Quantitative analysis of finger and forearm movements in patients with off state early stage Parkinson's disease and scans without evidence of dopaminergic deficit (SWEDD)

Kwon, Do Young; Kwon, Yuri; Kim, Ji Won

doi:10.1016/j.parkreldis.2018.07.012

Cited by 17 publications

(30 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from these, rounding errors or inconsistent reporting of results also exist. Furthermore, although we treated the differentiation of PD from SWEDD as subtyping, there is ongoing controversy regarding whether it should be considered as differential diagnosis or subtyping (Lee et al, 2014 ; Erro et al, 2016 ; Chou, 2017 ; Kwon et al, 2018 ). Given these limitations, clinicians interested in adapting machine learning models or implementing diagnostic systems based on novel biomarkers are advised to interpret published results with care.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Mei

Desrosiers

Frasnelli

2021

Front. Aging Neurosci.

212

View full text Add to dashboard Cite

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Mei

Desrosiers

Frasnelli

2021

Front. Aging Neurosci.

212

View full text Add to dashboard Cite

show abstract

“…The gyro sensor has been used to quantitatively analyze the clinical features for patients with movement disorders because it can measure angular movements and is free from gravity artifact. Indeed, many studies have attempted quantitative analysis of bradykinesia by using gyro sensors in PD patients [ 14 , 15 , 16 , 17 ] and scans without evidence of dopaminergic deficit (SWEDD) [ 15 ]. Although Parkinson’s tremor has been investigated by using the gyro sensor [ 23 , 24 ], quantitative measures of ET have still been required because of the difference of clinical features between ET and Parkinson’s tremors.…”

Section: Discussionmentioning

confidence: 99%

“…That is, the gyro sensor was shown to be helpful for the evaluation of tremor patterns. Actually, it has been reported that the gyro sensor based system was used to quantify upper limb bradykinesia [ 14 , 15 , 16 ] as well as lower limb bradykinesia [ 17 ] in patients with Parkinson’s disease (PD). Moreover, quantitative evaluation of motor function in patients with mild-to-moderate carpal tunnel syndrome was investigated using the gyro sensor [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

Quantitative measures of postural tremor at the upper limb joints in patients with essential tremor

Kwon

Choi

et al. 2020

THC

Self Cite

View full text Add to dashboard Cite

BACKGROUND: It is important to quantitatively assess tremor for accurate diagnosis and evaluation of the response to interventions in patients with essential tremor (ET). OBJECTIVE: The purpose of this study was to investigate the relationship between quantitative measures of postural tremor and clinical rating scale in patients with ET. METHODS: 18 ET patients performed a postural tremor task that required them to hold their arms outstretched parallel to the floor while wearing a gyro sensor based measurement system. The time domain variables were derived from the sensor signals. Additionally, the frequency domain variables were derived from the power spectrum of the angular velocity signal. Spearman correlation analysis was employed in the relationship between the variables and clinical score. RESULTS: The RMS angular velocity of roll and yaw directions at the hand joint were strongly correlated with the clinical rating scale (r = 0.7, p < 0.01). Similarly, the peak power of roll and yaw directions at the hand joint were moderately correlated with the clinical rating scale (r = 0.61 and r = 0.67, p < 0.01). In contrast, no significant correlation coefficients were observed in the peak frequency (p > 0.05). CONCLUSION: These results indicate that hand tremor of roll and yaw directions are more associated with assessment of severity of ET compared to other joints. This study suggests that quantitative measurements of postural tremor should be considered as tremor directionality as well as attachment location.

show abstract

“…dyskinetic CP [13], spasticity [141] Smoothness Difference between movement accelerometer readings & smoothed readings [122]; Number of movement units [BAI]; number of speed peaks (NSP) [114] Stroke [122], spasticity [141] Coefficient of variation Coefficient of variation of amplitude, speed & frequency [64,71]; STD of a 1-second sliding window of the RMS excursion angle divided by the mean & Coefficient of variation of acceleration & angular velocity [58]; Coefficient of variation of excursion angle [58,69,79,101]; Coefficient of variation of angular velocity [79]; Coefficient of variation of inter-tapinterval [144] PD [58,64,69,71,79,83,101], tremor [144] Rhytm STD of intervals a single finger tap movement in 60 sec [51]; Any sequence of regularly recurring events [67]; PD [51,67] Variability RMS error between the reference trial and the warped trial [117] Stroke [117] Higuchu's fractal dimension (HFD) Geometrical structure of non-linear time series [12] CP [12] Correlation between axes Mean, STD, skewness and kurtosis of signal derivative [86]; Correlation between each two axes of accelerometer [29] PD [76,86,89,99], HD [29], stroke [115] Peak of normalized cross-correlati...…”

Section: Max Accelerationmentioning

confidence: 99%

“…lower RMS amplitudes for PD patients in comparison with controls and Jun et al found decreasing angular displacement with increasing bradykinesia scores, but this was based on visual observation[60,79]. Chan et al found higher values for angular displacement for patients with PD with tremor in comparison with essential tremor[92].…”

mentioning

confidence: 98%

Assessment of upper limb movement disorders using wearable sensors during functional tasks: a systematic review

Vanmechelen

Haberfehlner

Vleeschhauwer

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Studies aiming to objectively quantify upper limb movement disorders during functional tasks using wearable sensors have recently increased, but there is a wide variety in described measurement and analyzing methods, hampering standardization of methods in research and clinics. Therefore, the primary objective of this review was to provide an overview of sensor set-up and type, included tasks, sensor features and methods used to quantify movement disorders during upper limb tasks in multiple pathological populations. The secondary objective was to select the most sensitive sensor features for symptom detection and quantification and discuss application of the proposed methods in clinical practice. Methods: A literature search using Scopus, Web of Science, and PubMed was performed. Articles needed to meet following criteria: (1) participants were adults/children with a neurological disease, (2) (at least) one sensor was placed on the upper limb for evaluation of movement disorders during functional tasks, (3) comparisons between: groups with/without movement disorders, sensor features before/after intervention, or sensor features with a clinical scale for assessment of the movement disorder. (4) Outcome measures included sensor features from acceleration/angular velocity signals. Results: A total of 101 articles were included, of which 56 researched Parkinsons Disease. Wrist(s), hand and index finger were the most popular sensor locations. The most frequent tasks for assessment were: finger tapping, wrist pro/supination, keeping the arms extended in front of the body and finger-to-nose. The most frequently calculated sensor features were mean, standard deviation, root-mean-square, ranges, skewness, kurtosis and entropy of acceleration and/or angular velocity, in combination with dominant frequencies and power of acceleration signals. Examples of clinical applications were automatization of a clinical scale or discrimination between a patient/control group or different patient groups. Conclusion: Current overview can support clinicians and researchers to select the most sensitive pathology-dependent sensor features and measurement methodologies for detection and quantification of upper limb movement disorders and for the objective evaluations of treatment effects. The insights from Parkinsons Disease studies can accelerate the development of wearable sensors protocols in the remaining pathologies, provided that there is sufficient attention for the standardisation of protocols, tasks, feasibility and data analysis methods.

show abstract

Quantitative analysis of finger and forearm movements in patients with off state early stage Parkinson's disease and scans without evidence of dopaminergic deficit (SWEDD)

Cited by 17 publications

References 30 publications

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Quantitative measures of postural tremor at the upper limb joints in patients with essential tremor

Assessment of upper limb movement disorders using wearable sensors during functional tasks: a systematic review

Contact Info

Product

Resources

About