LightPRA: A Lightweight Temporal Convolutional Network for Automatic Physical Rehabilitation Exercise Assessment.

Research evidence shows that physical rehabilitation exercises prescribed by medical experts can assist in restoring physical function, improving life quality, and promoting independence for physically disabled individuals. In response to the absence of immediate expert feedback on performed actions, developing a Human Action Evaluation (HAE) system emerges as a valuable automated solution, addressing the need for accurate assessment of exercises and guidance during physical rehabilitation. Previous HAE systems developed for the rehabilitation exercises have focused on developing models that utilize skeleton data as input to compute a quality score for each action performed by the patient. However, existing studies have focused on improving scoring performance while often overlooking computational efficiency. In this research, we propose LightPRA (Light Physical Rehabilitation Assessment) system, an innovative architectural solution based on a Temporal Convolutional Network (TCN), which harnesses the capabilities of dilated causal Convolutional Neural Networks (CNNs). This approach efficiently captures complex temporal features and characteristics of the skeleton data with lower computational complexity, making it suitable for real-time feedback provided on resource-constrained devices such as Internet of Things (IoT) devices and Edge computing frameworks. Through empirical analysis performed on the University of Idaho-Physical Rehabilitation Movement Data (UI-PRMD) and KInematic assessment of MOvement for remote monitoring of physical REhabilitation (KIMORE) datasets, our proposed LightPRA model demonstrates superior performance over several state-of-the-art approaches such as Spatial-Temporal Graph Convolutional Network (STGCN) and Long Short-Term Memory (LSTM)-based models in scoring human activity performance, while exhibiting lower computational cost and complexity.

Development and Pilot Testing of a Programmatic System for Competency Assessment in US Anesthesiology Residency Training.

BACKGROUND: In 2018, a set of entrustable professional activities (EPAs) and procedural skills assessments were developed for anesthesiology training, but they did not assess all the Accreditation Council for Graduate Medical Education (ACGME) milestones. The aims of this study were to (1) remap the 2018 EPA and procedural skills assessments to the revised ACGME Anesthesiology Milestones 2.0, (2) develop new assessments that combined with the original assessments to create a system of assessment that addresses all level 1 to 4 milestones, and (3) provide evidence for the validity of the assessments. METHODS: Using a modified Delphi process, a panel of anesthesiology education experts remapped the original assessments developed in 2018 to the Anesthesiology Milestones 2.0 and developed new assessments to create a system that assessed all level 1 through 4 milestones. Following a 24-month pilot at 7 institutions, the number of EPA and procedural skill assessments and mean scores were computed at the end of the academic year. Milestone achievement and subcompetency data for assessments from a single institution were compared to scores assigned by the institution's clinical competency committee (CCC). RESULTS: New assessment development, 2 months of testing and feedback, and revisions resulted in 5 new EPAs, 11 nontechnical skills assessments (NTSAs), and 6 objective structured clinical examinations (OSCEs). Combined with the original 20 EPAs and procedural skills assessments, the new system of assessment addresses 99% of level 1 to 4 Anesthesiology Milestones 2.0. During the 24-month pilot, aggregate mean EPA and procedural skill scores significantly increased with year in training. System subcompetency scores correlated significantly with 15 of 23 (65.2%) corresponding CCC scores at a single institution, but 8 correlations (36.4%) were <30.0, illustrating poor correlation. CONCLUSIONS: A panel of experts developed a set of EPAs, procedural skill assessment, NTSAs, and OSCEs to form a programmatic system of assessment for anesthesiology residency training in the United States. The method used to develop and pilot test the assessments, the progression of assessment scores with time in training, and the correlation of assessment scores with CCC scoring of milestone achievement provide evidence for the validity of the assessments.

Technology-based methods for the assessment of fine and gross motor skill in children: A systematic overview of available solutions and future steps for effective in-field use.

