Unbiased and mobile gait analysis detects motor impairment in Parkinson's disease

Integrating digital gait data with metabolomics and clinical data to predict outcomes in Parkinson's disease

Parkinson's disease (PD) presents diverse symptoms and comorbidities, complicating its diagnosis and management. The primary objective of this cross-sectional, monocentric study was to assess digital gait sensor data's utility for monitoring and diagnosis of motor and gait impairment in PD. As a secondary objective, for the more challenging tasks of detecting comorbidities, non-motor outcomes, and disease progression subgroups, we evaluated for the first time the integration of digital markers with metabolomics and clinical data. Using shoe-attached digital sensors, we collected gait measurements from 162 patients and 129 controls in a single visit. Machine learning models showed significant diagnostic power, with AUC scores of 83-92% for PD vs. control and up to 75% for motor severity classification. Integrating gait data with metabolomics and clinical data improved predictions for challenging-to-detect comorbidities such as hallucinations. Overall, this approach using digital biomarkers and multimodal data integration can assist in objective disease monitoring, diagnosis, and comorbidity detection.

Simplification of Mobility Tests and Data Processing to Increase Applicability of Wearable Sensors as Diagnostic Tools for Parkinson's Disease

Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson's disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.

Progression subtypes in Parkinson's disease identified by a data-driven multi cohort analysis

The progression of Parkinson's disease (PD) is heterogeneous across patients, affecting counseling and inflating the number of patients needed to test potential neuroprotective treatments. Moreover, disease subtypes might require different therapies. This work uses a data-driven approach to investigate how observed heterogeneity in PD can be explained by the existence of distinct PD progression subtypes. To derive stable PD progression subtypes in an unbiased manner, we analyzed multimodal longitudinal data from three large PD cohorts and performed extensive cross-cohort validation. A latent time joint mixed-effects model (LTJMM) was used to align patients on a common disease timescale. Progression subtypes were identified by variational deep embedding with recurrence (VaDER). In each cohort, we identified a fast-progressing and a slow-progressing subtype, reflected by different patterns of motor and non-motor symptoms progression, survival rates, treatment response, features extracted from DaTSCAN imaging and digital gait assessments, education, and Alzheimer's disease pathology. Progression subtypes could be predicted with ROC-AUC up to 0.79 for individual patients when a one-year observation period was used for model training. Simulations demonstrated that enriching clinical trials with fast-progressing patients based on these predictions can reduce the required cohort size by 43%. Our results show that heterogeneity in PD can be explained by two distinct subtypes of PD progression that are stable across cohorts. These subtypes align with the brain-first vs. body-first concept, which potentially provides a biological explanation for subtype differences. Our predictive models will enable clinical trials with significantly lower sample sizes by enriching fast-progressing patients.

The effects of an individualized smartphone-based exercise program on self-defined motor tasks in Parkinson's disease: a long-term feasibility study

BACKGROUND

Exercise therapy is considered effective for the treatment of motor impairment in patients with Parkinson's disease (PD). During the COVID-19 pandemic, training sessions were cancelled and the implementation of telerehabilitation concepts became a promising solution. The aim of this controlled interventional feasibility study was to evaluate the long-term acceptance and to explore initial effectiveness of a digital, home-based, high-frequency exercise program for PD patients. Training effects were assessed using patient-reported outcome measures combined with sensor-based and clinical scores.

METHODS

16 PD patients (smartphone group, SG) completed a home-based, individualized training program over 6-8 months using a smartphone app, remotely supervised by a therapist, and tailored to the patient's motor impairments and capacity. A control group (CG, n = 16) received medical treatment without participating in digital exercise training. The usability of the app was validated using System Usability Scale (SUS) and User Version of the Mobile Application Rating Scale (uMARS). Outcome measures included among others Unified Parkinson Disease Rating Scale, part III (UPDRS-III), sensor-based gait parameters derived from standardized gait tests, Parkinson's Disease Questionnaire (PDQ-39), and patient-defined motor activities of daily life (M-ADL).

RESULTS

Exercise frequency of 74.5% demonstrated high adherence in this cohort. The application obtained 84% in SUS and more than 3.5/5 points in each subcategory of uMARS, indicating excellent usability. The individually assessed additional benefit showed at least 6 out of 10 points (Mean = 8.2 ± 1.3). From a clinical perspective, patient-defined M-ADL improved for 10 out of 16 patients by 15.5% after the training period. The results of the UPDRS-III remained stable in the SG while worsening in the CG by 3.1 points (24%). The PDQ-39 score worsened over 6-8 months by 83% (SG) and 59% (CG) but the subsection mobility showed a smaller decline in the SG (3%) compared to the CG (77%) without reaching significance level for all outcomes. Sensor-based gait parameters remained constant in both groups.

CONCLUSIONS

Long-term training over 6-8 months with the app is considered feasible and acceptable, representing a cost-effective, individualized approach to complement dopaminergic treatment. This study indicates that personalized, digital, high-frequency training leads to benefits in motor sections of ADL and Quality of Life.

Subthalamic 85 Hz deep brain stimulation improves walking pace and stride length in Parkinson's disease patients

BACKGROUND

Mobile gait sensors represent a compelling tool to objectify the severity of symptoms in patients with idiopathic Parkinson's disease (iPD), but also to determine the therapeutic benefit of interventions. In particular, parameters of Deep Brain stimulation (DBS) with its short latency could be accurately assessed using sensor data. This study aimed at gaining insight into gait changes due to different DBS parameters in patients with subthalamic nucleus (STN) DBS.

METHODS

An analysis of various gait examinations was performed on 23 of the initially enrolled 27 iPD patients with chronic STN DBS. Stimulation settings were previously adjusted for either amplitude, frequency, or pulse width in a randomised order. A linear mixed effects model was used to analyse changes in gait speed, stride length, and maximum sensor lift.

RESULTS

The findings of our study indicate significant improvements in gait speed, stride length, and leg lift measurable with mobile gait sensors under different DBS parameter variations. Notably, we observed positive results at 85 Hz, which proved to be more effective than often applied higher frequencies and that these improvements were traceable across almost all conditions. While pulse widths did produce some improvements in leg lift, they were less well tolerated and had inconsistent effects on some of the gait parameters. Our research suggests that using lower frequencies of DBS may offer a more tolerable and effective approach to enhancing gait in individuals with iPD.

CONCLUSIONS

Our results advocate for lower stimulation frequencies for patients who report gait difficulties, especially those who can adapt their DBS settings remotely. They also show that mobile gait sensors could be incorporated into clinical practice in the near future.

