1
|
Sharma P, Pahuja SK, Veer K. A Systematic Review of Machine Learning Based Gait characteristics in Parkinson's disease. Mini Rev Med Chem 2021; 22:1216-1229. [PMID: 34579631 DOI: 10.2174/1389557521666210927151553] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Revised: 04/29/2021] [Accepted: 05/18/2021] [Indexed: 11/22/2022]
Abstract
OBJECTIVE Parkinson's disease is a pervasive neuro disorder that affects people's quality of life throughout the world. The unsatisfactory results of clinical rating scales open the door for more research. PD treatment using current biomarkers seems a difficult task. So automatic evaluation at an early stage may enhance the quality and time-period of life. METHODS Grading of Recommendations Assessment, Development, and Evaluation (GRADE) and Population, intervention, comparison, and outcome (PICO) search methodology schemes are followed to search the data and eligible studies for this survey. Approximate 1500 articles were extracted using related search strings. After the stepwise mapping and elimination of studies, 94 papers are found suitable for the present review. RESULTS After the quality assessment of extracted studies, nine inhibitors are identified to analyze people's gait with Parkinson's disease, where four are critical. This review also differentiates the various machine learning classification techniques with their PD analysis characteristics in previous studies. The extracted research gaps are described as future perspectives. Results can help practitioners understand the PD gait as a valuable biomarker for detection, quantification, and classification. CONCLUSION Due to less cost and easy recording of gait, gait-based techniques are becoming popular in PD detection. By encapsulating the gait-based studies, it gives an in-depth knowledge of PD, different measures that affect gait detection and classification.
Collapse
Affiliation(s)
- Pooja Sharma
- Department of Instrumentation and Control Engineering, Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab. India
| | - S K Pahuja
- Department of Instrumentation and Control Engineering, Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab. India
| | - Karan Veer
- Department of Instrumentation and Control Engineering, Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab. India
| |
Collapse
|
2
|
Abstract
AbstractObjective:Electroencephalography (EEG) has an influential role in neuroscience and commercial applications. Most of the tools available for EEG signal analysis use machine learning to extract the required information. So, the study of robust techniques for feature extraction and classification is an important thing to understand the practical use of EEG. The paper aims that if there is any special tool for a particular task. Which feature domain or classifier has a significant role in EEG signal analysis?Approach:It presents a detailed report of the current trend for bio-electrical signals classification focusing on various classifiers’ advantages and disadvantages. This study includes literature from 2000 to 2021 with a brief description of EEG signal origin and advancement in classification techniques.Results:Randomly used classifiers for EEG signal can be categorized into five classes, namely Linear Classifiers, Nearest Neighbor Classifiers, Nonlinear Bayesian Classifiers, Neural Networks, and Combinations of Classifiers. Approximately 40% of studies use Support Vector Machine, Nearest Neighbor, and their combination with others. For specific tasks, particular classifiers are recommended in the survey. Features can be defined into four categories, namely TDFs, FDFs, TFDFs, and statistical features, where 39% of studies used TFDFs. Multi-domains features are preferred when the required information cannot be obtained from one domain.Significance:The paper summarizes the recent approaches for feature extraction and classification of EEG signals. It describes the brain waves with their classification, related behavior, and task with the physiological correlation. The comparative analysis of different classifiers, toolbox, the channel used, accuracy, and the number of subjects from various studies can help the practitioners choose a suitable classifier. Furthermore, future directions can cope up with the relevant problems and can lead to accurate classification.
Collapse
|
3
|
Hwang S, Song CS. Relationship between manual dexterity and the unified parkinson's disease rating scale-motor exam. J Phys Ther Sci 2017; 28:3403-3406. [PMID: 28174461 PMCID: PMC5276770 DOI: 10.1589/jpts.28.3403] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2016] [Accepted: 08/20/2016] [Indexed: 11/24/2022] Open
Abstract
[Purpose] The purpose of this study was to examine the relationships between manual
dexterity and the Unified Parkinson’s Disease Rating Scale-Motor Exam as a clinical tool
for quantifying upper extremity function in persons with Parkinson’s disease. [Subjects
and Methods] Thirty-two persons with idiopathic Parkinson’s disease participated in this
study. This study measured two clinical outcomes, the box-and-block test and the Unified
Parkinson’s Disease Rating Scale-Motor Exam, to investigate the relationships between
manual dexterity and the Unified Parkinson’s Disease Rating Scale-Motor Exam. [Results]
The box-and-block test on the more affected side was positive relationship with the
box-and-block test on the less affected side. The Unified Parkinson’s Disease Rating
Scale-motor exam score had a negative correlation with the box-and-block test results for
both sides. [Conclusion] A positive association was noted between manual dexterity and
motor function in patients with idiopathic Parkinson disease. The results of this study
suggest that the box-and-block test and the Unified Parkinson’s Disease Rating Scale-Motor
Exam are good clinical measures that quantify upper extremity function and are necessary
for the accurate evaluation of patients and to plan intervention strategies.
