Objective Assessment of the Finger Tapping Task in Parkinson's Disease and Control Subjects using Azure Kinect and Machine Learning

Amprimo, Gianluca; Rechichi, Irene; Ferraris, Claudia; Olmo, Gabriella

doi:10.1109/cbms58004.2023.00293

Cited by 1 publication

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different classifiers can be trained to perform the classification, once feature extraction has been completed, with SVM [49] (with its different variants/kernels) being by far the most popular [37,39,40,43,46,47].…”

Section: Classifiersmentioning

confidence: 99%

“…On the other hand, multi-classifiers [50] (a.k.a. ensembles) are popular, the most widely used being random forest (RF) [42,46,47,51] and XGBoost [46,47,52]. Last but not least, conventional classifiers (such as Naïve Bayes [39,42], k-nearest neighbors [46,47], and logistic regression [39,42]) have commonly been used as baselines.…”

Section: Classifiersmentioning

confidence: 99%

“…• Fairly balanced datasets (IR < 2): the proportions between Parkinson's disease patients and healthy controls are balanced [27,39,40,42,47].…”

Section: Ir = Number O F Majority Number O F Minoritymentioning

confidence: 99%

“…The increasing use of Mediapipe must be noted in some of the most recent studies that were reviewed [17,45,47], replacing OpenPose [24], which was the most widely used in previous years [41][42][43].…”

mentioning

confidence: 99%

“…Accuracy: by far the most common measure [37,[39][40][41][42][45][46][47], the foundation and common understanding of its meaning is what makes accuracy so popular (e.g., the number of successful outcomes divided by the total number of examples). Even a nonfamiliar reader could determine the achievement level by interpreting the accuracy percentage.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Computer Vision for Parkinson’s Disease Evaluation: A Survey on Finger Tapping

Amo-Salas,

Olivares-Gil,

García-Bustillo

et al. 2024

Healthcare

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a progressive neurodegenerative disorder whose prevalence has steadily been rising over the years. Specialist neurologists across the world assess and diagnose patients with PD, although the diagnostic process is time-consuming and various symptoms take years to appear, which means that the diagnosis is prone to human error. The partial automatization of PD assessment and diagnosis through computational processes has therefore been considered for some time. One well-known tool for PD assessment is finger tapping (FT), which can now be assessed through computer vision (CV). Artificial intelligence and related advances over recent decades, more specifically in the area of CV, have made it possible to develop computer systems that can help specialists assess and diagnose PD. The aim of this study is to review some advances related to CV techniques and FT so as to offer insight into future research lines that technological advances are now opening up.

show abstract