Automatic Assessments of Parkinsonian Gait with Wearable Sensors for Human Assistive Systems

The rehabilitation evaluation of Parkinson's disease has always been the research focus of human assistive systems. It is a research hotspot to objectively and accurately evaluate the gait condition of Parkinson's disease patients, thereby adjusting the actuators of the human-machine system and making rehabilitation robots better adapt to the recovery process of patients. The rehabilitation evaluation of Parkinson's disease has always been the research focus of rehabilitation robots. It is a research hotspot to be able to objectively and accurately evaluate the recovery of Parkinson's disease patients, thereby adjusting the driving module of the human-machine collaboration system in real time, so that rehabilitation robots can better adapt to the recovery process of Parkinson's disease. The gait task in the Unified Parkinson's Disease Rating Scale (UPDRS) is a widely accepted standard for assessing the gait impairments of patients with Parkinson's disease (PD). However, the assessments conducted by neurologists are always subjective and inaccurate, and the results are determined by the neurologists' observation and clinical experience. Thus, in this study, we proposed a novel machine learning-based method of automatically assessing the gait task in UPDRS with wearable sensors as a more convenient and objective alternative means for PD gait assessment. In the design, twelve gait features, including three spatial-temporal features and nine kinematic features, were extracted and calculated from two shank-mounted IMUs. A novel nonlinear model is developed for calculating the score of gait task from the gait features. Twenty-five PD patients and twenty-eight healthy subjects were recruited for validating the proposed method. For comparison purpose, three traditional models, which have been used in previous studies, were also tested by the same dataset. In terms of percentages of participants, 84.9%, 73.6%, 73.6%, and 66.0% of the participants were accurately assigned into the true level with the proposed nonlinear model, the support vector machine model, the naive Bayes model, and the linear regression model, respectively, which indicates that the proposed method has a good performance on calculating the score of the UPDRS gait task and conformance with the rating done by neurologists.

Perspective on "in the wild" movement analysis using machine learning

Recent advances in wearable sensing and machine learning have created ample opportunities for "in the wild" movement analysis in sports, since the combination of both enables real-time feedback to be provided to athletes and coaches, as well as long-term monitoring of movements. The potential for real-time feedback is useful for performance enhancement or technique analysis, and can be achieved by training efficient models and implementing them on dedicated hardware. Long-term monitoring of movement can be used for injury prevention, among others. Such applications are often enabled by training a machine learned model from large datasets that have been collected using wearable sensors. Therefore, in this perspective paper, we provide an overview of approaches for studies that aim to analyze sports movement "in the wild" using wearable sensors and machine learning. First, we discuss how a measurement protocol can be set up by answering six questions. Then, we discuss the benefits and pitfalls and provide recommendations for effective training of machine learning models from movement data, focusing on data pre-processing, feature calculation, and model selection and tuning. Finally, we highlight two application domains where "in the wild" data recording was combined with machine learning for injury prevention and technique analysis, respectively.

Machine Learning and Wearable Sensors for the Early Detection of Balance Disorders in Parkinson's Disease

Dynamic posturography combined with wearable sensors has high sensitivity in recognizing subclinical balance abnormalities in patients with Parkinson's disease (PD). However, this approach is burdened by a high analytical load for motion analysis, potentially limiting a routine application in clinical practice. In this study, we used machine learning to distinguish PD patients from controls, as well as patients under and not under dopaminergic therapy (i.e., ON and OFF states), based on kinematic measures recorded during dynamic posturography through portable sensors. We compared 52 different classifiers derived from Decision Tree, K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network with different kernel functions to automatically analyze reactive postural responses to yaw perturbations recorded through IMUs in 20 PD patients and 15 healthy subjects. To identify the most efficient machine learning algorithm, we applied three threshold-based selection criteria (i.e., accuracy, recall and precision) and one evaluation criterion (i.e., goodness index). Twenty-one out of 52 classifiers passed the three selection criteria based on a threshold of 80%. Among these, only nine classifiers were considered "optimum" in distinguishing PD patients from healthy subjects according to a goodness index ≤ 0.25. The Fine K-Nearest Neighbor was the best-performing algorithm in the automatic classification of PD patients and healthy subjects, irrespective of therapeutic condition. By contrast, none of the classifiers passed the three threshold-based selection criteria in the comparison of patients in ON and OFF states. Overall, machine learning is a suitable solution for the early identification of balance disorders in PD through the automatic analysis of kinematic data from dynamic posturography.

Assessing Cerebellar Disorders with Wearable Inertial Sensor Data Using Time-Frequency and Autoregressive Hidden Markov Model Approaches

Wearable sensor data is relatively easily collected and provides direct measurements of movement that can be used to develop useful behavioral biomarkers. Sensitive and specific behavioral biomarkers for neurodegenerative diseases are critical to supporting early detection, drug development efforts, and targeted treatments. In this paper, we use autoregressive hidden Markov models and a time-frequency approach to create meaningful quantitative descriptions of behavioral characteristics of cerebellar ataxias from wearable inertial sensor data gathered during movement. We create a flexible and descriptive set of features derived from accelerometer and gyroscope data collected from wearable sensors worn while participants perform clinical assessment tasks, and use these data to estimate disease status and severity. A short period of data collection (<5 min) yields enough information to effectively separate patients with ataxia from healthy controls with very high accuracy, to separate ataxia from other neurodegenerative diseases such as Parkinson’s disease, and to provide estimates of disease severity.

The Effects of an Individualized Smartphone-Based Exercise Program on Self-defined Motor Tasks in Parkinson Disease: Pilot Interventional Study

BACKGROUND

Bradykinesia and rigidity are prototypical motor impairments of Parkinson disease (PD) highly influencing everyday life. Exercise training is an effective treatment alternative for motor symptoms, complementing dopaminergic medication. High frequency training is necessary to yield clinically relevant improvements. Exercise programs need to be tailored to individual symptoms and integrated in patients' everyday life. Due to the COVID-19 pandemic, exercise groups in outpatient setting were largely reduced. Developing remotely supervised solutions is therefore of significant importance.

OBJECTIVE

This pilot study aimed to evaluate the feasibility of a digital, home-based, high-frequency exercise program for patients with PD.

