In recent years, myoelectric control systems have emerged for upper limb wearable robotic exoskeletons to provide movement assistance and/or to restore motor functions in people with motor disabilities and to augment human performance in able-bodied individuals. In myoelectric control, electromyographic (EMG) signals from muscles are utilized to implement control strategies in exoskeletons and exosuits, improving adaptability and human–robot interactions during various motion tasks. This paper reviews the state-of-the-art myoelectric control systems designed for upper-limb wearable robotic exoskeletons and exosuits, and highlights the key focus areas for future research directions. Here, different modalities of existing myoelectric control systems were described in detail, and their advantages and disadvantages were summarized. Furthermore, key design aspects (i.e., supported degrees of freedom, portability, and intended application scenario) and the type of experiments conducted to validate the efficacy of the proposed myoelectric controllers were also discussed. Finally, the challenges and limitations of current myoelectric control systems were analyzed, and future research directions were suggested.

Early and accurate detection of scalp hair loss is imperative to provide timely and effective treatment plans to halt further progression and save medical costs. Many techniques have been developed leveraging deep learning to automate the hair loss detection process. However, the accuracy and robustness of assessing hair loss severity still remain a challenge and barrier for transitioning such a technique into practice. The presented work proposes an efficient and accurate algorithm to classify hair follicles and estimate hair loss severity, which was implemented and validated using a multitask deep learning method via a Mask R-CNN framework. A microscopic image of the scalp was resized, augmented, then processed through pre-trained ResNet models for feature extraction. The key features considered in this study concerning hair loss severity include the number of hair follicles, the thickness of the hair, and the number of hairs in each hair follicle. Based on these key features, labeling of hair follicles (healthy, normal, and severe) were performed on the images collected from 10 men in varying stages of hair loss. More specifically, Mask R-CNN was applied for instance segmentation of the hair follicle region and to classify the hair follicle state into three categories, following the labeling convention (healthy, normal and severe). Based on the state of each hair follicle captured from a single image, an estimation of hair loss severity was determined for that particular region of the scalp, namely local hair loss severity index (P), and by combining P of multiple images taken and processed from different parts of the scalp, we constructed the hair loss severity estimation ($P_{avg}$) and visualized in a heatmap to illustrate the overall hair loss type and condition. The proposed hair follicle classification and hair loss severity estimation using Mask R-CNN demonstrated a more efficient and accurate algorithm compared to other methods previously used, enhancing the classification accuracy by 4 to 15%. This performance supports its potential for use in clinical settings to enhance the accuracy and efficiency of current hair loss diagnosis and prognosis techniques.

Accurate and robust human immune system assessment through white blood cell evaluation require computer-aided tools with pathologist-level accuracy. This work presents a multi-attention leukocytes subtype classification method by leveraging fine-grained and spatial locality attributes of white blood cell. The proposed framework comprises three main components: texture-aware/attention map generation blocks, attention regularization, and attention-based data augmentation. The developed framework is applicable to general CNN-based architectures and enhances decision making by paying specific attention to the discriminative regions of a white blood cell. The performance of the proposed method/model was evaluated through an extensive set of experiments and validation. The obtained results demonstrate the superior performance of the model achieving 99.69 % accuracy compared to other state-of-the-art approaches. The proposed model is a good alternative and complementary to existing computer diagnosis tools to assist pathologists in evaluating white blood cells from blood smear images.

The individual effects of physical activity (PA) and sedentary behavior (SB) on health are well-recognized. However, little is known about the extent to which different combinations of these behaviors are associated with body composition and fall risk in older adults. This cross-sectional study examined the associations of mutually exclusive categories of PA and SB with body composition and fall risk in older women. Accelerometer-measured PA, body composition and fall risk (static and dynamic balance) parameters were assessed among 94 community-dwelling older women. The participants were categorized into four groups: active-low sedentary, active-high sedentary, inactive-low sedentary and inactive-high sedentary (active: ≥150 min/week moderate-to-vigorous PA (MVPA); low sedentary: lowest tertile of SB and light PA ratio). Compared to the inactive-high sedentary group, more favorable body composition and dynamic balance results were found in the active-low sedentary (body fat mass index (BFMI): β = −4.37, p = 0.002; skeletal muscle mass index (SMI): β = 1.23, p = 0.017; appendicular lean mass index (ALMI): β = 1.89, p = 0.003; appendicular fat mass index (AFMI): β = −2.19, p = 0.003; sit-to-stand: β = 4.52, p = 0.014) and inactive-low sedentary (BFMI: β = −3.14, p = 0.007; SMI: β = 1.05, p = 0.014; AFMI: β = −1.74, p = 0.005, sit-to-stand: β = 3.28, p = 0.034) groups. Our results suggest that PA programs focusing on concurrently achieving sufficient MVPA and reduced SB might promote a healthy body composition and reduced fall risk among older adults.