Collapse
Affiliation(s)
- Sujin Hwang
- Department of Physical Therapy, Division of Health Science, Baekseok University, Republic of Korea
| | - Chiang-Soon Song
- Department of Occupational Therapy, College of Health Science, Chosun University, Republic of Korea
| |
Collapse
|
4
|
Takimoto K, Takebayashi H, Miyamoto K, Takuma Y, Inoue Y, Miyamoto S, Okabe T, Okuda T, Kaba H. Comparison of timing and force control of foot tapping between elderly and young subjects. J Phys Ther Sci 2016; 28:1909-15. [PMID: 27390445 PMCID: PMC4932086 DOI: 10.1589/jpts.28.1909] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2016] [Accepted: 03/12/2016] [Indexed: 11/24/2022] Open
Abstract
[Purpose] To examine the ability of young and elderly individuals to control the timing
and force of periodic sequential foot tapping. [Subjects and Methods] Participants were 10
young (age, 22.1 ± 4.3 years) and 10 elderly individuals (74.8 ± 6.7 years) who were
healthy and active. The foot tapping task consisted of practice (stimulus-synchronized
tapping with visual feedback) and recall trials (self-paced tapping without visual
feedback), periodically performed in this order, at 500-, 1,000-, and 2,000-ms target
interstimulus-onset intervals, with a target force of 20% maximum voluntary contraction of
the ankle plantar-flexor muscle. [Results] The coefficients of variation of force and
intertap interval, used for quantifying the steadiness of the trials, were significantly
greater in the elderly than in the young individuals. At the 500-ms interstimulus-onset
interval, age-related effects were observed on the normalized mean absolute error of
force, which was used to quantify the accuracy of the trials. The coefficients of
variation of intertap interval for elderly individuals were significantly greater in the
practice than in the recall trials at the 500- and 1,000-ms interstimulus-onset intervals.
[Conclusion] The elderly individuals exhibited greater force and timing variability than
the young individuals and showed impaired visuomotor processing during foot tapping
sequences.
Collapse
Affiliation(s)
- Koji Takimoto
- Department of Physical Therapy, Tosa Rehabilitation College, Japan; Department of Physiology, Kochi Medical School, Kochi University, Japan
| | | | - Kenzo Miyamoto
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Yutaka Takuma
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Yoshikazu Inoue
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Shoko Miyamoto
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Takao Okabe
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Takahiro Okuda
- Department of Physical Therapy, Tosa Rehabilitation College, Japan
| | - Hideto Kaba
- Department of Physiology, Kochi Medical School, Kochi University, Japan
| |
Collapse
|
5
|
Son H, Kim E. Kinematic analysis of arm and trunk movements in the gait of Parkinson's disease patients based on external signals. J Phys Ther Sci 2015; 27:3783-6. [PMID: 26834352 PMCID: PMC4713791 DOI: 10.1589/jpts.27.3783] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2015] [Accepted: 09/17/2015] [Indexed: 12/04/2022] Open
Abstract
[Purpose] To investigate the role of external cues on arm swing amplitude and trunk
rotation in Parkinson’s disease. [Subjects and Methods] The subjects were 13 elderly
patients with Parkinson’s disease. Subjects walked under four different conditions in a
random order: no cue, visual cue, auditory cue, and combined cue. The auditory cue
velocity consisted of a metronome beat 20% greater than the subject’s general gait speed.
For the visual cue condition, bright yellow colored strips of tape placed on the floor at
intervals equal to 40% of each subject’s height. A motion analysis system was used to
measure arm swing amplitude and trunk rotation during walking. [Results] There was a
significant difference in the kinematic variables (arm swing amplitude) between different
cues, but there was not a significant difference in the kinematic variables with respect
to the trunk rotation. [Conclusion] The findings of this study indicate that patients with
Parkinson’s disease are likely to focus attention on auditory cues. The measurement of arm
and trunk kinematics during gait by auditory cues can increase the available methods for
the analysis of complex motor programs in movement disorders.