METHODS

In this pilot interventional study, patients diagnosed with PD received 4 weeks of personalized exercise at home using a smartphone app, remotely supervised by specialized therapists. Exercises were chosen based on the patient-defined motor impairment and depending on the patients' individual capacity (therapists defined 3-5 short training sequences for each participant). In a first education session, the tailored exercise program was explained and demonstrated to each participant and they were thoroughly introduced to the smartphone app. Intervention effects were evaluated using the Unified Parkinson Disease Rating Scale, part III; standardized sensor-based gait analysis; Timed Up and Go Test; 2-minute walk test; quality of life assessed by the Parkinson Disease Questionnaire; and patient-defined motor tasks of daily living. Usability of the smartphone app was assessed by the System Usability Scale. All participants gave written informed consent before initiation of the study.

RESULTS

In total, 15 individuals with PD completed the intervention phase without any withdrawals or dropouts. The System Usability Scale reached an average score of 72.2 (SD 6.5) indicating good usability of the smartphone app. Patient-defined motor tasks of daily living significantly improved by 40% on average in 87% (13/15) of the patients. There was no significant impact on the quality of life as assessed by the Parkinson Disease Questionnaire (but the subsections regarding mobility and social support improved by 14% from 25 to 21 and 19% from 15 to 13, respectively). Motor symptoms rated by Unified Parkinson Disease Rating Scale, part III, did not improve significantly but a descriptive improvement of 14% from 18 to 16 could be observed. Clinically relevant changes in Timed Up and Go test, 2-minute walk test, and sensor-based gait parameters or functional gait tests were not observed.

CONCLUSIONS

This pilot interventional study presented that a tailored, digital, home-based, and high-frequency exercise program over 4 weeks was feasible and improved patient-defined motor activities of daily life based on a self-developed patient-defined impairment score indicating that digital exercise concepts may have the potential to beneficially impact motor symptoms of daily living. Future studies should investigate sustainability effects in controlled study designs conducted over a longer period.

Data Representativeness in Accessibility Datasets: A Meta-Analysis

As data-driven systems are increasingly deployed at scale, ethical concerns have arisen around unfair and discriminatory outcomes for historically marginalized groups that are underrepresented in training data. In response, work around AI fairness and inclusion has called for datasets that are representative of various demographic groups. In this paper, we contribute an analysis of the representativeness of age, gender, and race & ethnicity in accessibility datasets-datasets sourced from people with disabilities and older adults-that can potentially play an important role in mitigating bias for inclusive AI-infused applications. We examine the current state of representation within datasets sourced by people with disabilities by reviewing publicly-available information of 190 datasets, we call these accessibility datasets. We find that accessibility datasets represent diverse ages, but have gender and race representation gaps. Additionally, we investigate how the sensitive and complex nature of demographic variables makes classification difficult and inconsistent (e.g., gender, race & ethnicity), with the source of labeling often unknown. By reflecting on the current challenges and opportunities for representation of disabled data contributors, we hope our effort expands the space of possibility for greater inclusion of marginalized communities in AI-infused systems.

The placement of foot-mounted IMU sensors does affect the accuracy of spatial parameters during regular walking

Gait analysis using foot-worn inertial measurement units has proven to be a reliable tool to diagnose and monitor many neurological and musculoskeletal indications. However, only few studies have investigated the robustness of such systems to changes in the sensor attachment and no consensus for suitable sensor positions exists in the research community. Specifically for unsupervised real-world measurements, understanding how the reliability of the monitoring system changes when the sensor is attached differently is from high importance. In these scenarios, placement variations are expected because of user error or personal preferences. In this manuscript, we present the largest study to date comparing different sensor positions and attachments. We recorded 9000 strides with motion-capture reference from 14 healthy participants with six synchronized sensors attached at each foot. Spatial gait parameters were calculated using a double-integration method and compared to the reference system. The results indicate that relevant differences in the accuracy of the stride length exists between the sensor positions. While the average error over multiple strides is comparable, single stride errors and variability parameters differ greatly. We further present a physics model and an analysis of the raw sensor data to understand the origin of the observed differences. This analysis indicates that a variety of attachment parameters can influence the systems’ performance. While this is only the starting point to understand and mitigate these types of errors, we conclude that sensor systems and algorithms must be reevaluated when the sensor position or attachment changes.

Foot Trajectory Features in Gait of Parkinson’s Disease Patients

Parkinson’s disease (PD) is a progressive neurological disorder characterized by movement disorders, such as gait instability. This study investigated whether certain spatial features of foot trajectory are characteristic of patients with PD. The foot trajectory of patients with mild and advanced PD in on-state and healthy older and young individuals was estimated from acceleration and angular velocity measured by inertial measurement units placed on the subject’s shanks, just above the ankles. We selected six spatial variables in the foot trajectory: forward and vertical displacements from heel strike to toe-off, maximum clearance, and change in supporting leg (F1 to F3 and V1 to V3, respectively). Healthy young individuals had the greatest F2 and F3 values, followed by healthy older individuals, and then mild PD patients. Conversely, the vertical displacements of mild PD patients were larger than the healthy older individuals. Still, those of healthy older individuals were smaller than the healthy young individuals except for V3. All six displacements of the advanced PD patients were smaller than the mild PD patients. To investigate features in foot trajectories in detail, a principal components analysis and soft-margin kernel support vector machine was used in machine learning. The accuracy in distinguishing between mild PD patients and healthy older individuals and between mild and advanced PD patients was 96.3 and 84.2%, respectively. The vertical and forward displacements in the foot trajectory was the main contributor. These results reveal that large vertical displacements and small forward ones characterize mild and advanced PD patients, respectively.

Co-evolution of machine learning and digital technologies to improve monitoring of Parkinson's disease motor symptoms

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor impairments such as tremor, bradykinesia, dyskinesia, and gait abnormalities. Current protocols assess PD symptoms during clinic visits and can be subjective. Patient diaries can help clinicians evaluate at-home symptoms, but can be incomplete or inaccurate. Therefore, researchers have developed in-home automated methods to monitor PD symptoms to enable data-driven PD diagnosis and management. We queried the US National Library of Medicine PubMed database to analyze the progression of the technologies and computational/machine learning methods used to monitor common motor PD symptoms. A sub-set of roughly 12,000 papers was reviewed that best characterized the machine learning and technology timelines that manifested from reviewing the literature. The technology used to monitor PD motor symptoms has advanced significantly in the past five decades. Early monitoring began with in-lab devices such as needle-based EMG, transitioned to in-lab accelerometers/gyroscopes, then to wearable accelerometers/gyroscopes, and finally to phone and mobile & web application-based in-home monitoring. Significant progress has also been made with respect to the use of machine learning algorithms to classify PD patients. Using data from different devices (e.g., video cameras, phone-based accelerometers), researchers have designed neural network and non-neural network-based machine learning algorithms to categorize PD patients across tremor, gait, bradykinesia, and dyskinesia. The five-decade co-evolution of technology and computational techniques used to monitor PD motor symptoms has driven significant progress that is enabling the shift from in-lab/clinic to in-home monitoring of PD symptoms.