The present review aims at providing researchers and practitioners with a holistic overview of technology-based methods for the assessment of fine and gross motor skill in children. We conducted a search of electronic databases using Web of Science, PubMed and Google Scholar, including studies published up to March 2020, that assessed fine and/or gross motor skills, and utilized technological assessment of varying study design. A total of 739 papers were initially retrieved, and after title/abstract screening, removal of duplicates, and full-text screening, 47 were included. Results suggest that motor skills can be quantitatively estimated using objective methods based on a wearable- and/or laboratory-based technology, for typically developing (TD) and non-TD children. Fine motor skill assessment solutions were; force transducers, instrumented tablets and pens, surface electromyography, and optoelectronic systems. Gross motor skill assessment solutions were; inertial measurements units, optoelectronic systems, baropodometric mats, and force platforms. This review provides a guide in identifying and evaluating the plethora of available technological solutions to motor skill assessment. Although promising, there is still a need for large-scale studies to validate these approaches in terms of accuracy, repeatability, and usability, where interdisciplinary collaborations between researchers and practitioners and transparent reporting practices should be advocated.

Predicting children's energy expenditure during physical activity using deep learning and wearable sensor data.

This study examined a series of machine learning models, evaluating their effectiveness in assessing children's energy expenditure, in terms of the metabolic equivalents (MET) of physical activity (PA), from triaxial accelerometery. The study also determined the impact of the sensor placement (waist, ankle or wrist) on the machine learning model's predictive performance. Twenty-eight healthy Caucasian children aged 8-11years (13 girls, 15 boys) undertook a series of activities reflective of different levels of PA (lying supine, seated and playing with Lego, slow walking, medium walking, and a medium paced run, instep passing a football, overarm throwing and catching and stationary cycling). Energy expenditure and physical activity were assessed during all activities using accelerometers (GENEActiv monitor) worn on four locations (i.e. non-dominant wrist, dominant wrist, dominant waist, dominant ankle) and breath-by-breath calorimetry data. MET values ranged from 1.2 ± 0.2 for seated playing with Lego to 4.1 ± 0.8 for running at 6.5 kmph-1. Machine learning models were used to determine the MET values from the accelerometer data and to determine which placement location performed more effectively in predicting the PA data. The study identified that novel machine learning models can be used to accurately predict METs, with 90% accuracy. The models showed a preference towards the dominant wrist or ankle as the movement in those positions were more consistent during PA. It was evident that machine learning models using these locations can be effectively used to accurately predict METs for PA in children.

The Effect of Acute Caffeine Ingestion on Cognitive Dual Task Performance during Assessment of Static and Dynamic Balance in Older Adults.

The present work aimed to evaluate the effect of 3 mg·kg-1 caffeine consumption on the standing and dynamic balance performance of older adults and sought to establish if caffeine ingestion can modulate the influence of a cognitive dual task on balance performance. Twelve apparently healthy participants (8 females) aged >65 years (72 ± 3.7 years) completed the study. Bipedal postural sway, four square step test, timed up and go, Y-balance (anterior reach only) and force-time characteristics of sit-to-stand performance were used to assess standing and dynamic balance. Attention and working memory were assessed using a serial 3s and 7s subtraction task during seated rest and completion of the bipedal standing assessment and Y-balance test. This battery of assessments was completed on two separate occasions, once following the consumption of a non-ergogenic placebo and again following the consumption of 3 mg·kg-1 caffeine. The administration of treatments was randomised, counterbalanced and double-blind. Caffeine reduced performance in the bipedal standing balance assessments, evidenced by an increase in COPML, COPPath, COPVelocity. Performance during the dynamic balance tests was unaffected, other than rate of force development during the sit-to-stand, which was improved following caffeine ingestion. The introduction of a cognitive dual task had either limited effects, or improved facets of bipedal standing balance, whilst performance during the dynamic balance task was significantly reduced. In both balance assessments, there was evidence for a reduction in the performance of the cognitive task when both the balance and cognitive tests were performed simultaneously, with this effect not modulated by caffeine consumption. These findings refute the idea that caffeine ingestion may have positive effects on balance performance. However, despite a caffeine-induced reduction in bipedal standing balance, it is unlikely that caffeine ingestion would exacerbate fall risk given the limited effects in the dynamic balance tests. Future work should establish if these effects are generalisable to older frail participants and if caffeine can modulate the detrimental effects of an acute exercise bout on balance performance.

Cross-validation of Actigraph derived accelerometer cut-points for assessment of sedentary behaviour and physical activity in children aged 8-11 years.