Background: Physical activity (PA) is vital for attenuating the aging-related physiological and functional declines in women aged 60 years or above. However, little is known about the objectively assessed PA behavior in older women during the COVID-19 pandemic and its association with sociodemographics, health and physical function, and COVID-19 related factors. Objective: This study aims to examine the objectively measured PA levels and associated factors among older US women who were living under the physical distancing guidelines during the second year of the pandemic. Methods: In this cross-sectional study, we collected free-living PA data from 94 community-dwelling older women aged between 60 and 96 years (mean age 75.1 years, SD 7.3) using wrist-worn ActiGraph GT9X accelerometers between February and August 2021. We examined whether their daily duration spent in sedentary behavior (SB), light-intensity physical activity (LPA), and moderate-to-vigorous-intensity physical activity (MVPA) varied by sociodemographic characteristics, health and physical function, and COVID-19 related factors. Results: On average, participants accumulated 12.4 (SD 1.9) hours/day in SB, 218.6 (SD 64.3) minutes/day in LPA, and 42.4 (SD 31.0) minutes/day in MVPA, exhibiting overall reduced PA levels than previously published pre–COVID-19 norms of older US women. Among participants aged ≥80 years, sedentary time was 7.5% (P=.003) higher and the time spent in LPA and MVPA was, respectively, 13.3% (P=.03) and 44.9% (P<.001) lower than those aged 60-79 years. More MVPA participation and a less sedentary lifestyle were observed in those who had a higher self-rated health score (MVPA: P=.001, SB: P=.04) and lower fear of falling (FOF; MVPA: P=.003, SB: P=.04). Poorer performance in the 30-second sit-to-stand (STS) test was independently associated with more SB (P=.01) and less LPA (P=.04) and MVPA (P=.001) time among participants. In addition, sedentary time was 5.0% higher (P=.03) in frail and prefrail participants than their healthy counterparts. Conclusions: During the pandemic, older women spent the majority of their waking time being sedentary, while LPA accounted for a larger portion of their daily PA. Therefore, replacing SB with LPA (rather than MVPA) might provide a more feasible PA target for older women, particularly those aged ≥80 years or who have reduced physical function. In addition, targeted interventions might be beneficial in promoting an active lifestyle for those who live alone, are prefrail or frail, and have a high FOF in older age. International Registered Report Identifier (IRRID): RR2-10.2196/27381

Purpose: The US Centers for Disease Control and Prevention (CDC) has implemented the Stopping Elderly Accidents, Deaths, and Injuries (STEADI) initiative. This initiative provides an algorithm for fall risk screening. However, the algorithm has the potential to overcategorize individuals as high risk for falling upon initial screening, which may burden clinicians with the task of recategorizing individuals after follow-up testing. Therefore, this study aimed to compare the accuracy, sensitivity, and specificity of fall risk appraisal between the STEADI, Short Fall-Efficacy Scale International (FES-I), and portable balance system (BTrackS) assessments in community-dwelling older adults. Patients and Methods: This cross-sectional analysis included 122 community-dwelling older adults, comprising 94 women and 28 men. Center-of-pressure postural sway was assessed using the BTrackS, fear of falling was assessed using the Short FES-I questionnaire, and all participants completed the STEADI checklist. Each assessment categorized participants as either high or low fall risk and fall risk appraisal was compared between groups using McNemar tests. Results: The STEADI checklist (high risk: n = 62; low risk: n = 60) significantly differed in fall risk appraisal compared to the BTrackS (high risk: n = 44; low risk: n = 78; p = 0.014) and the Short FES-I (high risk: n = 42; low risk: n = 80; p = 0.002). Compared to the BTrackS, the STEADI checklist had a specificity of 62.8%, sensitivity of 70.5%, and accuracy of 65.6%. Compared to the Short FES-I, the STEADI checklist had a specificity of 67.5%, sensitivity of 81.0%, and accuracy of 72.1%. Conclusion: The STEADI checklist appears to overcategorize individuals as high fall risk more frequently than direct assessments of postural sway and fear of falling. Further research is needed to examine potential improvements in accuracy when combining the STEADI checklist with direct assessments of postural sway and/or fear of falling. Plain Language Summary: Fall risk assessments are crucial for preventative care in older adults. However, the demands of clinical practice require an accurate and time-efficient method. The U.S Centers for Disease Control and Prevention (CDC) has implemented a fall risk checklist through the Stopping Elderly Accidents, Deaths, and Injuries (STEADI) initiative. However, the STEADI checklist might cost clinicians more time than expected, as some patients initially classified as high risk for falling may not actually be at high risk. This leads to unnecessary follow-up assessments. In this study, we compared the STEADI checklist to direct measures of postural sway (balance) using the BTrackS system and fear of falling using the Short FES-I survey to determine how they differed in classifying community-dwelling older adults as high versus low fall risk. Our results show that the STEADI checklist classifies older adults as high risk more frequently than the BTrackS and Short FES-I. Considering that the follow-up assessments for a high-risk classification by the STEADI checklist include a balance test, we suggest that combining a balance test such as the BTrackS with a questionnaire or checklist may yield better screening outcomes and accurately identify high-risk individuals in a timely manner. Further research is needed to determine the effectiveness of this combination and to establish a true gold standard method for fall risk appraisal.