Leveraging the Potential of Digital Technology for Better Individualized Treatment of Parkinson's Disease

Recent years have witnessed a strongly increasing interest in digital technology within medicine (sensor devices, specific smartphone apps) and specifically also neurology. Quantitative measures derived from digital technology could provide Digital Biomarkers (DMs) enabling a quantitative and continuous monitoring of disease symptoms, also outside clinics. This includes the possibility to continuously and sensitively monitor the response to treatment, hence opening the opportunity to adapt medication pathways quickly. In addition, DMs may in the future allow early diagnosis, stratification of patient subgroups and prediction of clinical outcomes. Thus, DMs could complement or in certain cases even replace classical examiner-based outcome measures and molecular biomarkers measured in cerebral spinal fluid, blood, urine, saliva, or other body liquids. Altogether, DMs could play a prominent role in the emerging field of precision medicine. However, realizing this vision requires dedicated research. First, advanced data analytical methods need to be developed and applied, which extract candidate DMs from raw signals. Second, these candidate DMs need to be validated by (a) showing their correlation to established clinical outcome measures, and (b) demonstrating their diagnostic and/or prognostic value compared to established biomarkers. These points again require the use of advanced data analytical methods, including machine learning. In addition, the arising ethical, legal and social questions associated with the collection and processing of sensitive patient data and the use of machine learning methods to analyze these data for better individualized treatment of the disease, must be considered thoroughly. Using Parkinson's Disease (PD) as a prime example of a complex multifactorial disorder, the purpose of this article is to critically review the current state of research regarding the use of DMs, discuss open challenges and highlight emerging new directions.

[Relevance of COMT inhibitors in the treatment of motor fluctuations]

Catechol O‑methyltransferase (COMT) inhibitors have been established in the treatment of Parkinson's disease for more than 20 years. They are considered the medication of choice for treating motor fluctuations. The available COMT inhibitors, entacapone, opicapone and tolcapone, differ pharmacokinetically in terms of their half-lives with implications for the dose frequency, in their indication requirements and in their spectrum of side effects, including diarrhea and yellow discoloration of urine. Many patients with motor fluctuations are currently not treated with COMT inhibitors and are, therefore, unlikely to receive individually optimized drug treatment. This manuscript summarizes the results of a working group including several Parkinson's disease experts, in which the value of COMT inhibitors was critically discussed.

Validation of a Sensor-Based Gait Analysis System with a Gold-Standard Motion Capture System in Patients with Parkinson's Disease

Digital technologies provide the opportunity to analyze gait patterns in patients with Parkinson’s Disease using wearable sensors in clinical settings and a home environment. Confirming the technical validity of inertial sensors with a 3D motion capture system is a necessary step for the clinical application of sensor-based gait analysis. Therefore, the objective of this study was to compare gait parameters measured by a mobile sensor-based gait analysis system and a motion capture system as the gold standard. Gait parameters of 37 patients were compared between both systems after performing a standardized 5 × 10 m walking test by reliability analysis using intra-class correlation and Bland–Altman plots. Additionally, gait parameters of an age-matched healthy control group (n = 14) were compared to the Parkinson cohort. Gait parameters representing bradykinesia and short steps showed excellent reliability (ICC > 0.96). Shuffling gait parameters reached ICC > 0.82. In a stridewise synchronization, no differences were observed for gait speed, stride length, stride time, relative stance and swing time (p > 0.05). In contrast, heel strike, toe off and toe clearance significantly differed between both systems (p < 0.01). Both gait analysis systems distinguish Parkinson patients from controls. Our results indicate that wearable sensors generate valid gait parameters compared to the motion capture system and can consequently be used for clinically relevant gait recordings in flexible environments.

A pathophysiological model of gait captures the details of the impairment of pace/rhythm, variability and asymmetry in Parkinsonian patients at distinct stages of the disease

Locomotion in people with Parkinson' disease (pwPD) worsens with the progression of disease, affecting independence and quality of life. At present, clinical practice guidelines recommend a basic evaluation of gait, even though the variables (gait speed, cadence, step length) may not be satisfactory for assessing the evolution of locomotion over the course of the disease. Collecting variables into factors of a conceptual model enhances the clinical assessment of disease severity. Our aim is to evaluate if factors highlight gait differences between pwPD and healthy subjects (HS) and do it at earlier stages of disease compared to single variables. Gait characteristics of 298 pwPD and 84 HS able to walk without assistance were assessed using a baropodometric walkway (GAITRite®). According to the structure of a model previously validated in pwPD, eight spatiotemporal variables were grouped in three factors: pace/rhythm, variability and asymmetry. The model, created from the combination of three factor scores, proved to outperform the single variables or the factors in discriminating pwPD from HS. When considering the pwPD split into the different Hoehn and Yahr (H&Y) stages, the spatiotemporal variables, factor scores and the model showed that multiple impairments of gait appear at H&Y stage 2.5, with the greatest difference from HS at stage 4. A contrasting behavior was found for the asymmetry variables and factor, which showed differences from the HS already in the early stages of PD. Our findings support the use of factor scores and of the model with respect to the single variables in gait staging in PD.

Assessment of gait and balance impairment in people with spinocerebellar ataxia using wearable sensors

OBJECTIVE

To explore the use of wearable sensors for objective measurement of motor impairment in spinocerebellar ataxia (SCA) patients during clinical assessments of gait and balance.

METHODS

In total, 14 patients with genetically confirmed SCA (mean age 61.6 ± 8.6 years) and 4 healthy controls (mean age 49.0 ± 16.4 years) were recruited through the Massachusetts General Hospital (MGH) Ataxia Center. Participants donned seven inertial sensors while performing two independent trials of gait and balance assessments from the Scale for the Assessment and Rating of Ataxia (SARA) and Brief Ataxia Rating Scale (BARS2). Univariate analysis was used to identify sensor-derived metrics from wearable sensors that discriminate motor function between the SCA and control groups. Multivariate linear regression models were used to estimate the subjective in-person SARA/BARS2 ratings. Spearman correlation coefficients were used to evaluate the performance of the model.

