Objective and quantitative assessment of motor function in Parkinson’s disease—from the perspective of practical applications

Yang, Ke; Xiong, Weixi; Liu, Feng‐Tao; Sun, Yi‐Min; Luo, Sushan; Ding, Zhaofeng; Wu, Jianjun; Wang, Jian

doi:10.21037/atm.2016.03.09

Cited by 40 publications

(42 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods are Thanks to their accuracy, unobtrusiveness, low cost, and ease of use, wearable sensors can represent an interesting solution for objective and quantitative evaluation of the motor performance [12]. Moreover, novel machine learning (ML) algorithms can enable mining of data acquired by wearable sensors, providing a useful tool for supporting clinicians in PD diagnosis since the beginning of the pathology [13,14].…”

Section: Clinical Backgroundmentioning

confidence: 99%

Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning

Cavallo

Moschetti

Esposito

et al. 2019

Parkinsonism & Related Disorders

View full text Add to dashboard Cite

Introduction: Parkinson's disease (PD) is a common neurodegenerative disorder characterized by disabling motor and non-motor symptoms. For example, idiopathic hyposmia (IH), which is a reduced olfactory sensitivity, is typical in > 95% of PD patients and is a preclinical marker for the pathology. Methods: In this work, a wearable inertial device, named SensHand V1, was used to acquire motion data from the upper limbs during the performance of six tasks selected by MDS-UPDRS III. Three groups of people were enrolled, including 30 healthy subjects, 30 IH people, and 30 PD patients. Forty-eight parameters per side were computed by spatiotemporal and frequency data analysis. A feature array was selected as the most significant to discriminate among the different classes both in two-group and three-group classification. Multiple analyses were performed comparing three supervised learning algorithms, Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes, on three different datasets. Results: Excellent results were obtained for healthy vs. patients classification (F-Measure 0.95 for RF and 0.97 for SVM), and good results were achieved by including subjects with hyposmia as a separate group (0.79 accuracy, 0.80 precision with RF) within a three-group classification. Overall, RF classifiers were the best approach for this application. Conclusion: The system is suitable to support an objective PD diagnosis. Further, combining motion analysis with a validated olfactory screening test, a two-step non-invasive, low-cost procedure can be defined to appropriately analyze people at risk for PD development, helping clinicians to identify also subtle changes in motor performance that characterize PD onset.

show abstract

Section: Clinical Backgroundmentioning

confidence: 99%

Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning

Cavallo

Moschetti

Esposito

et al. 2019

Parkinsonism & Related Disorders

View full text Add to dashboard Cite

show abstract

“…There has been a fair amount of research in the area of applying machine learning methods for the automatic assessment of the movement disorders associated with PD, particularly tremor and bradykinesia [14] , [15] , [17] – [19] . At the same time, there were only two reports on the application of these methods in HD [9] , [13] .…”

Section: Introductionmentioning

confidence: 99%

Automated Assessment of Movement Impairment in Huntington’s Disease

Bennasar

Hicks

Clinch

et al. 2018

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Quantitative assessment of movement impairment in Huntington’s disease (HD) is essential to monitoring of disease progression. This paper aimed to develop and validate a novel low cost, objective automated system for the evaluation of upper limb movement impairment in HD in order to eliminate the inconsistency of the assessor and offer a more sensitive, continuous assessment scale. Patients with genetically confirmed HD and healthy controls were recruited to this observational study. Demographic data, including age (years), gender, and unified HD rating scale total motor score (UHDRS-TMS), were recorded. For the purposes of this paper, a modified upper limb motor impairment score (mULMS) was generated from the UHDRS-TMS. All participants completed a brief, standardized clinical assessment of upper limb dexterity while wearing a tri-axial accelerometer on each wrist and on the sternum. The captured acceleration data were used to develop an automatic classification system for discriminating between healthy and HD participants and to automatically generate a continuous movement impairment score (MIS) that reflected the degree of the movement impairment. Data from 48 healthy and 44 HD participants was used to validate the developed system, which achieved 98.78% accuracy in discriminating between healthy and HD participants. The Pearson correlation coefficient between the automatic MIS and the clinician rated mULMS was 0.77 with a p-value < 0.01. The approach presented in this paper demonstrates the possibility of an automated objective, consistent, and sensitive assessment of the HD movement impairment.

show abstract

“…The latter is particularly relevant to PD given its multifaceted, complex and fluctuating nature [30][31][32][33]. It is important to understand whether and to what extent clinicians perceive a certain piece of evidence as informative and whether it is coming from a subjective information source (e.g., patient self-reports, diaries, questionnaires) or from an objective source e.g., wearable digital health technology, neuropsychological assessments, medical assessment techniques (such as Magnetic Resonance Imaging (MRI), blood samples) [34][35][36].…”

Section: User-centred Development Of Cdss Based On Mhealthmentioning

confidence: 99%

Designing a mHealth clinical decision support system for Parkinson’s disease: a theoretically grounded user needs approach

Timotijević

Hodgkins

Banks

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background: Despite the established evidence and theoretical advances explaining human judgments under uncertainty, developments of mobile health (mHealth) Clinical Decision Support Systems (CDSS) have not explicitly applied the psychology of decision making to the study of user needs. We report on a user needs approach to develop a prototype of a mHealth CDSS for Parkinson's disease (PD), which is theoretically grounded in the psychological literature about expert decision making and judgement under uncertainty.Methods: A suite of user needs studies was conducted in 4 European countries (Greece, Italy, Slovenia, the UK) prior to the development of PD_Manager, a mHealth-based CDSS designed for Parkinson's disease, using wireless technology. Study 1 undertook Hierarchical Task Analysis (HTA) including elicitation of user needs, cognitive demands and perceived risks/benefits (ethical considerations) associated with the proposed CDSS, through structured interviews of prescribing clinicians (N = 47). Study 2 carried out computational modelling of prescribing clinicians' (N = 12) decision strategies based on social judgment theory. Study 3 was a vignette study of prescribing clinicians' (N = 18) willingness to change treatment based on either self-reported symptoms data, devices-generated symptoms data or combinations of both. Results: Study 1 indicated that system development should move away from the traditional silos of 'motor' and 'non-motor' symptom evaluations and suggest that presenting data on symptoms according to goal-based domains would be the most beneficial approach, the most important being patients' overall Quality of Life (QoL). The computational modelling in Study 2 extrapolated different factor combinations when making judgements about different questions. Study 3 indicated that the clinicians were equally likely to change the care plan based on information about the change in the patient's condition from the patient's self-report and the wearable devices. Conclusions: Based on our approach, we could formulate the following principles of mHealth design: 1) enabling shared decision making between the clinician, patient and the carer; 2) flexibility that accounts for diagnostic and treatment variation among clinicians; 3) monitoring of information integration from multiple sources. Our approach highlighted the central importance of the patient-clinician relationship in clinical decision making and the relevance of theoretical as opposed to algorithm (technology)-based modelling of human judgment.

show abstract

Objective and quantitative assessment of motor function in Parkinson’s disease—from the perspective of practical applications

Cited by 40 publications

References 51 publications

Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning

Upper limb motor pre-clinical assessment in Parkinson's disease using machine learning

Automated Assessment of Movement Impairment in Huntington’s Disease

Designing a mHealth clinical decision support system for Parkinson’s disease: a theoretically grounded user needs approach

Contact Info

Product

Resources

About