Design and test of an automated version of the modified Jebsen test of hand function using Microsoft Kinect

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks

BACKGROUND

In-home rehabilitation systems are a promising, potential alternative to conventional therapy for stroke survivors. Unfortunately, physiological differences between participants and sensor displacement in wearable sensors pose a significant challenge to classifier performance, particularly for people with stroke who may encounter difficulties repeatedly performing trials. This makes it challenging to create reliable in-home rehabilitation systems that can accurately classify gestures.

METHODS

Twenty individuals who suffered a stroke performed seven different gestures (mass flexion, mass extension, wrist volar flexion, wrist dorsiflexion, forearm pronation, forearm supination, and rest) related to activities of daily living. They performed these gestures while wearing EMG sensors on the forearm, as well as FMG sensors and an IMU on the wrist. We developed a model based on prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size to improve model accuracy. Our model was evaluated against conventional transfer learning with neural networks, as well as subject-dependent and subject-independent classifiers: neural networks, LGBM, LDA, and SVM.

RESULTS

Our proposed model achieved 82.2% hand-gesture classification accuracy, which was better (P<0.05) than one-shot transfer learning with neural networks (63.17%), neural networks (59.72%), LGBM (65.09%), LDA (63.35%), and SVM (54.5%). In addition, our model performed similarly to subject-dependent classifiers, slightly lower than SVM (83.84%) but higher than neural networks (81.62%), LGBM (80.79%), and LDA (74.89%). Using K-Best features improved the accuracy in 3 of the 6 classifiers used for evaluation, while not affecting the accuracy in the other classifiers. Increasing the window size improved the accuracy of all the classifiers by an average of 4.28%.

CONCLUSION

Our proposed model showed significant improvements in hand-gesture recognition accuracy in individuals who have had a stroke as compared with conventional transfer learning, neural networks and traditional machine learning approaches. In addition, K-Best feature selection and increased window size can further improve the accuracy. This approach could help to alleviate the impact of physiological differences and create a subject-independent model for stroke survivors that improves the classification accuracy of wearable sensors.

TRIAL REGISTRATION NUMBER

The study was registered in Chinese Clinical Trial Registry with registration number CHiCTR1800017568 in 2018/08/04.

Backward logistic regression analysis of the determinants of the hand function among patients with leprosy: A cross-sectional study

Introduction

The hands are the most common site of disability in leprosy. Hand dysfunction could result in difficulty performing activities of daily living. Therefore, hand function should be regularly assessed to ensure that any decrease in hand function could be diagnosed earlier.

Methods

This study included 110 patients with leprosy from Likupang and Lembata, Indonesia. Hand function was assessed using the modified Jebsen test to measure hand function respective of the dominance. The grip and pinch strength were used as objective measures of clinical arm function. The World Health Organization (WHO) hand disability grade were used to determine the degree of impairment. Other factors such as age, sex and the type of leprosy were also considered. All factors were analysed using backward logistic regression.

Results

Among the 110 participants, a decrease in the dominant (48.2%) and non-dominant (50.9%) hand functions were found. Pinch strength (OR: 3.39; 95% CI: 1.13-10.19) and age (OR: 4.91; 95% CI: 1.72-14.03) were significantly associated with hand function irrespective of the dominance. Conversely, the WHO hand disability grade (OR: 2.97; 95% CI: 1.10-8.04) and type of leprosy (OR: 0.34; 95% CI: 0.12-0.97) were significantly associated with only function of the dominant hand.

Conclusion

There is a significant association of age and pinch strength with hand function regardless of the hand dominance. In contrast, the WHO hand disability grade and type of leprosy are significantly associated with the function of the dominant hand only.

Digital Devices for Assessing Motor Functions in Mobility-Impaired and Healthy Populations: Systematic Literature Review

Background

With the advent of smart sensing technology, mobile and wearable devices can provide continuous and objective monitoring and assessment of motor function outcomes.

Objective

We aimed to describe the existing scientific literature on wearable and mobile technologies that are being used or tested for assessing motor functions in mobility-impaired and healthy adults and to evaluate the degree to which these devices provide clinically valid measures of motor function in these populations.