RESULTS

Stride length variability, stride duration, cadence, stance phase, pelvis sway, and turn duration were different between SCA and controls (p < 0.05). Similarly, sway and sway velocity of the ankle, hip, and center of mass differentiated SCA and controls (p < 0.05). Using these features, linear regression models showed moderate-to-strong correlation with clinical scores from the in-person rater during SARA assessments of gait (r = 0.73, p = 0.003) and stance (r = 0.90, p < 0.001) and the BARS2 gait assessment (r = 0.74, p = 0.003).

CONCLUSION

This study demonstrates that sensor-derived metrics can potentially be used to estimate the level of motor impairment in patient with SCA quickly and objectively. Thus, digital biomarkers from wearable sensors have the potential to be an integral tool for SCA clinical trials and care.

Detection of Unsupervised Standardized Gait Tests From Real-World Inertial Sensor Data in Parkinson's Disease

Gait tests as part of home monitoring study protocols for patients with movement disorders may provide valuable standardized anchor-points for real-world gait analysis using inertial measurement units (IMUs). However, analyzing unsupervised gait tests relies on reliable test annotations by the patients requiring a potentially error-prone interaction with the recording system. To overcome this limitation, this work presents a novel algorithmic pipeline for the automated detection of unsupervised standardized gait tests from continuous real-world IMU data. In a study with twelve Parkinson's disease patients, we recorded real-world gait data over two weeks using foot-worn IMUs. During continuous daily recordings, the participants performed series of three consecutive 4×10 -Meters-Walking-Tests ( 4×10 MWTs) at different walking speeds, besides their usual daily-living activities. The algorithm first detected these gait test series using a gait sequence detection algorithm, a peak enhancement pipeline, and subsequence Dynamic Time Warping and then decomposed them into single 4×10 MWTs based on the walking speed. In the evaluation with 419 available gait test series, the detection reached an F1-score of 88.9% and the decomposition an F1-score of 94.0%. A concurrent validity evaluation revealed very good agreement between spatio-temporal gait parameters derived from manually labelled and automatically detected 4×10 MWTs. Our algorithm allows to remove the burden of system interaction from the patients and reduces the time for manual data annotation for researchers. The study contributes to an improved automated processing of real-world IMU gait data and enables a simple integration of standardized tests into continuous long-term recordings. This will help to bridge the gap between supervised and unsupervised gait assessment.

The effect of levodopa on bilateral coordination and gait asymmetry in Parkinson's disease using inertial sensor

This study aimed to evaluate the effect of levodopa on the phase coordination index (PCI) and gait asymmetry (GA) of patients with Parkinson's disease (PD) and to investigate correlations between the severity of motor symptoms and gait parameters measured using an inertial sensor. Twenty-six patients with mild-to-moderate-stage PD who were taking levodopa participated in this study. The Unified Parkinson's Disease Rating Scale part III (UPDRS III) was used to assess the severity of motor impairment. The Postural Instability and Gait Difficulty (PIGD) subscore was calculated from UPDRS III. Patients were assessed while walking a 20-m corridor in both "OFF" and "ON" levodopa medication states, and gait analysis was performed using inertial sensors. We investigated the changes in gait parameters after taking levodopa and the correlations between UPDRS III, PIGD, and gait parameters. There was a significant improvement in PCI after taking levodopa. No significant effect of levodopa on GA was found. In "OFF" state, PCI and GA were not correlated with UPDRS III and PIGD. However, in "ON" state, PCI was the only gait parameter correlating with UPDRS III, and it was also highly correlated with PIGD compared to other gait parameters. Significant improvement in bilateral-phase coordination was identified in patients with PD after taking levodopa, without significant change in gait symmetricity. Considering the high correlation with UDPRS III and PIGD in "ON" states, PCI may be a useful and quantitative parameter to measure the severity of motor symptoms in PD patients who are on medication.

Simple Smartphone-Based Assessment of Gait Characteristics in Parkinson Disease: Validation Study

Background

Parkinson disease (PD) is a common movement disorder. Patients with PD have multiple gait impairments that result in an increased risk of falls and diminished quality of life. Therefore, gait measurement is important for the management of PD.

Objective

We previously developed a smartphone-based dual-task gait assessment that was validated in healthy adults. The aim of this study was to test the validity of this gait assessment in people with PD, and to examine the association between app-derived gait metrics and the clinical and functional characteristics of PD.

Methods

Fifty-two participants with clinically diagnosed PD completed assessments of walking, Movement Disorder Society Unified Parkinson Disease Rating Scale III (UPDRS III), Montreal Cognitive Assessment (MoCA), Hamilton Anxiety (HAM-A), and Hamilton Depression (HAM-D) rating scale tests. Participants followed multimedia instructions provided by the app to complete two 20-meter trials each of walking normally (single task) and walking while performing a serial subtraction dual task (dual task). Gait data were simultaneously collected with the app and gold-standard wearable motion sensors. Stride times and stride time variability were derived from the acceleration and angular velocity signal acquired from the internal motion sensor of the phone and from the wearable sensor system.

Results

High correlations were observed between the stride time and stride time variability derived from the app and from the gold-standard system (r=0.98-0.99, P<.001), revealing excellent validity of the app-based gait assessment in PD. Compared with those from the single-task condition, the stride time (F_1,103=14.1, P<.001) and stride time variability (F_1,103=6.8, P=.008) in the dual-task condition were significantly greater. Participants who walked with greater stride time variability exhibited a greater UPDRS III total score (single task: β=.39, P<.001; dual task: β=.37, P=.01), HAM-A (single-task: β=.49, P=.007; dual-task: β=.48, P=.009), and HAM-D (single task: β=.44, P=.01; dual task: β=.49, P=.009). Moreover, those with greater dual-task stride time variability (β=.48, P=.001) or dual-task cost of stride time variability (β=.44, P=.004) exhibited lower MoCA scores.

Conclusions

A smartphone-based gait assessment can be used to provide meaningful metrics of single- and dual-task gait that are associated with disease severity and functional outcomes in individuals with PD.

