Search

Background: This study introduced a novel approach for predicting occupational injury severity by leveraging deep learning-based text classification techniques to analyze unstructured narratives. Unlike conventional methods that rely on structured data, our approach recognizes the richness of information within injury narrative descriptions with the aim of extracting valuable insights for improved occupational injury severity assessment. 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. [ABSTRACT FROM AUTHOR]

Body-powered prostheses are known for their advantages of cost, reliability, training period, maintenance, and proprioceptive feedback. This study primarily aims to analyze the work related to the improvement of upper limb body-powered prostheses prior to 2016. A systematic review conducted via the search of the Web of Science electronic database, Google Scholar, and Google Patents identified 155 papers from 1921 to 2016. Sackett's initial rules of evidence were used to determine the levels of evidence, and only papers categorized in the design and development category and patents were analyzed. A total of 40 papers in the sixth level of "Design and Development" of an upper limb body-powered prosthesis were found. Approximately 81% were categorized under mechanical alteration. Most papers were patent-type documents (48%), with the Journal of Rehabilitation Research and Development publishing most of the articles related to the design and development of body-powered prostheses. Papers in the scope of the study were published once every 3 years in almost a century, proving that only a few studies were conducted to improve body-powered arms compared with myoelectric technology. Further research should be carried out mainly in areas that have received less attention. [ABSTRACT FROM AUTHOR]

Background Prosthesis suspension systems can alter the distribution of pressure within the prosthetic socket. This study evaluates a new suspension system for lower limb prostheses, and aims to compare the interface pressure and amputees' satisfaction with the new system compared with a common prosthetic suspension system (pin/lock). Methods Ten transtibial amputees walked at a self-selected speed on a level ground with two different suspension systems, namely the pin/lock and HOLO system. The interface pressure was measured using the F-socket transducers at the proximal, middle and distal sites of residual limb. Furthermore, subjective feedback was logged to compare two systems. Results The pressure was significantly higher at the proximal and distal areas with the pin/lock suspension system during the swing phase of gait (P < 0.05). Subjective feedback also showed traction at the stump with the pin/lock system. There were no significant differences in the pressure applied to the mid-anterior and mid posterior stump for both suspension systems. However, the lateral and medial sides exhibited higher pressure with the new system during stance phase. Conclusions The intention of this study was to deepen understanding on the effect of suspension system on the load distribution over the residual limb. The new coupling system was proved compatible with the pin/lock system in terms of suspending the leg and amputee's satisfaction. On the other hand, the HOLO system could distribute the pressure more uniformly over the residual limb. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusions Functional electrical stimulation (FES) cycling has been reported to enhance muscle strength and improve muscle fatigue resistance after spinal cord injury (SCI). Despite its proposed benefits, the quantification of muscle fatigue during FES cycling remains poorly documented. This study sought to quantify the relationship between the vibrational performance of electrically‐evoked muscles measured through mechanomyography (MMG) and its oxidative metabolism through near‐infrared spectroscopy (NIRS) characteristics during FES cycling in fatiguing paralyzed muscles in individuals with SCI.Six individuals with SCI participated in the study. They performed 30 min of FES cycling with MMG and NIRS sensors on their quadriceps throughout the cycling, and the signals were analyzed.A moderate negative correlation was found between MMG root mean square (RMS) and oxyhaemoglobin (O2Hb) [r = −0.38, p = 0.003], and between MMG RMS and total hemoglobin (tHb) saturation [r = −0.31, p = 0.017]. Statistically significant differences in MMG RMS, O2Hb, and tHb saturation occurred during pre‐ and post‐fatigue of FES cycling (p < 0.05).MMG RMS was negatively associated with O2Hb and muscle oxygen derived from NIRS. MMG and NIRS sensors showed good inter‐correlations, suggesting a promising use of MMG for characterizing metabolic fatigue at the muscle oxygenation level during FES cycling in individuals with SCI. [ABSTRACT FROM AUTHOR]