Collapse
Affiliation(s)
- Hohee Son
- Department of Physical Therapy, College of Health Sciences, Catholic University of Pusan, Republic of Korea
| | - Eunjung Kim
- Department of Physical Therapy, Masan University, Republic of Korea
| |
Collapse
|
6
|
Yu L, Zhang Q, Hu C, Huang Q, Ye M, Li D. Effects of different frequencies of rhythmic auditory cueing on the stride length, cadence, and gait speed in healthy young females. J Phys Ther Sci 2015; 27:485-7. [PMID: 25729197 PMCID: PMC4339167 DOI: 10.1589/jpts.27.485] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/29/2014] [Accepted: 09/02/2014] [Indexed: 11/24/2022] Open
Abstract
[Purpose] The aim of this study was to explore the effects of different frequencies of
rhythmic auditory cueing (RAC) on stride length, cadence, and gait speed in healthy young
females. The findings of this study might be used as clinical guidance of physical therapy
for choosing the suitable frequency of RAC. [Subjects] Thirteen healthy young females were
recruited in this study. [Methods] Ten meters walking tests were measured in all subjects
under 4 conditions with each repeated 3 times and a 3-min seated rest period between
repetitions. Subjects first walked as usual and then were asked to listen carefully to the
rhythm of a metronome and walk with 3 kinds of RAC (90%, 100%, and 110% of the mean
cadence). The three frequencies (90%, 100%, and 110%) of RAC were randomly assigned. Gait
speed, stride length, and cadence were calculated, and a statistical analysis was
performed using the SPSS (version 17.0) computer package. [Results] The gait speed and
cadence of 90% RAC walking showed significant decreases compared with normal walking and
100% and 110% RAC walking. The stride length, cadence, and gait speed of 110% RAC walking
showed significant increases compared with normal walking and 90% and 100% RAC walking.
[Conclusion] Our results showed that 110% RAC was the best of the 3 cueing frequencies for
improvement of stride length, cadence, and gait speed in healthy young females.
Collapse
Affiliation(s)
- Lili Yu
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| | - Qi Zhang
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| | - Chunying Hu
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| | - Qiuchen Huang
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| | - Miao Ye
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| | - Desheng Li
- Capital Medical University, School of Rehabilitation Medicine, China ; China Rehabilitation Research Center, Department of Physical Therapy, China
| |
Collapse
|
7
|
Lim H. Effect of the modulation of optic flow speed on gait parameters in children with hemiplegic cerebral palsy. J Phys Ther Sci 2014; 26:145-8. [PMID: 24567695 PMCID: PMC3927028 DOI: 10.1589/jpts.26.145] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2013] [Accepted: 08/25/2013] [Indexed: 11/24/2022] Open
Abstract
[Purpose] We investigated the effects of modulation of the optic flow speed on gait
parameters in children with hemiplegic cerebral palsy. [Methods] We examined 10 children
with hemiplegic cerebral palsy. The children underwent gait analysis under 3 different
conditions of optic flow speed: slow, normal, and fast optic flow speed. The children
walked across the walkway of a GAITRite system, while watching a virtual reality screen,
and walking velocity, cadence, stride length, step length, single support time, and double
support time were recorded. [Results] Compared with the other applied flow speed
conditions, the fast optic flow speed (2 times the normal speed) significantly increased
walking velocity, cadence, normalized step length, base of support, and single support
cycle of both the paretic and non-paretic lower limbs. Moreover, compared with the other
applied flow speed conditions, the slow optic flow speed (0.25 times the normal speed)
yielded a significantly decreased walking velocity, cadence, normalized step length, base
of support, and single support cycle for both the paretic and non-paretic lower limbs.
[Conclusion] The gait parameters of children with hemiplegic cerebral palsy are altered by
modulation of the optic flow speed. Thus, we believe that gait training involving
modulation of the optic flow speed is feasible and suitable for resolving abnormal gait
patterns in children with hemiplegic cerebral palsy.
Collapse
Affiliation(s)
- Hyungwon Lim
- Department of Physical Therapy, Medical School, Dankook University Chonan Campus
| |
Collapse
|