Estimation of stride-by-stride spatial gait parameters using inertial measurement unit attached to the shank with inverted pendulum model

Inertial measurement unit (IMU)-based gait analysis systems have become popular in clinical environments because of their low cost and quantitative measurement capability. When a shank is selected as the IMU mounting position, an inverted pendulum model (IPM) can accurately estimate its spatial gait parameters. However, the stride-by-stride estimation of gait parameters using one IMU on each shank and the IPMs has not been validated. This study validated a spatial gait parameter estimation method using a shank-based IMU system. Spatial parameters were estimated via the double integration of the linear acceleration transformed by the IMU orientation information. To reduce the integral drift error, an IPM, applied with a linear error model, was introduced at the mid-stance to estimate the update velocity. the gait data of 16 healthy participants that walked normally and slowly were used. The results were validated by comparison with those extracted from an optical motion-capture system; the results showed strong correlation (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$r>0.9$$\end{document}r>0.9) and good agreement with the gait metrics (stride length, stride velocity, and shank vertical displacement). In addition, the biases of the stride length and stride velocity extracted using the motion capture system were smaller in the IPM than those in the previous method using the zero-velocity-update. The error variabilities of the gait metrics were smaller in the IPM than those in the previous method. These results indicated that the reconstructed shank trajectory achieved a greater accuracy and precision than that of previous methods. This was attributed to the IPM, which demonstrates that shank-based IMU systems with IPMs can accurately reflect many spatial gait parameters including stride velocity.

Sharing Practices for Datasets Related to Accessibility and Aging

Datasets sourced from people with disabilities and older adults play an important role in innovation, benchmarking, and mitigating bias for both assistive and inclusive AI-infused applications. However, they are scarce. We conduct a systematic review of 137 accessibility datasets manually located across different disciplines over the last 35 years. Our analysis highlights how researchers navigate tensions between benefits and risks in data collection and sharing. We uncover patterns in data collection purpose, terminology, sample size, data types, and data sharing practices across communities of focus. We conclude by critically reflecting on challenges and opportunities related to locating and sharing accessibility datasets calling for technical, legal, and institutional privacy frameworks that are more attuned to concerns from these communities.

Characterization of gait variability in multiple system atrophy and Parkinson's disease

BACKGROUND

Gait impairment is a pivotal feature of parkinsonian syndromes and increased gait variability is associated with postural instability and a higher risk of falls.

OBJECTIVES

We compared gait variability at different walking velocities between and within groups of patients with Parkinson-variant multiple system atrophy, idiopathic Parkinson's disease, and a control group of older adults.

METHODS

Gait metrics were recorded in 11 multiple system atrophy, 12 Parkinson's disease patients, and 18 controls using sensor-based gait analysis. Gait variability was analyzed for stride, swing and stance time, stride length and gait velocity. Values were compared between and within the groups at self-paced comfortable, fast and slow walking speed.

RESULTS

Multiple system atrophy patients displayed higher gait variability except for stride time at all velocities compared with controls, while Parkinson's patients did not. Compared with Parkinson's disease, multiple system atrophy patients displayed higher variability of swing time, stride length and gait velocity at comfortable speed and at slow speed for swing and stance time, stride length and gait velocity (all P < 0.05). Stride time variability was significantly higher in slow compared to comfortable walking in patients with multiple system atrophy (P = 0.014). Variability parameters significantly correlated with the postural instability/gait difficulty subscore in both disease groups. Conversely, significant correlations between variability parameters and MDS-UPDRS III score was observed only for multiple system atrophy patients.

CONCLUSION

This analysis suggests that gait variability parameters reflect the major axial impairment and postural instability displayed by multiple system atrophy patients compared with Parkinson's disease patients and controls.

Understanding the Neurophysiological and Molecular Mechanisms of Exercise-Induced Neuroplasticity in Cortical and Descending Motor Pathways: Where Do We Stand?

Exercise is a promising, cost-effective intervention to augment successful aging and neurorehabilitation. Decline of gray and white matter accompanies physiological aging and contributes to motor deficits in older adults. Exercise is believed to reduce atrophy within the motor system and induce neuroplasticity which, in turn, helps preserve motor function during aging and promote re-learning of motor skills, for example after stroke. To fully exploit the benefits of exercise, it is crucial to gain a greater understanding of the neurophysiological and molecular mechanisms underlying exercise-induced brain changes that prime neuroplasticity and thus contribute to postponing, slowing, and ameliorating age- and disease-related impairments in motor function. This knowledge will allow us to develop more effective, personalized exercise protocols that meet individual needs, thereby increasing the utility of exercise strategies in clinical and non-clinical settings. Here, we review findings from studies that investigated neurophysiological and molecular changes associated with acute or long-term exercise in healthy, young adults and in healthy, postmenopausal women.

Parkinson's Disease Diagnosis and Severity Assessment Using Ground Reaction Forces and Neural Networks

Gait analysis plays a key role in the diagnosis of Parkinson’s Disease (PD), as patients generally exhibit abnormal gait patterns compared to healthy controls. Current diagnosis and severity assessment procedures entail manual visual examinations of motor tasks, speech, and handwriting, among numerous other tests, which can vary between clinicians based on their expertise and visual observation of gait tasks. Automating gait differentiation procedure can serve as a useful tool in early diagnosis and severity assessment of PD and limits the data collection to solely walking gait. In this research, a holistic, non-intrusive method is proposed to diagnose and assess PD severity in its early and moderate stages by using only Vertical Ground Reaction Force (VGRF). From the VGRF data, gait features are extracted and selected to use as training features for the Artificial Neural Network (ANN) model to diagnose PD using cross validation. If the diagnosis is positive, another ANN model will predict their Hoehn and Yahr (H&Y) score to assess their PD severity using the same VGRF data. PD Diagnosis is achieved with a high accuracy of 97.4% using simple network architecture. Additionally, the results indicate a better performance compared to other complex machine learning models that have been researched previously. Severity Assessment is also performed on the H&Y scale with 87.1% accuracy. The results of this study show that it is plausible to use only VGRF data in diagnosing and assessing early stage Parkinson’s Disease, helping patients manage the symptoms earlier and giving them a better quality of life.

Automatic clinical gait test detection from inertial sensor data

The analysis of gait data is one approach to support clinicians with the diagnosis and therapy of diseases, for example Parkinson's disease (PD). Traditionally, gait data of standardized tests in the clinic is analyzed, ensuring a predefined setting. In recent years, long-term home-based gait analysis has been used to acquire a more representative picture of the patient's disease status. Data is recorded in a less artificial setting and therefore allows a more realistic perception of the disease progression. However, fully unsupervised gait data without additional context information impedes interpretation. As an intermediate solution, performance of gait tests at home was introduced. Integration of instrumented gait test requires annotations of those tests for their identification and further processing. To overcome these limitations, we developed an algorithm for automatic detection of standardized gait tests from continuous sensor data with the goal of making manual annotations obsolete. The method is based on dynamic time warping, which compares an input signal with a predefined template and quantifies similarity between both. Different templates were compared and an optimized template was created. The classification scored a F1-measure of 86.7% for evaluation on a data set acquired in a clinical setting. We believe that this approach can be transferred to home-monitoring systems and will facilitate a more efficient and automated gait analysis.

