Harnessing physical activity monitoring and digital biomarkers of frailty from pendant based wearables to predict chemotherapy resilience in veterans with cancer

This study evaluated the use of pendant-based wearables for monitoring digital biomarkers of frailty in predicting chemotherapy resilience among 27 veteran cancer patients (average age: 64.6 ± 13.4 years), undergoing bi-weekly chemotherapy. Immediately following their first day of chemotherapy cycle, participants wore a water-resistant pendant sensor for 14 days. This device tracked frailty markers like cadence (slowness), daily steps (inactivity), postural transitions (weakness), and metrics such as longest walk duration and energy expenditure (exhaustion). Participants were divided into resilient and non-resilient groups based on adverse events within 6 months post-chemotherapy, including dose reduction, treatment discontinuation, unplanned hospitalization, or death. A Chemotherapy-Resilience-Index (CRI) ranging from 0 to 1, where higher values indicate poorer resilience, was developed using regression analysis. It combined physical activity data with baseline Eastern Cooperative Oncology Group (ECOG) assessments. The protocol showed a 97% feasibility rate, with sensor metrics effectively differentiating between groups as early as day 6 post-therapy. The CRI, calculated using data up to day 6 and baseline ECOG, significantly distinguished resilient (CRI = 0.2 ± 0.27) from non-resilient (CRI = 0.7 ± 0.26) groups (p < 0.001, Cohen's d = 1.67). This confirms the potential of remote monitoring systems in tracking post-chemotherapy functional capacity changes and aiding early non-resilience detection, subject to validation in larger studies.

Advances in prosthetic technology: a perspective on ethical considerations for development and clinical translation

Technological advancements of prostheses in recent years, such as haptic feedback, active power, and machine learning for prosthetic control, have opened new doors for improved functioning, satisfaction, and overall quality of life. However, little attention has been paid to ethical considerations surrounding the development and translation of prosthetic technologies into clinical practice. This article, based on current literature, presents perspectives surrounding ethical considerations from the authors' multidisciplinary views as prosthetists (HG, AM, CLM, MGF), as well as combined research experience working directly with people using prostheses (AM, CLM, MGF), wearable technologies for rehabilitation (MGF, BN), machine learning and artificial intelligence (BN, KKQ), and ethics of advanced technologies (KKQ). The target audience for this article includes developers, manufacturers, and researchers of prosthetic devices and related technology. We present several ethical considerations for current advances in prosthetic technology, as well as topics for future research, that may inform product and policy decisions and positively influence the lives of those who can benefit from advances in prosthetic technology.

Potential applications of artificial intelligence and machine learning on diagnosis, treatment, and outcome prediction to address health care disparities of chronic limb-threatening ischemia

Chronic limb-threatening ischemia (CLTI) is the most advanced form of peripheral artery disease. CLTI has an extremely poor prognosis and is associated with considerable risk of major amputation, cardiac morbidity, mortality, and poor quality of life. Early diagnosis and targeted treatment of CLTI is critical for improving patient's prognosis. However, this objective has proven elusive, time-consuming, and challenging due to existing health care disparities among patients. In this article, we reviewed how artificial intelligence (AI) and machine learning (ML) can be helpful to accurately diagnose, improve outcome prediction, and identify disparities in the treatment of CLTI. We demonstrate the importance of AI/ML approaches for management of these patients and how available data could be used for computer-guided interventions. Although AI/ML applications to mitigate health care disparities in CLTI are in their infancy, we also highlighted specific AI/ML methods that show potential for addressing health care disparities in CLTI.

