No abstract

No abstract

Numerous postural sway metrics have been shown to be sensitive to balance impairment and fall risk in individuals with MS. Yet, there are no guidelines concerning the most appropriate postural sway metrics to monitor impairment. This investigation implemented a machine learning approach to assess the accuracy and feature importance of various postural sway metrics to differentiate individuals with MS from healthy controls as a function of physiological fall risk. 153 participants (50 controls and 103 individuals with MS) underwent a static posturography assessment and a physiological fall risk assessment. Participants were further classified into four subgroups based on fall risk: controls, low-risk MS (n = 34), moderate-risk MS (n = 27), high-risk MS (n = 42). Twenty common sway metrics were derived following standard procedures and subsequently used to train a machine learning algorithm (random forest – RF, with 10-fold cross validation) to predict individuals’ fall risk grouping. The sway-metric based RF classifier had high accuracy in discriminating controls from MS individuals (>86%). Sway sample entropy was identified as the strongest feature for classification of low-risk MS individuals from healthy controls. Whereas for all other comparisons, mediolateral sway amplitude was identified as the strongest predictor for fall risk groupings.

Background Falls are the leading cause of injury-related death in older adults. Due to various constraints, objective fall risk screening is seldom performed in clinical settings. Smartphones offer a high potential to provide fall risk screening for older adults in home settings. However, there is limited understanding of whether smartphone technology for falls screening is usable by older adults who present age-related changes in perceptual, cognitive, and motor capabilities. Objective The aims of this study were to develop a fall risk mobile health (mHealth) app and to determine the usability of the fall risk app in healthy, older adults. Methods A fall risk app was developed that consists of a health history questionnaire and 5 progressively challenging mobility tasks to measure individual fall risk. An iterative design-evaluation process of semistructured interviews was performed to determine the usability of the app on a smartphone and tablet. Participants also completed a Systematic Usability Scale (SUS). In the first round of interviews, 6 older adults participated, and in the second round, 5 older adults participated. Interviews were videotaped and transcribed, and the data were coded to create themes. Average SUS scores were calculated for the smartphone and tablet. Results There were 2 themes identified from the first round of interviews, related to perceived ease of use and perceived usefulness. While instructions for the balance tasks were difficult to understand, participants found it beneficial to learn about their risk for falls, found the app easy to follow, and reported confidence in using the app on their own. Modifications were made to the app, and following the second round of interviews, participants reported high ease of use and usefulness in learning about their risk of falling. Few differences were reported between using a smartphone or tablet. Average SUS scores ranged from 79 to 84. Conclusions Our fall risk app was found to be highly usable by older adults as reported from interviews and high scores on the SUS. When designing a mHealth app for older adults, developers should include clear and simple instructions and preventative strategies to improve health. Furthermore, if the design accommodates for age-related sensory changes, smartphones can be as effective as tablets. A mobile app to assess fall risk has the potential to be used in home settings by older adults.

People with multiple sclerosis (pwMS) often suffer from gait impairments. These changes in gait have been wellstudied in laboratory and clinical settings. A thorough investigation of gait alterations during community ambulation and their contributing factors, however, is lacking. The aim of the present study was to evaluate community ambulation and physical activity in pwMS and healthy controls and to compare in-lab gait to community ambulation. To this end, 104 subjects were studied:44 pwMS and 60 healthy controls (whose age was similar to the controls). The subjects wore a tri-axial, lower-back accelerometer during usual-walking and dual-task walking in the lab and during community ambulation (1 week) to evaluate the amount, type, and quality of activity. The results showed that during community ambulation, pwMS took fewer steps and walked more slowly, with greater asymmetry, and larger stride-to-stride variability, compared to the healthy controls (p<0.001). Gait speed during most of community ambulation was significantly lower than the in-lab usual-walking value and similar to the in-lab dual-tasking value. Significant group (pwMS /controls) by walking condition (in-lab/community ambulation) interactions were observed (e.g., gait speed).Greater disability was associated with fewer steps and reduced gait speed during community ambulation. In contrast, physical fatigue was correlated with sedentary activity but was not related to any of the measures of community ambulation gait quality including gait speed. This disparity suggests that more than one mechanism contributes to community ambulation and physical activity in pwMS. Together, these findings demonstrate that during community ambulation, pwMS have marked gait alterations in multiple gait features, reminiscent of dual-task walking measured in the laboratory. Disease-related factors associated with these changes might be targets of rehabilitation.