Clinical Relevance of Standardized Mobile Gait Tests. Reliability Analysis Between Gait Recordings at Hospital and Home in Parkinson's Disease: A Pilot Study

BACKGROUND

Gait impairments in Parkinson's disease (PD) are quantified using inertial sensors under standardized test settings in the hospital. Recent studies focused on the assessment of free-living gait in PD. However, the clinical relevance of standardized gait tests recorded at the patient's home is unclear.

OBJECTIVE

To evaluate the reliability of supervised, standardized sensor-based gait outcomes at home compared to the hospital.

METHODS

Patients with PD (n = 20) were rated by a trained investigator using the Unified Parkinson Disease Rating Scale (UPDRS-III). Gait tests included a standardized 4×10 m walk test and the Timed Up and Go Test (TUG). Tests were performed in the hospital (HOSPITAL) and at patients' home (HOME), and controlled for investigator, time of the day, and medication. Statistics included reliability analysis using Intra-Class correlations and Bland-Altman plots.

RESULTS

UPDRS-III and TUG were comparable between HOSPITAL and HOME. PD patients' gait at HOME was slower (gait velocity Δ= -0.07±0.11 m/s, -6.1%), strides were shorter (stride length Δ= -9.2±9.4 cm; -7.3%), and shuffling of gait was more present (maximum toe-clearance Δ= -0.7±2.5 cm; -8.8%). Particularly, narrow walkways (<85 cm) resulted in a significant reduction of gait velocity at home. Reliability analysis (HOSPITAL vs. HOME) revealed excellent ICC coefficients for UPDRS-III (0.950, p < 0.000) and gait parameters (e.g., stride length: 0.898, p < 0.000; gait velocity: 0.914, p < 0.000; stance time: 0.922, p < 0.000; stride time: 0.907, p < 0.000).

CONCLUSION

This pilot study underlined the clinical relevance of gait parameters by showing excellent reliability for supervised, standardized gait tests at HOSPITAL and HOME, even though gait parameters were different between test conditions.

Parkinson's disease detection from 20-step walking tests using inertial sensors of a smartphone: Machine learning approach based on an observational case-control study

Parkinson's disease (PD) is a neurodegenerative disease inducing dystrophy of the motor system. Automatic movement analysis systems have potential in improving patient care by enabling personalized and more accurate adjust of treatment. These systems utilize machine learning to classify the movement properties based on the features derived from the signals. Smartphones can provide an inexpensive measurement platform with their built-in sensors for movement assessment. This study compared three feature selection and nine classification methods for identifying PD patients from control subjects based on accelerometer and gyroscope signals measured with a smartphone during a 20-step walking test. Minimum Redundancy Maximum Relevance (mRMR) and sequential feature selection with both forward (SFS) and backward (SBS) propagation directions were used in this study. The number of selected features was narrowed down from 201 to 4-15 features by applying SFS and mRMR methods. From the methods compared in this study, the highest accuracy for individual steps was achieved with SFS (7 features) and Naive Bayes classifier (accuracy 75.3%), and the second highest accuracy with SFS (4 features) and k Nearest neighbours (accuracy 75.1%). Leave-one-subject-out cross-validation was used in the analysis. For the overall classification of each subject, which was based on the majority vote of the classified steps, k Nearest Neighbors provided the most accurate result with an accuracy of 84.5% and an error rate of 15.5%. This study shows the differences in feature selection methods and classifiers and provides generalizations for optimizing methodologies for smartphone-based monitoring of PD patients. The results are promising for further developing the analysis system for longer measurements carried out in free-living conditions.

Portable accelerometers for the evaluation of spatio-temporal gait parameters in people with Parkinson's disease: an integrative review

PURPOSE

The progression of Parkinson's disease causes an increase in motor dysfunctions, which makes it necessary to evaluate and monitor these changes. This integrative review aimed to gather studies - without any language restrictions - on the use, advantages and disadvantages of portable accelerometers for the evaluation of spatio-temporal gait parameters in people with Parkinson's disease published between 2014 and 2019.

METHODS

Articles were selected from the PubMed, Web of Science and Science Direct databases by combining descriptors from the Health Sciences Descriptors (DeCS) and Medical Subject Headings (MeSH) - "accelerometry", "accelerometer", "ActiGraph", "gait", "gait analysis", "gait rehabilitation", "walking inertial sensors", "Parkinson disease", "Parkinson" and "Parkinson's disease" - using OR and AND. The adapted Critical Appraisal Skill Program was used to analyze the methodological quality.

RESULTS

All the studies used portable wearable and wireless triaxial accelerometers. Among all types of accelerometers discussed, commercial wearable devices not based on smartphones and prototypes of wearable devices based and not based on smartphones can be pointed out. There was no standardization for the protocols of use, but the sensors were more often attached to the lower back (L3/L4/L5 vertebrae). The advantages included lower cost, possibility of use in outdoor environments and less complexity of data reading for non-specialized users. However, they still seem to show reduced precision and accuracy.

CONCLUSIONS

Due to the still insufficient number of articles published on the subject, we consider the need for further research, which should detail protocols of evaluation, advantages and disadvantages in stages of disease.

Gait variability as digital biomarker of disease severity in Huntington's disease

BACKGROUND

Impaired gait plays an important role for quality of life in patients with Huntington's disease (HD). Measuring objective gait parameters in HD might provide an unbiased assessment of motor deficits in order to determine potential beneficial effects of future treatments.

OBJECTIVE

To objectively identify characteristic features of gait in HD patients using sensor-based gait analysis. Particularly, gait parameters were correlated to the Unified Huntington's Disease Rating Scale, total motor score (TMS), and total functional capacity (TFC).

METHODS

Patients with manifest HD at two German sites (n = 43) were included and clinically assessed during their annual ENROLL-HD visit. In addition, patients with HD and a cohort of age- and gender-matched controls performed a defined gait test (4 × 10 m walk). Gait patterns were recorded by inertial sensors attached to both shoes. Machine learning algorithms were applied to calculate spatio-temporal gait parameters and gait variability expressed as coefficient of variance (CV).