Game-based intradialytic non-weight-bearing exercise training on gait speed and balance in older adults with diabetes: a single-blind randomized controlled trial

Older adults with diabetes receiving hemodialysis have impaired gait speed and balance compared to the general population, which have been associated with increased risks of falls and mortality. This study evaluated the effectiveness of a game-based intradialytic exercise training program (iExergame) on improving gait speed and balance. This was a single-blind randomized controlled trial. The intervention group (IG) received iExergame training using real-time audiovisual feedback with wearable inertial sensors. The control group (CG) received conventional training without any technology. Both trainings were intradialytic, non-weight-bearing, and used ankle range of motion. Gait and balance parameters were collected at baseline and 4-week follow-up. Data from 70 adults (age 64.2 ± 9.0 years) were analyzed. Compared to the CG, the IG showed greater changes between baseline and 4-week follow-up in several parameters. Gait parameters included faster speeds and longer stride lengths, particularly during dual task walking (p < 0.050). Balance parameters included reductions in center of mass (p = 0.004), ankle (p < 0.001), and hip (p = 0.010) sways during semi-tandem stance, particularly in users of assistive devices. iExergame training could improve gait speed and balance in this population and might be an option to increase intradialytic exercise adherence while reducing burdens of exercise administration.

Indications of musculoskeletal health in deceased male individuals with lower-limb amputations: comparison to non-amputee and diabetic controls

Individuals with lower-limb amputations, many of whom have type 2 diabetes, experience impaired musculoskeletal health. This study: (1) compared residual and intact limbs of diabetic and non-diabetic post-mortem individuals with amputation to identify structures vulnerable to injury, and (2) compared findings to diabetic and healthy control groups to differentiate influences of amputation and diabetes on musculoskeletal health. Postmortem CT scans of three groups, ten individuals each, were included: (1) individuals with transtibial or transfemoral amputations, half with diabetes (2) diabetic controls, and (3) healthy controls. Hip and knee joint spaces, cross-sectional thigh muscle and fat areas, and cross-sectional bone properties (e.g. area, thickness, geometry) were measured. Wilcoxon Signed-Rank and Kruskal-Wallis tests assessed statistical significance. Asymmetry percentages between limbs assessed clinical significance. Residual limbs of individuals with amputation, particularly those with diabetes, had significantly less thigh muscle area and thinner distal femoral cortical bone compared to intact limbs. Compared to control groups, individuals with amputation had significantly narrower joint spaces, less thigh muscle area bilaterally, and thinner proximal femoral cortical bone in the residual limb. Diabetic individuals with amputation had the most clinically significant asymmetry. Findings tended to align with those of living individuals. However, lack of available medical information and small sample sizes reduced the anticipated clinical utility. Larger sample sizes of living individuals are needed to assess generalizability of findings. Quantifying musculoskeletal properties and differentiating influences of amputation and diabetes could eventually help direct rehabilitation techniques.

Machine Learning-Based Aggression Detection in Children with ADHD Using Sensor-Based Physical Activity Monitoring

Aggression in children is highly prevalent and can have devastating consequences, yet there is currently no objective method to track its frequency in daily life. This study aims to investigate the use of wearable-sensor-derived physical activity data and machine learning to objectively identify physical-aggressive incidents in children. Participants (n = 39) aged 7 to 16 years, with and without ADHD, wore a waist-worn activity monitor (ActiGraph, GT3X+) for up to one week, three times over 12 months, while demographic, anthropometric, and clinical data were collected. Machine learning techniques, specifically random forest, were used to analyze patterns that identify physical-aggressive incident with 1-min time resolution. A total of 119 aggression episodes, lasting 7.3 ± 13.1 min for a total of 872 1-min epochs including 132 physical aggression epochs, were collected. The model achieved high precision (80.2%), accuracy (82.0%), recall (85.0%), F1 score (82.4%), and area under the curve (89.3%) to distinguish physical aggression epochs. The sensor-derived feature of vector magnitude (faster triaxial acceleration) was the second contributing feature in the model, and significantly distinguished aggression and non-aggression epochs. If validated in larger samples, this model could provide a practical and efficient solution for remotely detecting and managing aggressive incidents in children.

