OBJECTIVE: This study investigated whether the inclusion of video games in the upper limb amputee rehabilitation protocol could have a beneficial impact for muscle preparation, coordination, and patient motivation among individuals who have undergone transradial upper limb amputation.
METHODS: Ten participants, including five amputee participants and five able-bodied participants, were enrolled in 10 1-hour sessions within a 4-week rehabilitation program. In order to investigate the effects of the rehabilitation protocol used in this study, virtual reality box and block tests and electromyography (EMG) assessments were performed. Maximum voluntary contraction was measured before, immediately after, and 2 days after interacting with four different EMG-controlled video games. Participant motivation was assessed with the Intrinsic Motivation Inventory (IMI) questionnaire and user evaluation survey.
RESULTS: Survey analysis showed that muscle strength and coordination increased at the end of training for all the participants. The results of Pearson correlation analysis indicated that there was a significant positive association between the training period and the box and block test score (r8=0.95, P
EVIDENCE ACQUISITION: Searches were conducted with the Web of Science, Google Scholar, IEEE Xplore, and PubMed databases from inception up to September 2020. Articles that employed virtual reality in the rehabilitation of individual with upper limb loss were included in the research if it is written in English, the keyword exists in the title and abstract; it uses visual feedback in nonimmersive, semi-immersive, or fully immersive virtual environments. Data extraction was carried out by two independent researchers. The study was drafted using the Preferred Reporting Items for Systematic Reviews and Meta-analysis Protocols (PRISMA).
EVIDENCE SYNTHESIS: A total of 38 articles met the inclusion criteria. Most studies were published between 2010 and 2020. Thirty-nine percent of the studies (N.=15), originates from North America; 55% of the studies (N.=21), were publicly funded; 61% of the studies (N.=24), was without disclosure of conflict of interest; 82% of the studies (N.=31), were cited in other studies. All the studies were published in journals and conference proceedings. Sixty-six percent of the studies (N.=25) has come out with positive outcome. The design studies were mostly case reports, case series, and poorly designed cohort studies that made up 55% (N.=21) of all the studies cited here.
CONCLUSIONS: The research conducted on the use of virtual reality in individual with upper limb loss rehabilitation is of very low quality. The improvements to the research protocol are much needed. It is not necessary to develop new devices, but rather to assess existing devices with well-conducted randomized controlled trials.
METHODS: The system components and hand prototypes involve the anthropometry, CAD design and prototyping, biomechatronics engineering together with the prosthetics. The modeler construction of the system develop allows the ultrasonic sensors that are placed on the shoulder to generate the wrist movement of the prosthesis. The kinematics of wrist movement, which are the pronation/supination and flexion/extension were tested using the motion analysis and general motion of human hand were compared. The study also evaluated the require degree of detection for the input of the ultrasonic sensor to generate the wrist movements.
RESULTS: The values collected by the vicon motion analysis for biomechatronics prosthesis system were reliable to do the common tasks in daily life. The degree of the head needed to bend to give the full input wave was about 45°-55° of rotation or about 14 cm-16 cm. The biomechatronics wrist prosthesis gave higher degree of rotation to do the daily tasks but did not achieve the maximum degree of rotation.
CONCLUSION: The new development of using sensor and actuator in generating the wrist movements will be interesting for used list in medicine, robotics technology, rehabilitations, prosthetics and orthotics.
METHODS: Web of Science, Scopus, ScienceDirect, IEEE Xplore, and Google Scholar databases were searched for relevant studies published between January 2013 and July 2019. The quality of the included studies was objectively evaluated using the Downs and Black checklist.
RESULTS: A total of 129 articles on FES cycling were retained for analysis. A total of 51 articles related to Cybathlon were reviewed, and 14 articles were ultimately evaluated for the quality. In 2017, the year following the Cybathlon championship, Web of Science cited 23 published studies on the championship, which was almost 5-fold more than that in 2016 (n = 5). Training was most often reported as a topic of interest in these studies, which mostly (76.7%) highlighted the training parameters of interest to participating teams in their effort to maximize their FES cycling performance during the Cybathlon championship.
CONCLUSION: The present study indicates that the Cybathlon championship in 2016 contributed to the number of literature published in 2017 on FES cycling for individuals with SCI. This finding may contribute to the lessons that can be learned from participation in the Cybathlon and potentially provide additional insights into research in the field of race-based FES cycling.
METHODS: Natural language processing (NLP) techniques were harnessed to preprocess the occupational injury narratives obtained from the US Occupational Safety and Health Administration (OSHA) from January 2015 to June 2023. The methodology involved meticulous preprocessing of textual narratives to standardize text and eliminate noise, followed by the innovative integration of Term Frequency-Inverse Document Frequency (TF-IDF) and Global Vector (GloVe) word embeddings for effective text representation. The proposed predictive model adopts a novel Bidirectional Long Short-Term Memory (Bi-LSTM) architecture and is further refined through model optimization, including random search hyperparameters and in-depth feature importance analysis. The optimized Bi-LSTM model has been compared and validated against other machine learning classifiers which are naïve Bayes, support vector machine, random forest, decision trees, and K-nearest neighbor.
RESULTS: The proposed optimized Bi-LSTM models' superior predictability, boasted an accuracy of 0.95 for hospitalization and 0.98 for amputation cases with faster model processing times. Interestingly, the feature importance analysis revealed predictive keywords related to the causal factors of occupational injuries thereby providing valuable insights to enhance model interpretability.
CONCLUSION: Our proposed optimized Bi-LSTM model offers safety and health practitioners an effective tool to empower workplace safety proactive measures, thereby contributing to business productivity and sustainability. This study lays the foundation for further exploration of predictive analytics in the occupational safety and health domain.