Rahul Soangra

Conventional clinical assessments of stroke rehabilitation are limited to supervised environments and fail to capture continuous real-world motor behavior. This proof-of-concept pilot study (case series, n = 3) evaluated the feasibility and longitudinal sensitivity of wearable IMU-derived digital biomarkers of three individuals with chronic stroke across Chapman University’s Stroke Boot Camp (SBC), a two-week intensive interdisciplinary rehabilitation program. A lower-back-mounted DynaPort McRoberts IMU provided continuous multi-day free-living monitoring across five sessions that spanned one week pre-intervention through to three months post-intervention. A validated Python-based pipeline implemented Mobilise-D gait sequence detection, wavelet-based heel strike and toe-off identification, and extraction of linear spatiotemporal parameters alongside a 24-feature nonlinear biomarker panel, which included sample entropy, multi-scale entropy variants, Lyapunov exponents, and recurrence quantification analysis metrics. A standardized clinical battery (FMA, BBS, FGA, 10 MWT, 6 MWT) was administered at each session. All three participants exhibited a 52–62% increase in Wolf’s Lyapunov exponent during SBC Week 2, which was most consistent across participants. Participant-specific entropy responses were heterogeneous, with SampEn and RCMSE showing greater longitudinal sensitivity than conventional spatiotemporal metrics. These results demonstrate that a single lumbar IMU, paired with a nonlinear analytics pipeline, can detect gait reorganization during intensive stroke rehabilitation imperceptible to standard clinical measures, providing a reproducible methodological foundation for larger controlled trials.

Background/Objectives: First responders frequently encounter high-stress environments that challenge physiological resilience and autonomic regulation. Heart rate variability (HRV) complexity is a critical marker of adaptive capacity and stress regulation. This study assessed the impact of a wearable-based mindfulness intervention on HRV complexity among first responders using a smartwatch. Methods: A total of 87 first responders participated in a one-month wearable-based intervention. Participants wore Garmin Vivosmart 5 devices to continuously collect PPG data (photoplethysmogram), focusing on beat-to-beat intervals (BBIs). The intervention involved daily Ecological Momentary Assessments (EMAs) and individual randomization to either a mindfulness message, a prompt to access an audio exercise, or no-treatment/control; interventions were delivered via the MYAPT.MIND mobile application. HRV metrics, including Sample Entropy, Multiscale Entropy (MSE), Recurrence Rate (RR), and Determinism (Det), were analyzed pre- and post-intervention/control using paired-samples t-tests. Results: Significant improvements were observed in HRV complexity metrics post-intervention. Sample Entropy increased (M = 1.42, SD = 0.11) compared to pre-intervention (M = 1.39, SD = 0.10; p = 0.007). MSE also showed significant gains (p = 0.038), particularly at lower scales, indicating enhanced short-term autonomic flexibility. Reductions were noted in RR (p = 0.025) and Det (p = 0.018), suggesting improved cardiovascular adaptability and reduced physiological rigidity. Other traditional time-domain metrics, such as Mean HR, SDNN, and RMSSD, did not exhibit significant changes. Conclusions: The wearable-based intervention significantly enhanced HRV complexity, reflecting improved autonomic regulation and adaptive capacity in first responders. These findings support the integration of digital mindfulness strategies for stress management in high-risk occupations. Future research should explore the longitudinal effects and mechanisms mediating these autonomic adaptations.

This proof-of-concept study evaluated the effectiveness of a novel semi-immersive virtual reality dual-task protocol in identifying lingering postural control deficits in individuals with a remote history of concussion. Study aimed to examine how dual-tasking - specifically, centred and peripheral vision Stroop tasks - affects postural sway during standing and walking in previously concussed individuals and healthy controls. The virtual reality system integrated motion capture and force plate technology to create an ecologically realistic environment, enabling more realistic task performance. A divided attention task incorporating centred and peripheral visual stimuli was administered during standing and walking conditions. Task performance was compared between healthy controls and individuals with a documented history of concussion. Statistical analyses included independent-samples t-tests, MANOVA, and Cohen's d for significant effects. Significant gait and postural stability impairments were identified in concussed participants. Concussed individuals exhibited larger sway areas and slower sway dynamics during standing tasks and shorter strides during walking tasks. Concussed individuals exhibited a significantly larger sway area during both the centred Stroop balance task (t(14) = 2.60, p = .021, d = 1.15) and the peripheral Stroop balance task (t(13) = 2.27, p = .041, d = 1.06). These findings suggest that semi-immersive virtual reality dual-task assessments, particularly those involving peripheral visual demands, may detect subtle post-concussion deficits often missed by standard evaluations. This highlights the potential of virtual reality based assistive technology tools to inform more personalised interventions. Such approaches may ultimately improve long-term outcomes and quality of life through more ecologically realistic, real-world assessments.