Taking a Load Off: User Perceptions of Smart Offloading Walkers for Diabetic Foot Ulcers Using the Technology Acceptance Model

People with diabetic foot ulcers (DFUs) are commonly prescribed offloading walkers, but inadequate adherence to prescribed use can be a barrier to ulcer healing. This study examined user perspectives of offloading walkers to provide insight on ways to help promote adherence. Participants were randomized to wear: (1) irremovable, (2) removable, or (3) smart removable walkers (smart boot) that provided feedback on adherence and daily walking. Participants completed a 15-item questionnaire based on the Technology Acceptance Model (TAM). Spearman correlations assessed associations between TAM ratings with participant characteristics. Chi-squared tests compared TAM ratings between ethnicities, as well as 12-month retrospective fall status. A total of 21 adults with DFU (age 61.5 ± 11.8 years) participated. Smart boot users reported that learning how to use the boot was easy (ρ =-0.82, p≤ 0.001). Regardless of group, people who identified as Hispanic or Latino, compared to those who did not, reported they liked using the smart boot (p = 0.05) and would use it in the future (p = 0.04). Non-fallers, compared to fallers, reported the design of the smart boot made them want to wear it longer (p = 0.04) and it was easy to take on and off (p = 0.04). Our findings can help inform considerations for patient education and design of offloading walkers for DFUs.

Electrical stimulation to regain lower extremity muscle perfusion and endurance in patients with post-acute sequelae of SARS CoV-2: A randomized controlled trial

Muscle deconditioning and impaired vascular function in the lower extremities (LE) are among the long-term symptoms experienced by COVID-19 patients with a history of severe illness. These symptoms are part of the post-acute sequelae of Sars-CoV-2 (PASC) and currently lack evidence-based treatment. To investigate the efficacy of lower extremity electrical stimulation (E-Stim) in addressing PASC-related muscle deconditioning, we conducted a double-blinded randomized controlled trial. Eighteen (n = 18) patients with LE muscle deconditioning were randomly assigned to either the intervention (IG) or the control (CG) group, resulting in 36 LE being assessed. Both groups received daily 1 h E-Stim on both gastrocnemius muscles for 4 weeks, with the device functional in the IG and nonfunctional in the CG. Changes in plantar oxyhemoglobin (OxyHb) and gastrocnemius muscle endurance (GNMe) in response to 4 weeks of daily 1 h E-Stim were assessed. At each study visit, outcomes were measured at onset (t₀ ), 60 min (t₆₀ ), and 10 min after E-Stim therapy (t₇₀ ) by recording ΔOxyHb with near-infrared spectroscopy. ΔGNMe was measured with surface electromyography at two time intervals: 0-5 min (Intv₁ ) and: 55-60 min (Intv₂ ). Baseline OxyHb decreased in both groups at t₆₀ (IG: p = 0.046; CG: p = 0.026) and t₇₀ (IG = p = 0.021; CG: p = 0.060) from t₀ . At 4 weeks, the IG's OxyHb increased from t₆₀ to t₇₀ (p < 0.001), while the CG's decreased (p = 0.003). The IG had higher ΔOxyHb values than the CG at t₇₀ (p = 0.004). Baseline GNMe did not increase in either group from Intv₁ to Intv₂ . At 4 weeks, the IG's GNMe increased (p = 0.031), whereas the CG did not change. There was a significant association between ΔOxyHb and ΔGNMe (r = 0.628, p = 0.003) at 4 weeks in the IG. In conclusion, E-Stim can improve muscle perfusion and muscle endurance in individuals with PASC experiencing LE muscle deconditioning.

Clinical evaluation of fall risk in older adults who use lower-limb prostheses: A scoping review

BACKGROUND

No reviews or evidence-based clinical protocols exist to evaluate fall risk in older adults who use lower-limb prostheses, despite falls being prevalent and costly in this population. This scoping review sought to determine assessments, defined as clinical outcome measures and gait parameters, associated with fall risk in this population to determine if a systematic review is warranted and help inform an evidence-based clinical protocol.

METHODS

Google Scholar, PubMed, and Scopus were searched on April 19th, 2022 to include peer-reviewed original research. Included articles reported relationships between falls and clinical outcome measures or gait parameters in older adults who use transtibial or transfemoral prostheses. Clinical outcome measures included self-reported questionnaires and functional mobility tests. Gait parameters included spatiotemporal, kinematic, and kinetic data during walking and stair negotiation.

