' subjective responses to the unexpected slip perturbation; and spatiotemporal and kinematic features of unperturbed and perturbed walking (step length, width, and time, and mechanical stability) pre- and post-training. Randomisation: Blocked stratified randomization. Blinding: Assessors were blinded to group allocation. Results: Numbers randomised: 28 participants were randomized (15 to reactive balance training, 13 to control). Of these, nine reactive balance training group participants and seven control participants were eligible and consented to additional data collection for the pilot study. Numbers analysed: 12 participants (six per group) completed the post-training unexpected slip data collection and were included in analysis of the pilot objective. Outcome: All unexpected slips triggered as intended. Overall, participants did not report increased state anxiety or any concerns about the unexpected slip. Analysis of spatiotemporal and kinematic data suggested better stability following the unexpected slip for reactive balance trained participants than control participants; however, there were also between-group differences in spatiotemporal and kinematic features of walking pre- and post-training. Conclusions: Unexpected slips are feasible in research. However, their value as outcomes in clinical trials may depend on ensuring the groups are balanced on prognostic factors. Trial registration:ISRCTN05434601Funding: Canadian Institutes of Health Research.

show abstract

A Public Data Set of Videos, Inertial Measurement Unit, and Clinical Scales of Freezing of Gait in Individuals With Parkinson's Disease During a Turning-In-Place Task

Cited by 9 publications

References 38 publications

Comparison of state-of-the-art deep learning architectures for detection of freezing of gait in Parkinson’s disease

Comparison of state-of-the-art deep learning architectures for detection of freezing of gait in Parkinson’s disease

Detection and assessment of Parkinson's disease based on gait analysis: A survey

The effect of reactive balance training on responses to novel unexpected balance perturbations: a feasibility study

Contact Info

Product

Resources

About