Traditional evaluations of surgical skill rely heavily on subjective assessments, limiting precision and scalability in modern surgical education. With the emergence of robotic platforms and simulation-based training, there is a pressing need for objective, interpretable, and scalable tools to assess technical proficiency in surgery. This study introduces an explainable machine learning (XAI) framework using surface electromyography (sEMG) and accelerometer data to classify surgeon skill levels and uncover actionable neuromuscular biomarkers of expertise. Twenty-six participants, including novices, residents, and expert urologists, performed standardized robotic tasks (suturing, knot tying, and peg transfers) while sEMG and motion data were recorded from 12 upper-extremity muscle sites using Delsys^® Trigno™ wireless sensors. Time- and frequency-domain features, along with nonlinear dynamical measures such as Lyapunov exponents, entropy, and fractal dimensions, were extracted and fed into multiple supervised machine learning classifiers (SVM, Random Forest, XGBoost, Naïve Bayes). Classification performance was evaluated using accuracy, F1-score, MCC, and AUC. To ensure interpretability, SHAP and LIME were employed to identify and visualize key features distinguishing skill levels. Ensemble models (XGBoost and Random Forest) outperformed others, achieving classification accuracies above 72%, with high F1-scores for all classes. Nonlinear features, particularly Mean_Long_Lyapunov exponent, Correlation Dimension, Approximate Entropy, and Hurst exponent, consistently ranked among the top predictors. Expert surgeons exhibited higher movement complexity and temporal consistency, reflected in higher entropy and correlation dimension, and lower Lyapunov exponents compared to novices. XAI methods revealed that different classes were driven by distinct feature sets: entropy measures best identified novice patterns, while fractal and stability features were more predictive of expert performance. SHAP and LIME enabled both global and instance-specific interpretation of classifier decisions, enhancing transparency and enabling targeted feedback. This study demonstrates the feasibility and utility of combining multimodal wearable sensor data with explainable machine learning to assess robotic surgical skill. The identified biomarkers capture nuanced aspects of motor control such as adaptability, complexity, and stability that distinguish novice, intermediate, and expert surgeons. Beyond classification, the explainable framework offers interpretable insights into why specific skill levels were assigned, providing a pathway for personalized surgical feedback and training. This approach advances the development of objective, transparent, and clinically meaningful assessment tools in surgical education.

This study investigates the kinematic effects of non-athletic, flat-soled sneakers on lower extremity joints during walking. Ten healthy gym-goers (24.4 ± 1.7 years) underwent treadmill gait analysis under two conditions: wearing non-athletic sneakers and walking with only socks. Gait was captured using the Gait Real-time Analysis and Interactive Lab (GRAIL). Dependent variables included cadence, support times, and stride length. Walking with socks significantly increased cadence ( p < .0001) and single support time ( p = .0103), and decreased initial ( p = .018), terminal ( p = .0056), and total double support times ( p = .0092). No significant difference in stride length was observed. These findings suggest non-athletic sneakers may impair proprioception and balance compared to walking in socks. Further research should explore how footwear types influence gait and postural stability.

This study examines the combined effects of green noise and texting on gait to understand how multitasking and auditory stimuli affect walking stability. Green noise, associated with relaxation, was the environmental stimulus; texting the cognitive distractor. We hypothesized texting would reduce cadence and stride length, with green noise either stabilizing or disrupting gait. Ten participants walked on a treadmill under five conditions: normal walking (NW), no texting/sound (WNTNS), sound only (WNTS), texting only (WTNS), and texting with sound (WTS). Gait parameters—step length, step width, single support time, and terminal double support time—were analyzed. Step length decreased in WNTS ( p = .0106) and WTS ( p = .0115) versus NW; step width increased in WTNS ( p < .0001). Single support time was prolonged in WTS; terminal double support time increased in all conditions vs. NW ( p = .0435). Cognitive and environmental distractions alter gait, potentially increasing fall risk. Further research should explore how green noise and texting influence walking stability.

Modern walking often involves secondary tasks that may increase fall risk, especially in older adults. About one-third of adults aged 65+ fall annually, with dual-tasking further elevating this risk. This study examines how cognitive and motor dual-tasks affect gait variability. Ten healthy young adults completed baseline and three dual-task conditions: (1) walking with a Stroop test, (2) walking while carrying a tray with water, and (3) both tasks combined. Gait parameters—including step length, step width, stride length, and double support time—were analyzed. Significant alterations were observed with P-values of 0.0019 (right step length), 0.004 (step width), 0.0007 (stride length), and 0.0477 (double support time), indicating increased gait variability. These results suggest dual-tasking disrupts gait stability and highlight the clinical value of dual-task training for improving motor-cognitive integration and reducing fall risk.

