1
|
Fernandez-Bermejo J, Martinez-Del-Rincon J, Dorado J, Toro XD, Santofimia MJ, Lopez JC. Edge Computing Transformers for Fall Detection in Older Adults. Int J Neural Syst 2024; 34:2450026. [PMID: 38490957 DOI: 10.1142/s0129065724500266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/17/2024]
Abstract
The global trend of increasing life expectancy introduces new challenges with far-reaching implications. Among these, the risk of falls among older adults is particularly significant, affecting individual health and the quality of life, and placing an additional burden on healthcare systems. Existing fall detection systems often have limitations, including delays due to continuous server communication, high false-positive rates, low adoption rates due to wearability and comfort issues, and high costs. In response to these challenges, this work presents a reliable, wearable, and cost-effective fall detection system. The proposed system consists of a fit-for-purpose device, with an embedded algorithm and an Inertial Measurement Unit (IMU), enabling real-time fall detection. The algorithm combines a Threshold-Based Algorithm (TBA) and a neural network with low number of parameters based on a Transformer architecture. This system demonstrates notable performance with 95.29% accuracy, 93.68% specificity, and 96.66% sensitivity, while only using a 0.38% of the trainable parameters used by the other approach.
Collapse
Affiliation(s)
- Jesús Fernandez-Bermejo
- Faculty of Social Science and Information Technology, University of Castilla-La Mancha, 45600 Talavera de la Reina, Toledo, Spain
| | - Jesús Martinez-Del-Rincon
- The Centre for Secure Information Technologies (CSIT), Institute of Electronics, Communications & Information Technology, Queen's University of Belfast, Belfast BT3 9DT, UK
| | - Javier Dorado
- School of Computer Engineering, University of Castilla-La Mancha, 13071 Ciudad Real, Ciudad Real, Spain
| | - Xavier Del Toro
- School of Computer Engineering, University of Castilla-La Mancha, 13071 Ciudad Real, Ciudad Real, Spain
| | - María J Santofimia
- School of Computer Engineering, University of Castilla-La Mancha, 13071 Ciudad Real, Ciudad Real, Spain
| | - Juan C Lopez
- School of Computer Engineering, University of Castilla-La Mancha, 13071 Ciudad Real, Ciudad Real, Spain
| |
Collapse
|
2
|
Sekiguchi Y, Honda K, Izumi SI. Effect of Walking Adaptability on an Uneven Surface by a Stepping Pattern on Walking Activity After Stroke. Front Hum Neurosci 2022; 15:762223. [PMID: 35058764 PMCID: PMC8764227 DOI: 10.3389/fnhum.2021.762223] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2021] [Accepted: 11/16/2021] [Indexed: 11/24/2022] Open
Abstract
Real-world walking activity is important for poststroke patients because it leads to their participation in the community and physical activity. Walking activity may be related to adaptability to different surface conditions of the ground. The purpose of this study was to clarify whether walking adaptability on an uneven surface by step is related to daily walking activity in patients after stroke. We involved 14 patients who had hemiparesis after stroke (age: 59.4 ± 8.9 years; post-onset duration: 70.7 ± 53.5 months) and 12 healthy controls (age: 59.5 ± 14.2 years). The poststroke patients were categorized as least limited community ambulators or unlimited ambulators. For the uneven surface, the study used an artificial grass surface (7 m long, 2-cm leaf length). The subjects repeated even surface walking and the uneven surface walking trials at least two times at a comfortable speed. We collected spatiotemporal and kinematic gait parameters on both the even and uneven surfaces using a three-dimensional motion analysis system. After we measured gait, the subjects wore an accelerometer around the waist for at least 4 days. We measured the number of steps per day using the accelerometer to evaluate walking activity. Differences in gait parameters between the even and uneven surfaces were calculated to determine how the subjects adapted to an uneven surface while walking. We examined the association between the difference in parameter measurements between the two surface properties and walking activity (number of steps per day). Walking activity significantly and positively correlated with the difference in paretic step length under the conditions of different surface properties in the poststroke patients (r = 0.65, p = 0.012) and step width in the healthy controls (r = 0.68, p = 0.015). The strategy of increasing the paretic step length, but not step width, on an uneven surface may lead to a larger base of support, which maintains stability during gait on an uneven surface in poststroke patients, resulting in an increased walking activity. Therefore, in poststroke patients, an increase in paretic step length during gait on an uneven surface might be more essential for improving walking activity.
