Machine learning-based assessment tool for imbalance and vestibular dysfunction with virtual reality rehabilitation system

Yeh, Shih-Ching; Huang, Ming-Chun; Wang, Pa‐Chun; Fang, Te-Yung; Su, Mu-Chun; Tsai, Po‐Yi; Rizzo, Albert

doi:10.1016/j.cmpb.2014.04.014

Cited by 46 publications

(35 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yeh and al. made patients suffering from vestibular dysfunction and healthy patients follow a rehabilitation treatment with stereoscopic glasses [42]. He uses a Microsoft Kinect device to capture the subject's movement, and a Nintendo Wii Fit to get the statokinesigram of each patient.…”

Section: Vr For Balance Rehabilitationmentioning

confidence: 99%

Advantages and limitations of virtual reality for balance assessment and rehabilitation

Morel

Bideau

Lardy

et al. 2015

Neurophysiologie Clinique/Clinical Neurophysiology

View full text Add to dashboard Cite

Virtual reality (VR) is now commonly used in many domains because of its ability to provide a standardized, reproducible and controllable environment. In balance assessment, it can be used to control stimuli presented to patients and thus accurately evaluate their progression or compare them to different populations in standardized situations. In balance rehabilitation, VR allows the creation of new generation tools and at the same time the means to assess the efficiency of each parameter of these tools in order to optimize them. Moreover, with the development of low-cost devices, this rehabilitation can be continued at home, making access to these tools much easier, in addition to their entertaining and thus motivating properties. Nevertheless, and even more with low-cost systems, VR has limits that can alter the results of the studies that use it: the latency of the system (the delay cumulated on each step of the process from data acquisition on the patients to multimodal outputs); and distance perception, which tends to be underestimated in VR. After having described why VR is an essential tool for balance assessment and rehabilitation and illustrated this statement with a case study, this review discusses the previous works in the domain with regards to the technological limits of VR.

show abstract

Section: Vr For Balance Rehabilitationmentioning

confidence: 99%

Advantages and limitations of virtual reality for balance assessment and rehabilitation

Morel

Bideau

Lardy

et al. 2015

Neurophysiologie Clinique/Clinical Neurophysiology

View full text Add to dashboard Cite

show abstract

“…The gradient boosting classifier was the best algorithm in our datasets. This algorithm has recently been studied in varied medical fields (20,21,25,26), and has shown highly predictive performance. Other algorithms including SVC (24,(27)(28)(29), decision trees (30), genetics-based algorithms (31), and the multilayer perceptron classifier (32) did not show the best predictive performance in our datasets.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [43] machine learning methods were used for assessing the imbalance and vestibular dysfunction. Yeh et al [43] used SVM-based solution and within six different test setups, the highest accuracy was around 95.0%. Finally, Dastgheib et al [11] applied machine learning methods to the diagnosis of Ménière's disease.…”

Section: Related Workmentioning

confidence: 99%

Classification of patients and controls based on stabilogram signal data

Joutsijoki

Rasku

Pyykkö

et al. 2019

IDA

View full text Add to dashboard Cite

Inner ear balance problems are common worldwide and are often difficult to diagnose. In this study we examine the classification of patients with inner ear balance problems and controls (people not suffering from inner ear balance problems) based on data derived from the stabilogram signals and using machine learning algorithms. This paper is a continuation for our earlier paper where the same dataset was used and the focus was medically oriented. Our collected dataset consists of stabilogram (a force platform response) data from 30 patients suffering from Ménière's disease and 30 students called controls. We select a wide variety of machine learning algorithms from traditional baseline methods to state-of-the-art methods such as Least-Squares Support Vector Machines and Random Forests. We perform extensive and carefully made parameter value searches and we are able to achieve 88.3% accuracy using k-nearest neighbor classifier. Our results show that machine learning algorithms are well capable of separating patients and controls from each other.

show abstract

Machine learning-based assessment tool for imbalance and vestibular dysfunction with virtual reality rehabilitation system

Cited by 46 publications

References 20 publications

Advantages and limitations of virtual reality for balance assessment and rehabilitation

Advantages and limitations of virtual reality for balance assessment and rehabilitation

Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability

Classification of patients and controls based on stabilogram signal data

Contact Info

Product

Resources

About