AIM: To cross-validate previously calibrated Actigraph cut-points in children. METHODS: Twenty-eight children (50% boys) aged between 8 and 11 years of age (9.4 ± 1.4 years) performed a series of 5 minute bouts of activity reflective of different levels of PA from sedentary behaviour (SB) to moderate to vigorous physical activity (MVPA); V˙ O2 was assessed using breath-by-breath indirect calorimetry, and activity was assessed using Actigraph accelerometers worn on the hip and non-dominant wrist. The V˙ O2 values were then converted into age-specific METs (measured METs) and coded as SB, light PA and MVPA. Accelerometer data were analysed using previously calibrated cut-points at different epochs, that is 5, 15, 30 and 60 seconds. RESULTS: Receiver operating characteristic (ROC) curve analysis indicated that there was excellent discrimination of SB using the Evenson et al (15 seconds), Romanzini (15 seconds), Treuth et al (30 seconds), Freedson et al (60 seconds), Treuth et al (60 seconds) and Troiano et al (60 seconds) cut-points. ROC analysis indicated poor discrimination for LPA irrespective of the cut-points used. Good discrimination of MVPA was evident for all existing cut-points using a 60-second epoch. CONCLUSION: There is considerable variation in the performance of existing cut-points for assessment of SB, LPA and MPA in children.

Perioperative Surgical Home, Fixing a Fragmented Process to Improve Quality of Care.

The practice of Perioperative Medicine is in need of greater coordination and organization. The traditional model of perioperative patient care, scheduling surgical care based primarily on surgeon/patient availability, along with the operative need, with little thought for coordination and planning to ensure that patients can safely undergo surgery and expect the best possible outcome, is in need of a paradigm change. Return to the highest level of functionality should be the patient centered approach.

Calibration of GENEActiv accelerometer wrist cut-points for the assessment of physical activity intensity of preschool aged children.

This study sought to validate cut-points for use of wrist-worn GENEActiv accelerometer data, to analyse preschool children's (4 to 5 year olds) physical activity (PA) levels via calibration with oxygen consumption values (VO2). This was a laboratory-based calibration study. Twenty-one preschool children, aged 4.7 ± 0.5 years old, completed six activities (ranging from lying supine to running) whilst wearing the GENEActiv accelerometers at two locations (left and right wrist), these being the participants' non-dominant and dominant wrist, and a Cortex face mask for gas analysis. VO2 data was used for the assessment of criterion validity. Location specific activity intensity cut-points were established via receiver operator characteristic curve (ROC) analysis. The GENEActiv accelerometers, irrespective of their location, accurately discriminated between all PA intensities (sedentary, light, and moderate and above), with the dominant wrist monitor providing a slightly more precise discrimination at light PA and the non-dominant at the sedentary behaviour and moderate and above intensity levels (area under the curve (AUC) for non-dominant = 0.749-0.993, compared to AUC dominant = 0.760-0.988). CONCLUSION: This study establishes wrist-worn physical activity cut-points for the GENEActiv accelerometer in preschoolers. What is Known: • GENEActiv accelerometers have been validated as a PA measurement tool in adolescents and adults. • No study to date has validated the GENEActiv accelerometers in preschoolers. What is New: • Cut-points were determined for the wrist-worn GENEActiv accelerometer in preschoolers. • These cut-points can be used in future research to help classify and increase preschoolers' compliance rates with PA.

Environmental and school influences on physical activity in South Asian children from low socio-economic backgrounds: A qualitative study.

South Asian (SA) children are less active but have enhanced metabolic risk factors. Physical activity (PA) is a modifiable risk factor for metabolic disease. Evidence suggests that environmental factors and socio-economic status influence PA behaviour. The purpose of this study was to understand PA environments, barriers and facilitators of PA in deprived environments for children from SA backgrounds. Focus groups were conducted with 5 groups of children aged 7-9 years (n = 33; male = 16, female = 17; SA = 17, White = 8 and Black = 8) from two schools in deprived wards of Coventry, England. Thematic analysis was used to identify key themes and subthemes across all transcripts. From the results, emergent themes included school and home environment, outdoor activity, equipment, weather, parental constraints and safety. Ethnic differences were apparent for sources of beliefs and knowledge and religious practice as constraints for PA. The findings suggest that school provides a good foundation for PA attitude, knowledge and behaviour, especially for SA children. To increase PA, multi-component interventions are needed, which focus on changing the home environment (i.e. junk food and media time), encouraging outdoors activity, changing perceptions of safety and weather conditions, which provide parental constraints for children. Interventions also need to be considerate to religious practices that might constrain time.