Collapse
Affiliation(s)
- Yusuke Sekiguchi
- Department of Physical Medicine and Rehabilitation, Graduate School of Medicine, Tohoku University, Sendai, Japan
- *Correspondence: Yusuke Sekiguchi,
| | - Keita Honda
- Department of Physical Medicine and Rehabilitation, Graduate School of Medicine, Tohoku University, Sendai, Japan
| | - Shin-Ichi Izumi
- Department of Physical Medicine and Rehabilitation, Graduate School of Medicine, Tohoku University, Sendai, Japan
- Department of Physical Medicine and Rehabilitation, Graduate School of Biomedical Engineering, Tohoku University, Sendai, Japan
| |
Collapse
|
3
|
Darbin O, Hatanaka N, Takara S, Kaneko N, Chiken S, Naritoku D, Martino A, Nambu A. Parkinsonism Differently Affects the Single Neuronal Activity in the Primary and Supplementary Motor Areas in Monkeys: An Investigation in Linear and Nonlinear Domains. Int J Neural Syst 2020; 30:2050010. [PMID: 32019380 DOI: 10.1142/s0129065720500100] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
The changes in neuronal firing activity in the primary motor cortex (M1) and supplementary motor area (SMA) were compared in monkeys rendered parkinsonian by treatment with 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine. The neuronal dynamic was characterized using mathematical tools defined in different frameworks (rate, oscillations or complex patterns). Then, and for each cortical area, multivariate and discriminate analyses were further performed on these features to identify those important to differentiate between the normal and the pathological neuronal activity. Our results show a different order in the importance of the features to discriminate the pathological state in each cortical area which suggests that the M1 and the SMA exhibit dissimilarities in their neuronal alterations induced by parkinsonism. Our findings highlight the need for multiple mathematical frameworks to best characterize the pathological neuronal activity related to parkinsonism. Future translational studies are warranted to investigate the causal relationships between cortical region-specificities, dominant pathological hallmarks and symptoms.
Collapse
Affiliation(s)
- Olivier Darbin
- Department of Neurology, University South Alabama, 307 University Blvd, Mobile, AL 36688, USA
| | - Nobuhiko Hatanaka
- Division of System Neurophysiology, National Institute for Physiological Sciences and Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Sayuki Takara
- Division of System Neurophysiology, National Institute for Physiological Sciences and Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Nobuya Kaneko
- Division of System Neurophysiology, National Institute for Physiological Sciences and Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Satomi Chiken
- Division of System Neurophysiology, National Institute for Physiological Sciences and Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Dean Naritoku
- Department of Neurology, University South Alabama, 307 University Blvd, Mobile, AL 36688, USA
| | - Anthony Martino
- Department of Neurology, University South Alabama, 307 University Blvd, Mobile, AL 36688, USA
| | - Atsushi Nambu
- Division of System Neurophysiology, National Institute for Physiological Sciences and Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| |
Collapse
|
4
|
Darbin O, Hatanaka N, Takara S, Kaneko M, Chiken S, Naritoku D, Martino A, Nambu A. Local field potential dynamics in the primate cortex in relation to parkinsonism reveled by machine learning: A comparison between the primary motor cortex and the supplementary area. Neurosci Res 2020; 156:66-79. [PMID: 31991205 DOI: 10.1016/j.neures.2020.01.012] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2019] [Revised: 11/09/2019] [Accepted: 11/29/2019] [Indexed: 12/20/2022]
Abstract
The present study compares the cortical local field potentials (LFPs) in the primary motor cortex (M1) and the supplementary motor area (SMA) of non-human primates rendered Parkinsonian with administration of dopaminergic neurotoxin, 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine. The dynamic of the LFPs was investigated under several mathematical frameworks and machine learning was used to discriminate the recordings based on these features between healthy, parkinsonian with off-medication and parkinsonian with on-medication states. The importance of each feature in the discrimination process was further investigated. The dynamic of the LFPs in M1 and SMA was affected regarding its variability (time domain analysis), oscillatory activities (frequency domain analysis) and complex patterns (non-linear domain analysis). Machine learning algorithms achieved accuracy near 0.90 for comparisons between conditions. The TreeBagger algorithm provided best accuracy. The relative importance of these features differed with the cortical location, condition and treatment. Overall, the most important features included beta oscillation, fractal dimension, gamma oscillation, entropy and asymmetry of amplitude fluctuation. The importance of features in discriminating between normal and pathological states, and on- or off-medication states depends on the pair-comparison and it is region-specific. These findings are discussed regarding the refinement of current models for movement disorders and the development of on-demand therapies.
