Background: Parkinson disease (PD) is a progressive neurodegenerative disorder that affects motor coordination, leading to gait abnormalities. Early detection of PD is crucial for effective management and treatment. Traditional diagnostic methods often require invasive procedures or are performed when the disease has significantly progressed. Therefore, there is a need for noninvasive techniques that can identify early motor symptoms, particularly those related to gait. Objective: The study aimed to develop a noninvasive approach for the early detection of PD by analyzing model-based gait features. The primary focus is on identifying subtle gait abnormalities associated with PD using kinematic characteristics. Methods: Data were collected through controlled video recordings of participants performing the timed up and go (TUG) assessment, with particular emphasis on the turning phase. The kinematic features analyzed include shoulder distance, step length, stride length, knee and hip angles, leg and arm symmetry, and trunk angles. These features were processed using advanced filtering techniques and analyzed through machine learning methods to distinguish between normal and PD-affected gait patterns. Results: The analysis of kinematic features during the turning phase of the TUG assessment revealed that individuals with PD exhibited subtle gait abnormalities, such as freezing of gait, reduced step length, and asymmetrical movements. The model-based features proved effective in differentiating between normal and PD-affected gait, demonstrating the potential of this approach in early detection. Conclusions: This study presents a promising noninvasive method for the early detection of PD by analyzing specific gait features during the turning phase of the TUG assessment. The findings suggest that this approach could serve as a sensitive and accurate tool for diagnosing and monitoring PD, potentially leading to earlier intervention and improved patient outcomes.

This link will take you to a page that’s not on LinkedIn

This study explores the application of machine learning (ML) to derive and analyze individual gait patterns (i.e., gait signatures) from ground reaction force data. This study leverages three datasets...

Background: Gait speed indicates of onset or decline of physical performance in sarcopenia. However, real-time measurements of other gait parameters, such as step length, stride length, step width, and support time, are limited. The advent of wearable technology has facilitated the measurement of these parameters, necessitating further investigation into their potential applications. Objective: This study aimed to investigate the relationship between gait parameters measured using wearable sensors and muscle mass, strength, and physical performance in community-dwelling older adults. Methods: In a cross-sectional study of 91 participants aged ≥ 65 years, gait parameters, such as step count, step length, cadence, single and double support times, vertical oscillation, and instantaneous vertical loading rate (IVLR), measured by a wireless earbud device, were analyzed with respect to the appendicular skeletal muscle mass index (SMI), calf circumference, hand grip strength, 5-time chair stand test, short physical performance battery (SPPB), and SARC-F questionnaire: strength, assistance with walking, rise from a chair, climb stairs and falls. This study was conducted from July 10, 2023, and November 1, 2023, at an outpatient clinic of a university hospital in Seoul, Korea. Multiple regression analysis was performed to investigate independent associations after adjusting for age, sex, body mass index, and comorbidities. Results: Among 91 participants (45 men and 46 women; mean age: 74.1 for men and 73.6 for women), gait speed and vertical oscillation showed negative associations with the 5-time chair stand test (p < 0.001) and SARC-F, but positive associations with SPPB (p < 0.001). Vertical oscillations were also associated with grip strength (p = 0.003). Single and double support times were associated with the 5-time chair stand test and SPPB (p < 0.001). In addition, double support time was associated with SARC-F scores (p < 0.001). Gait speed, support time, vertical oscillation, and IVLR showed independent associations with the 5-time chair stand test and SPPB (p < 0.001), both related to muscle strength or physical performance. Gait speed, double support time, and vertical oscillation all had significant associations with SARC-F scores. Conclusions: This study demonstrated a significant association between gait monitoring using wearable sensors and quantitative assessments of muscle strength and physical performance in elderly people. Furthermore, this study substantiated the extensive applicability of diverse gait parameters in predicting sarcopenia.

Background: Frailty affects over 50% of older adults in long-term care (LTC), and early detection is critical due to its potential reversibility. Wearable sensors enable continuous monitoring of gait and physical activity, and machine learning has shown promise in detecting frailty among community-dwelling older adults. However, its applicability in LTC remains underexplored. Furthermore, dynamic gait outcomes (eg, gait stability and symmetry) may offer more sensitive frailty indicators than traditional measures like gait speed, yet their potential remains largely untapped. Objective: This study aimed to evaluate whether frailty in LTC facilities could be effectively identified using machine learning models trained on gait and daily physical activity data derived from a single accelerometer. Methods: This study is a cross-sectional secondary analysis of baseline data from a 2-arm cluster randomized controlled trial. Of the 164 individuals initially enrolled, 51 participants (age: mean 85.0, SD 9.0 years; female: n=24, 47.1%) met the inclusion criteria of completing all assessments required for this study and were included in the final analysis. Frailty status was assessed using the fatigue, resistance, ambulation, incontinence, loss of weight, nutritional approach, and help with dressing (FRAIL-NH) scale. Participants completed a 5-meter walking task while wearing a 3D accelerometer. Following this task, the accelerometer was used to record daily physical activity over approximately 1 week. A total of 34 dynamic and spatial-temporal gait outcomes, 3 physical activity variables, and 6 demographic characteristics were extracted. Five conventional machine learning models were trained to classify frailty status using a leave-one-out cross-validation approach. Model performance was evaluated based on accuracy and the area under the receiver operating characteristic curve. To enhance model interpretability, explainable artificial intelligence techniques were used to identify the most influential predictive outcomes. Results: The extreme gradient boosting model demonstrated the optimal performance with an accuracy of 86.3% and an area under the curve of 0.92. Explainable artificial intelligence analysis revealed that older adults with frailty exhibited more variable, complex, and asymmetric gait patterns, which were characterized by higher stride length variability, increased sample entropy, and a higher gait symmetry score. Conclusions: Our findings suggest that dynamic gait outcomes may serve as more sensitive indicators of frailty than spatial-temporal gait outcomes (eg, gait speed) in LTC settings, offering valuable insights for enhancing frailty detection and management.

Background: Measuring free-living gait with wearable sensors has great potential in supporting personalised rehabilitation. There are challenges meeting the accuracy levels of laboratory-based measurements in detecting initial and final contact, particularly in impaired populations. Objective: To test the criterion validity of a novel temporal gait measurement technique, combining the ActivPAL 4+ (PAL Technologies, Glasgow, UK) and the Teager-Kaiser Energy Operator, to measure stance phase duration in chronic stroke survivors through comparison with the Evoke cluster marker system (Vicon, Oxford, UK). Methods: Stroke participants (n=13, mean age = 59 years  14, time since stroke = 1.5 years  0.5) were assessed using the ACTIVPAL 4+ and a motion capture system. Two 10m walk tests were measured, while wearing two ActivPAL 4+ (located on anterior of both thighs) and clusters on the pelvis and ankles from the motion capture system. The Teager-Kaiser Energy Operator signal processing technique was used to extract the stance durations of the ActivPAL 4+, compared with a previously validated method. Results: There was a good agreement (bias: 0.03s, limits of agreement: -0.22 to 0.28s) between the ACTIVPAL 4+ and motion capture system despite a slight underestimation (mean stance time: 0.850s vs. motion capture system: 0.881s). Conclusions: Findings suggest the ACTIVPAL 4+, combined with Teager-Kaiser Energy Operator technique, provides valid stance time measurements when compared laboratory-based systems, supporting its use in free-living gait analysis and feedback during rehabilitation. Limitations include laboratory-only validation and a small population of chronic stroke patients. Future work should explore free-living gait, and larger, and broader, cross section of stroke populations.