Background: The design and performance of a new development prosthesis system known as biomechatronics wrist prosthesis is presented in this paper. The prosthesis system was implemented by replacing the Bowden tension cable of body powered prosthesis system using two ultrasonic sensors, two servo motors and microcontroller inside the prosthesis hand for transradial user.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. [ABSTRACT FROM AUTHOR]

Background: Understanding of kinematics force applied at the elbow is important in many fields, including biomechanics, biomedical engineering and rehabilitation. This paper provides a comparison of a mathematical model of elbow joint using three different types of prosthetics for transhumeral user, and characterizes the forces required to overcome the passive mechanical of the prosthetics at the residual limb.Methods: The study modeled the elbow as a universal joint with intersecting axes of x-axis and y-axis in a plain of upper arm and lower arm. The equations of force applied, torque, weight and length of different type of prosthetics and the anthropometry of prosthetics hand are discussed in this study. The study also compares the force, torque and pressure while using all three types of prosthetics with the normal hand.Results: The result was measured from the elbow kinematics of seven amputees, using three different types of prosthetics. The F-Scan sensor used in the study is to determine the pressure applied at the residual limb while wearing different type of prostheses.Conclusion: These technological advances in assessment the biomechanics of an elbow joint for three different type of prosthetics with the normal hand bring the new information for the amputees and prosthetist to choose the most suitable device to be worn daily. [ABSTRACT FROM AUTHOR]

Prosthetic alignment is a highly subjective process that is still based on clinical judgments. Thus, researchers have aimed their effort to quantify prosthetic alignment by providing an objective method that can assist and guide prosthetists in achieving transtibial (TT) prosthetic alignment. This systematic review aimed to examine the current literature on TT prosthetic alignment to scope the qualitative and quantitative methods designed to guide prosthetists throughout the TT prosthetic alignment process as well as evaluate the reported instruments and devices that are used to align TT prostheses and their clinical feasibility. A literature search, completed in June 2022, was performed using the following databases: Web of Science (Clarivate), SCOPUS (Elsevier), and Pub Med (Medline) with searching terms focusing on TT, prosthesis, prosthetist, prosthetic alignment, and questionnaires, resulting in 2790 studies being screened. Twenty-four studies have used quantitative methodologies, where sensor technologies were found to be the most frequently proposed technology combined with gait analysis tools and/or subjective assessments. A qualitative method that assists prosthetists throughout the alignment process was not found. In this systematic review, we presented diverse methods for guiding and assisting clinical decision-making regarding TT prosthetic alignment. However, most of these methods considered varied parameters, and there is a need for elaboration toward standardized methods, which would improve the prosthetic alignment clinical outcome., (Copyright © 2023 International Society for Prosthetics and Orthotics.)

Background: The advancement of biomedical research generates myriad healthcare-relevant data, including medical records and medical device maintenance information. The COVID-19 pandemic significantly affects the global mortality rate, creating an enormous demand for medical devices. As information technology has advanced, the concept of intelligent healthcare has steadily gained prominence. Smart healthcare utilises a new generation of information technologies, such as the Internet of Things (loT), big data, cloud computing, and artificial intelligence, to completely transform the traditional medical system. With the intention of presenting the concept of smart healthcare, a predictive model is proposed to predict medical device failure for intelligent management of healthcare services., Methods: Present healthcare device management can be improved by proposing a predictive machine learning model that prognosticates the tendency of medical device failures toward smart healthcare. The predictive model is developed based on 8,294 critical medical devices from 44 different types of equipment extracted from 15 healthcare facilities in Malaysia. The model classifies the device into three classes; (i) class 1, where the device is unlikely to fail within the first 3 years of purchase, (ii) class 2, where the device is likely to fail within 3 years from purchase date, and (iii) class 3 where the device is likely to fail more than 3 years after purchase. The goal is to establish a precise maintenance schedule and reduce maintenance and resource costs based on the time to the first failure event. A machine learning and deep learning technique were compared, and the best robust model for smart healthcare was proposed., Results: This study compares five algorithms in machine learning and three optimizers in deep learning techniques. The best optimized predictive model is based on ensemble classifier and SGDM optimizer, respectively. An ensemble classifier model produces 77.90%, 87.60%, and 75.39% for accuracy, specificity, and precision compared to 70.30%, 83.71%, and 67.15% for deep learning models. The ensemble classifier model improves to 79.50%, 88.36%, and 77.43% for accuracy, specificity, and precision after significant features are identified. The result concludes although machine learning has better accuracy than deep learning, more training time is required, which is 11.49 min instead of 1 min 5 s when deep learning is applied. The model accuracy shall be improved by introducing unstructured data from maintenance notes and is considered the author's future work because dealing with text data is time-consuming. The proposed model has proven to improve the devices' maintenance strategy with a Malaysian Ringgit (MYR) cost reduction of approximately MYR 326,330.88 per year. Therefore, the maintenance cost would drastically decrease if this smart predictive model is included in the healthcare management system., Competing Interests: The authors declare that they have no competing interests., (© 2023 Abd Rahman et al.)