Collapse
Affiliation(s)
- Olivier Darbin
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Neurology, University South Alabama, 307 University Blvd, Mobile, AL 36688, USA.
| | - Nobuhiko Hatanaka
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Sayuki Takara
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Masaya Kaneko
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Satomi Chiken
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| | - Dean Naritoku
- Department of Neurology, University South Alabama, 307 University Blvd, Mobile, AL 36688, USA
| | - Anthony Martino
- Department of Neurosurgery, University South Alabama, 307 University Blvd., Mobile, AL 36688, USA
| | - Atsushi Nambu
- Division of System Neurophysiology, National Institute for Physiological Sciences, Okazaki, Aichi 444-8585, Japan; Department of Physiological Sciences, SOKENDAI (Graduate University for Advanced Studies), Okazaki, Aichi 444-8585, Japan
| |
Collapse
|
5
|
Garcia-Agundez A, Folkerts AK, Konrad R, Caserman P, Tregel T, Goosses M, Göbel S, Kalbe E. Recent advances in rehabilitation for Parkinson's Disease with Exergames: A Systematic Review. J Neuroeng Rehabil 2019; 16:17. [PMID: 30696453 PMCID: PMC6352377 DOI: 10.1186/s12984-019-0492-1] [Citation(s) in RCA: 62] [Impact Index Per Article: 12.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2018] [Accepted: 01/23/2019] [Indexed: 01/31/2023] Open
Abstract
OBJECTIVE The goal of this contribution is to gather and to critically analyze recent evidence regarding the potential of exergaming for Parkinson's disease (PD) rehabilitation and to provide an up-to-date analysis of the current state of studies on exergame-based therapy in PD patients. METHODS We performed our search based on the conclusions of a previous systematic review published in 2014. Inclusion criteria were articles published in the indexed databases Pubmed, Scopus, Sciencedirect, IEEE and Cochrane published since January 1, 2014. Exclusion criteria were papers with a target group other than PD patients exclusively, or contributions not based on exergames. Sixty-four publications out of 525 matches were selected. RESULTS The analysis of the 64 selected publications confirmed the putative improvement in motor skills suggested by the results of the previous review. The reliability and safety of both Microsoft Kinect and Wii Balance Board in the proposed scenarios was further confirmed by several recent studies. Clinical trials present better (n = 5) or similar (n = 3) results than control groups (traditional rehabilitation or regular exercise) in motor (TUG, BBS) and cognitive (attention, alertness, working memory, executive function), thus emphasizing the potential of exergames in PD. Pilot studies (n = 11) stated the safety and feasibility of both Microsoft Kinect and Wii Balance Board, potentially in home scenarios as well. Technical papers (n = 30) stated the reliability of balance and gait data captured by both devices. Related meta-analyses and systematic reviews (n = 15) further support these statements, generally citing the need for adaptation to patient's skills and new input devices and sensors as identified gaps. CONCLUSION Recent evidence indicates exergame-based therapy has been widely proven to be feasible, safe, and at least as effective as traditional PD rehabilitation. Further insight into new sensors, best practices and different cognitive stadiums of PD (such as PD with Mild Cognitive Impairment), as well as task specificity, are required. Also, studies linking game parameters and results with traditional assessment methods, such as UPDRS scores, are required. Outcomes for randomized controlled trials (RCTs) should be standardized, and follow-up studies are required, particularly for motor outcomes.
Collapse
Affiliation(s)
| | - Ann-Kristin Folkerts
- Department of Medical Psychology | Neuropsychology and Gender Studies & Center for Neuropsychological Diagnostics and Intervention (CeNDI), University Hospital Cologne, Cologne, Germany
| | - Robert Konrad
- Multimedia Communications Lab, Technische Universitaet Darmstadt, Darmstadt, Germany
| | - Polona Caserman
- Multimedia Communications Lab, Technische Universitaet Darmstadt, Darmstadt, Germany
| | - Thomas Tregel
- Multimedia Communications Lab, Technische Universitaet Darmstadt, Darmstadt, Germany
| | - Mareike Goosses
- Department of Medical Psychology | Neuropsychology and Gender Studies & Center for Neuropsychological Diagnostics and Intervention (CeNDI), University Hospital Cologne, Cologne, Germany
| | - Stefan Göbel
- Multimedia Communications Lab, Technische Universitaet Darmstadt, Darmstadt, Germany
| | - Elke Kalbe
- Department of Medical Psychology | Neuropsychology and Gender Studies & Center for Neuropsychological Diagnostics and Intervention (CeNDI), University Hospital Cologne, Cologne, Germany
| |
Collapse
|