Assessment of the ergogenic effect of caffeine supplementation on mood, anticipation timing, and muscular strength in older adults.

The effect of caffeine to promote improvements in mood, cognition, and exercise performance has been well established in young and athletic adults. However, little is known about whether such nutritional ergogenic aids are effective in enhancing psychological well-being, physiological or cognitive performance in older adults. This study assesses the ergogenic effect of caffeine on mood, perceptual-motor coupling, and muscular strength in an older human population. Following a familiarization session, 12 apparently healthy volunteers (nine females and three males; 69 ± 6 years) completed two laboratory visits. "Pre ingestion" trials of mood state Brunel Mood State Inventory (BRUMS) and coincidence anticipation performance (Bassin anticipation timer) at slow (3 mph) and fast (8 mph) stimulus speeds were completed on both visits. Using a randomized, double-blind, cross-over design, participants consumed either caffeine (3 mg/kg body mass) or a placebo. Sixty minutes postingestion participants repeated the trials before completing a set of 10 consecutive repetitions of maximal knee extension using isokinetic dynamometry. Rating of perceived exertion (RPE) was assessed following the fifth and final repetition. Caffeine ingestion significantly improved mood state scores for vigor by 17% (P = 0.009) and reduced absolute error by 35% (P = 0.045) during coincidence anticipation assessment at 8 mph compared to placebo. There were no other significant effects. Caffeine ingestion failed to augment maximal voluntary contraction of the knee extensors and RPE did not prove to be significantly different to from placebo (P > 0.33 in each case). Acute caffeine ingestion may not be an effective ergogenic aid for improving muscular strength in older adults but could possibly be used as a nutrition supplement for enhancing mood and improving cognitive performance in daily living tasks where interceptive timing skills are required.

Ambulatory physical activity levels of white and South Asian children in Central England.

AIMS: To assess ambulatory physical activity in white and south Asian children from Central England and to examine variation in activity between weekdays and weekends. METHODS: 536 primary school children [255 boys and 281 girls, mean age (SD) = 9.6 (1.0) years] wore a sealed pedometer for 4 days (2 weekend and 2 weekdays). Repeated measures analysis of covariance was used to examine weekend versus weekday, gender, ethnic and socio-economic status differences in steps/day controlling for age, hours of daylight and body mass index (BMI). RESULTS: Children attained significantly higher mean steps/day during weekdays than weekends (p = 0.001) with age being more strongly associated with weekend than weekday steps/day (p = 0.014). The decline in steps/day from weekdays to weekends was greater in high compared to low socio-economic status children (p = 0.002). White children attained higher mean steps/day than south Asian children (p = 0.015). BMI was negatively associated with steps/day (p = 0.004). 39.2 and 29.9% of white and south Asian children met the BMI-referenced cut-offs for health. CONCLUSION: Physical activity was greater during weekdays compared to weekends, was associated with BMI, age and socio-economic status and white children were more active than south Asian children.

Brief report: understanding intention to be physically active and physical activity behaviour in adolescents from a low socio-economic status background: an application of the Theory of Planned Behaviour.

The aim of this brief report is to report on the utility of the Theory of Planned Behaviour (TPB) for predicting the physical activity intentions and behaviour of British adolescents from lower-than-average socio-economic backgrounds. A prospective questionnaire design was employed with 197, 13-14 year olds (76 males, 121 females). At time 1 participant completed standard measures of TPB variables. One week later (Time 2), participants completed the Physical Activity Questionnaire for Adolescents (PAQ-A) as a measure of physical activity behaviour. Hierarchical regression analyses showed that attitude and perceived behavioural control jointly accounted for 25% of the variance in intention (p = 0.0001). Perceived behavioural control emerged as the only significant predictor of physical activity behaviour and explained 3.7% of the variance (p = 0.001). Therefore, attitude and PBC successfully predicts intention towards physical activity and PBC predicts physical activity behaviour in British adolescents from lower-than-average socio-economic backgrounds.