RESULTS

Nineteen articles were included. Clinical outcome measure scores, gait parameter data, and cutoff scores by fall status (nonfallers, single fallers, recurrent fallers) were summarized. Six articles determined clinical outcome measures that had statistically significant associations with falls, and two articles determined gait parameters that had statistically significant associations with falls.

CONCLUSIONS

The majority of articles found no clinical outcome measure or gait parameter alone was effective at identifying fall risks in this population. Future research should evaluate a combination of assessments and collect prospective fall data to move towards establishing an evidence-based protocol to evaluate fall risk in older adults using lower-limb prostheses.

Normalized kinematic walking symmetry data for individuals who use lower-limb prostheses: considerations for clinical practice and future research

Introduction

Individuals who use unilateral transtibial or transfemoral prostheses have negative secondary health effects associated with decreased kinematic (e.g., spatiotemporal and joint angle) walking symmetry between prosthetic and intact limbs. Research studies have quantified kinematic walking symmetry, but studies can be difficult to compare owing to the inclusion of small sample sizes and differences in participant demographics, biomechanical parameters, and mathematical analysis of symmetry. This review aims to normalize kinematic walking symmetry research data across studies by level of limb loss and prosthetic factors to inform considerations in clinical practice and future research.

Methods

A search was performed on March 18, 2020, in PubMed, Scopus, and Google Scholar to encompass kinematic walking symmetry literature from the year 2000. First, the most common participant demographics, kinematic parameters, and mathematical analysis of symmetry were identified across studies. Then, the most common mathematical analysis of symmetry was used to recalculate symmetry data across studies for the five most common kinematic parameters.

Results

Forty-four studies were included in this review. The most common participant demographics were younger adults with traumatic etiology who used componentry intended for higher activity levels. The most common kinematic parameters were step length, stance time, and sagittal plane ankle, knee, and hip range of motion. The most common mathematical analysis was a particular symmetry index equation.

Conclusions

Normalization of data showed that symmetry tended to decrease as level of limb loss became more proximal and to increase with prosthetic componentry intended for higher activity levels. However, most studies included 10 or fewer individuals who were active younger adults with traumatic etiologies.

Clinical Relevance

Data summarized in this review could be used as reference values for rehabilitation and payer justification. Specifically, these data can help guide expectations for magnitudes of walking symmetry throughout rehabilitation or to justify advanced prosthetic componentry for active younger adults under 65 years of age with traumatic etiologies to payers.

A pilot case series for concurrent validation of inertial measurement units to motion capture in individuals who use unilateral lower-limb prostheses

Introduction

Inertial measurement units (IMUs) may be viable options to collect gait data in clinics. This study compared IMU to motion capture data in individuals who use unilateral lower-limb prostheses.

Methods

Participants walked with lower-body IMUs and reflective markers in a motion analysis space. Sagittal plane hip, knee, and ankle waveforms were extracted for the entire gait cycle. Discrete points of peak flexion, peak extension, and range of motion were extracted from the waveforms. Stance times were also extracted to assess the IMU software's accuracy at detecting gait events. IMU and motion capture-derived data were compared using absolute differences and root mean square error (RMSE).

Results

Five individuals (n = 3 transtibial; n = 2 transfemoral) participated. IMU prosthetic limb data was similar to motion capture (RMSE: waveform ≤4.65°; discrete point ≤9.04°; stance ≤0.03s). However, one transfemoral participant had larger differences at the microprocessor knee joint (RMSE: waveform ≤15.64°; discrete ≤29.21°) from IMU magnetometer interference. Intact limbs tended to have minimal differences between IMU and motion capture data (RMSE: waveform ≤6.33°; discrete ≤9.87°; stance ≤0.04s).

Conclusion

Findings from this pilot study suggest IMUs have the potential to collect data similar to motion capture systems in sagittal plane kinematics and stance time.