Non-skid socks and external weight are commonly utilized in healthcare and training to improve stability and simulate real-world conditions. However, their combined effects on postural response during perturbation remain unclear. This study examined how non-skid socks and added anterior weight affect latency and amplitude responses during postural perturbations. Ten healthy participants (mean age 24.5 ± 4.38 years) underwent randomized perturbation conditions with and without non-skid socks and 10% body weight applied via weighted vests. Results from two-way ANOVA and mixed-effects models revealed no significant effects of socks, weight, or their interaction on latency (p > 0.05). However, amplitude analysis showed a significant interaction (p < 0.001), indicating that the combination of socks and weight increased postural instability. Specifically, conditions involving non-skid socks and weight resulted in higher amplitudes, suggesting greater deviations of the center of gravity and increased fall risk. Conversely, non-skid socks alone reduced amplitude, enhancing stability compared to barefoot conditions. These findings highlight the nuanced effects of non-skid socks and added weight on balance and stability. While socks alone may improve postural control, their combination with weight appears to elevate instability. Future research should include larger, diverse samples to confirm these findings and guide clinical practice regarding non-skid socks and weighted training protocols.

Objective: The aim of this study was to establish the interactions between joint angular kinematics and gross motor function in typically developing healthy Ghanaian children. Methods: A descriptive cross-sectional study design was employed. A total of 150 (69 (46.0%), 3.25 ± 0.08-year-old boys and 81 (54.0%), 3.25 ± 0.06-year-old girls) 2–4-year-old children were recruited. Joint angular kinematic variables [left hip flexion (LHF), left hip extension (LHE), right hip flexion (RHF), left knee flexion (LKF), right hip extension (RHE), left knee extension (LKE), right knee flexion (RKF), left ankle dorsi-flexion (LADF), right knee extension (RKE), right ankle plantar flexion (RAPF), left ankle plantar flexion (LAPF), and right ankle dorsi-flexion (RADF)] and gross motor function (lying and rolling, sitting, crawling and kneeling, standing, and walking, running, and jumping) were measured with standard scales. Results: The correlations between lying and rolling vs. RHE (r = 0.221; p-value < 0.01), LKE (r = −0.267; p-value < 0.01), LAPF (r = 0.264; p-value < 0.01), and RADF (r = 0.240; p-value < 0.01); crawling and kneeling vs. LKE (r = 0.196; p-value < 0.05) and RADF (r = 0.188; p-value < 0.05); and walking, running, and jumping vs. LKE (r = −0.214; p-value < 0.01) and RADF (r = −0.207; p-value < 0.05) were significant. Conclusions: There was a negative correlation between joint angular kinematics and total gross motor function in this sampled population. Typically, developing healthy children should be exposed to a range of motion, flexibility, and active transportation programs for optimal active lifestyles and improvements in gross motor skills.

This study explores the efficacy of integrating stroboscopic glasses with smartphone-based applications to evaluate postural control, offering a cost-effective alternative to traditional forceplate technology. Athletes, particularly those with visual and visuo-oculomotor enhancements due to sports, often suffer from injuries that necessitate reliance on visual inputs for balance—conditions that can be simulated and studied using visual perturbation methods such as stroboscopic glasses. These glasses intermittently occlude vision, mimicking visual impairments that are crucial in assessing dependency on visual information for postural stability. Participants performed these tasks under three visual conditions: full vision, partial vision occlusion via stroboscopic glasses, and no vision (eyes closed), on foam surfaces to induce postural instability. The use of a smartphone app to measure postural sway was validated against traditional force plate measurements, providing a comparative analysis of both tools under varied sensory conditions. We investigated postural parameters like anterior–posterior and medial–lateral sway ranges, root mean square values, 95% confidence ellipse area, and sway velocity and median dominant sway frequency from both the smartphone and the force plates. Our findings indicate that force plates exhibit high sensitivity to various visual conditions, as evidenced by significant differences observed in certain postural parameters, which were not detected by smartphone-based measurements. Overall, our findings indicate that smartphones show promise as a cost-effective alternative to force plate measurements for routine monitoring of postural control in sports, although they may not achieve the same level of accuracy as force plates. The integration of stroboscopic glasses further refined the assessment by effectively simulating visual impairments, thereby allowing precise evaluation of an individual’s ability to maintain balance under visually perturbed conditions.