Materials with low-strength and low-impedance properties, such as elastomers and polymeric foams are major contributors to prosthetic liner design. Polyethylene-Light (Pelite™) is a foam liner that is the most frequently used in prosthetics but it does not cater to all amputees' limb and skin conditions. The study aims to investigate the newly modified Foam Liner, a combination of two different types of foams (EVA + PU + EVA) as the newly modified Foam Liner in terms of compressive and tensile properties in comparison to Pelite™, polyurethane (PU) foam, and ethylene-vinyl acetate (EVA) foam. Universal testing machine (AGS-X, Shimadzu, Kyoto, Japan) has been used to measure the tensile and compressive stress. Pelite™ had the highest compressive stress at 566.63 kPa and tensile stress at 1145 kPa. Foam Liner fell between EVA and Pelite™ with 551.83 kPa at compression and 715.40 kPa at tension. PU foam had the lowest compressive stress at 2.80 kPa and tensile stress at 33.93 kPa. Foam Liner has intermediate compressive elasticity but has high tensile elasticity compared to EVA and Pelite™. Pelite™ remains the highest in compressive and tensile stiffness. Although it is good for amputees with bony prominence, constant pressure might result in skin breakdown or ulcer. Foam Liner would be the best for amputees with soft tissues on the residual limbs to accommodate movement., (© 2020 Walter de Gruyter GmbH, Berlin/Boston.)

Objectives: This study aims to assess the level of awareness of transtibial amputee patients on stump contractures and their compliance with efforts implemented to prevent the condition., Patients and Methods: This study included 50 unilateral transtibial amputees (26 males, 24 females; mean age 55.4±14.7 years; range, 18 to 78 years) who met the respondent criteria of the study. The respondents were randomly selected and were issued with a questionnaire., Results: The majority of the transtibial amputees were aware of stump contracture complications. It was found that they also preferred methods of prevention which required less effort, was cost-effective, and were also practical., Conclusion: More focus should be placed on contracture prevention methods which were most complied with by the patients. This is because the effectiveness of a prevention method is highly influenced by patients' compliance with the method. Patients with a higher risk of developing stump contractures should be also given more attention in post-amputation care., Competing Interests: Conflict of Interest: The authors declared no conflicts of interest with respect to the authorship and/or publication of this article.

There are a number of prosthetic terminal devices which offer functional restoration to individuals with upper limb deficiencies. Hosmer and Ottobock are major commercial hook providers for prosthetic terminal devices. The concern of this paper is to analyse the voluntary opening (VO) Ottobock model 10A18 and Hosmer model 99P hooks (one band) during opening operation and to find out favourable features in the design. Two tests were conducted to analyse the performance of both hooks. The first test used a simple bench tool to investigate cable excursion and hook opening angle and the second test used force sensor to find out the force supplied at a different hook opening angle. The study found that the average cable excursion for both hooks is approximately 30% less than the hook's opening span with the force at the hook's tip section being inversely proportional to the force at the lateral section. Ottobock 10A18 has a better control for grasping larger objects, while Hosmer 99P has the highest average force at the tip section but yet less efficient in generating adequate force for activities of daily living. Favourable features identified are low cable excursion per hook opening span and balance lateral to hook tip pinch force.