Methods

A systematic literature review was conducted by searching Embase, MEDLINE, CENTRAL (January 1, 2015, to June 24, 2020), the United States and European Union clinical trial registries, and the United States Food and Drug Administration website using predefined study selection criteria. Study selection, data extraction, and quality assessment were performed by 2 independent reviewers.

Results

A total of 91 publications representing 87 unique studies were included. The most represented clinical conditions were Parkinson disease (n=51 studies), followed by stroke (n=5), Huntington disease (n=5), and multiple sclerosis (n=2). A total of 42 motion-detecting devices were identified, and the majority (n=27, 64%) were created for the purpose of health care–related data collection, although approximately 25% were personal electronic devices (eg, smartphones and watches) and 11% were entertainment consoles (eg, Microsoft Kinect or Xbox and Nintendo Wii). The primary motion outcomes were related to gait (n=30), gross motor movements (n=25), and fine motor movements (n=23). As a group, sensor-derived motion data showed a mean sensitivity of 0.83 (SD 7.27), a mean specificity of 0.84 (SD 15.40), a mean accuracy of 0.90 (SD 5.87) in discriminating between diseased individuals and healthy controls, and a mean Pearson r validity coefficient of 0.52 (SD 0.22) relative to clinical measures. We did not find significant differences in the degree of validity between in-laboratory and at-home sensor-based assessments nor between device class (ie, health care–related device, personal electronic devices, and entertainment consoles).

Conclusions

Sensor-derived motion data can be leveraged to classify and quantify disease status for a variety of neurological conditions. However, most of the recent research on digital clinical measures is derived from proof-of-concept studies with considerable variation in methodological approaches, and much of the reviewed literature has focused on clinical validation, with less than one-quarter of the studies performing analytical validation. Overall, future research is crucially needed to further consolidate that sensor-derived motion data may lead to the development of robust and transformative digital measurements intended to predict, diagnose, and quantify neurological disease state and its longitudinal change.

Depth Sensor-Based Assessment of Reachable Work Space for Visualizing and Quantifying Paretic Upper Extremity Motor Function in People With Stroke

BACKGROUND

Quantitative evaluation of upper extremity (UE) motor function is important in people with hemiparetic stroke. A depth sensor-based assessment of reachable work space (RWS) was applied to visualize and quantify paretic UE motor function.

OBJECTIVE

The objectives of this study were to examine the characteristics of RWS and to assess its validity, reliability, measurement error, and responsiveness in people with hemiparetic stroke.

DESIGN

This was a descriptive, repeated-measures, observational study.

METHODS

Fifty-eight people with stroke participated. RWS was assessed on both paretic and nonparetic UEs, and the RWS ratio was determined by dividing the RWS of the paretic UE by that of the nonparetic UE. The concurrent validity of the RWS was determined by examining the relationship with the Fugl-Meyer Assessment UE motor score. Test-retest reproducibility was examined in 40 participants. Responsiveness was determined by examining the RWS results before and after 3 weeks of intensive training of the paretic UE in 32 participants.

RESULTS

The lower area of RWS bordering shoulder was significantly larger than the upper area, and the medial-lower area of RWS bordering shoulder was significantly larger than the lateral-lower area. The RWS ratio was highly correlated with the Fugl-Meyer Assessment UE motor score (r = 0.81). The RWS ratio showed good intrarater relative reliability (intraclass correlation coefficient = 0.94) and no fixed or proportional bias. The minimal detectable change of the RWS ratio was 16.6. The responsiveness of the RWS ratio was large (standardized response mean = 0.83).

LIMITATIONS

Interexaminer reliability was not assessed.

CONCLUSIONS

The RWS assessment showed sufficient validity, reliability, and responsiveness in people with hemiparetic stroke. A depth sensor-based RWS evaluation is useful for visualizing and quantifying paretic UE motor function in the clinical setting.

Validity and Reliability of the Kinect for Assessment of Standardized Transitional Movements and Balance: Systematic Review and Translation into Practice

The validity and reliability of using the Kinect camera to measure standardized assessment of transitional movement, stepping, and balance was systematically reviewed and critically appraised for quality of the methods and results. The study made recommendations of specific tests for practice based on inclusion of both validity and reliability testing as well as quality of results. Authors' willingness to share their software was reported. Translation into practice is limited by lack of redundancy among studies and access to the software to implement the tests.