RESULTS

Stride length (- 15%) and gait velocity (- 19%) were reduced, while stride (+ 7%) and stance time (+ 2%) were increased in patients with HD. However, parameters reflecting gait variability were substantially altered in HD patients (+ 17% stride length CV up to + 41% stride time CV with largest effect size) and showed strong correlations to TMS and TFC (0.416 ≤ r_Sp ≤ 0.690). Objective gait variability parameters correlated with disease stage based upon TFC.

CONCLUSIONS

Sensor-based gait variability parameters were identified as clinically most relevant digital biomarker for gait impairment in HD. Altered gait variability represents characteristic irregularity of gait in HD and reflects disease severity.

Accelerometry-Based Digital Gait Characteristics for Classification of Parkinson's Disease: What Counts?

Objective: Gait may be a useful biomarker that can be objectively measured with wearable technology to classify Parkinson's disease (PD). This study aims to: (i) comprehensively quantify a battery of commonly utilized gait digital characteristics (spatiotemporal and signal-based), and (ii) identify the best discriminative characteristics for the optimal classification of PD. Methods: Six partial least square discriminant analysis (PLS-DA) models were trained on subsets of 210 characteristics measured in 142 subjects (81 people with PD, 61 controls (CL)). Results: Models accuracy ranged between 70.42-88.73% (AUC: 78.4-94.5%) with a sensitivity of 72.84-90.12% and a specificity of 60.3-86.89%. Signal-based digital gait characteristics independently gave 87.32% accuracy. The most influential characteristics in the classification models were related to root mean square values, power spectral density, step velocity and length, gait regularity and age. Conclusions: This study highlights the importance of signal-based gait characteristics in the development of tools to help classify PD in the early stages of the disease.

Objective sensor-based gait measures reflect motor impairment in multiple sclerosis patients: Reliability and clinical validation of a wearable sensor device

BACKGROUND

Gait deficits are common in multiple sclerosis (MS) and contribute to disability but may not be easily detected in the early stages of the disease.

OBJECTIVES

We investigated whether sensor-based gait analysis is able to detect gait impairments in patients with MS (PwMS).

METHODS

A foot-worn sensor-based gait analysis system was used in 102 PwMS and 22 healthy controls (HC) that were asked to perform the 25-foot walking test (25FWT) two times in a self-selected speed (25FWT_pref), followed by two times in a speed as fast as possible (25FWT_fast). The Multiple Sclerosis Walking Scale (MSWS-12) was used as a subjective measure of patient mobility. Patients were divided into EDSS and functional system subgroups.

RESULTS

Datasets between two consecutive measurements (test-retest-reliability) were highly correlated in all analysed mean gait parameters (e.g. 25FWT_fast: stride length r = 0.955, gait speed r = 0.969) Subgroup analysis between HC and PwMS with lower (EDSS≤3.5) and higher (EDSS 4.0-7.0) disability showed significant differences in mean stride length, gait speed, toe off angle, stance time and swing time (e.g. stride length of EDSS subgroups 25FWT_fast p ≤ 0.001, 25FWT_pref p = 0.003). The differences between EDSS subgroups were more pronounced in fast than in self-selected gait speed (e.g. stride length 25FWT_fast 33.6 cm vs. 25FWT_pref 16.3 cm). Stride length (25FWT_fast) highly correlated to EDSS (r=-0.583) and MSWS-12 (r=-0.668). We observed significant differences between HC and PwMS with (FS 0-1) and without (FS≥2) pyramidal or cerebellar disability (e.g. gait speed of FS subgroups p ≤ 0.001).

CONCLUSION

Sensor-based gait analysis objectively supports the clinical assessment of gait abnormalities even in the lower stages of MS, especially when walking with fast speed. Stride length and gait speed where identified as the most clinically relevant gait measures. Thus, it may be used to support the assessment of PwMS with gait impairment in the future, e.g. for more objective classification of disability. Its role in home-monitoring scenarios need to be evaluated in further studies.

Assessment of gait parameters and physical function in patients with advanced cancer participating in a 12-week exercise and nutrition programme: A controlled clinical trial

OBJECTIVE

Gait is a sensitive marker for functional declines commonly seen in patients treated for advanced cancer. We tested the effect of a combined exercise and nutrition programme on gait parameters of advanced-stage cancer patients using a novel wearable gait analysis system.

METHODS

Eighty patients were allocated to a control group with nutritional support or to an intervention group additionally receiving whole-body electromyostimulation (WB-EMS) training (2×/week). At baseline and after 12 weeks, physical function was assessed by a biosensor-based gait analysis during a six-minute walk test, a 30-s sit-to-stand test, a hand grip strength test, the Karnofsky Index and EORTC QLQ-C30 questionnaire. Body composition was measured by bioelectrical impedance analysis and inflammation by blood analysis.

RESULTS

Final analysis included 41 patients (56.1% male; 60.0 ± 13.0 years). After 12 weeks, the WB-EMS group showed higher stride length, gait velocity (p < .05), six-minute walking distance (p < .01), bodyweight and skeletal muscle mass, and emotional functioning (p < .05) compared with controls. Correlations between changes in gait and in body composition, physical function and inflammation were detected.

CONCLUSION

Whole-body electromyostimulation combined with nutrition may help to improve gait and functional status of cancer patients. Sensor-based mobile gait analysis objectively reflects patients' physical status and could support treatment decisions.

Comparison of Walking Protocols and Gait Assessment Systems for Machine Learning-Based Classification of Parkinson's Disease

Early diagnosis of Parkinson's diseases (PD) is challenging; applying machine learning (ML) models to gait characteristics may support the classification process. Comparing performance of ML models used in various studies can be problematic due to different walking protocols and gait assessment systems. The objective of this study was to compare the impact of walking protocols and gait assessment systems on the performance of a support vector machine (SVM) and random forest (RF) for classification of PD. 93 PD and 103 controls performed two walking protocols at their normal pace: (i) four times along a 10 m walkway (intermittent walk-IW), (ii) walking for 2 minutes on a 25 m oval circuit (continuous walk-CW). 14 gait characteristics were extracted from two different systems (an instrumented walkway-GAITRite; and an accelerometer attached at the lower back-Axivity). SVM and RF were trained on normalized data (accounting for step velocity, gender, age and BMI) and evaluated using 10-fold cross validation with area under the curve (AUC). Overall performance was higher for both systems during CW compared to IW. SVM performed better than RF. With SVM, during CW Axivity significantly outperformed GAITRite (AUC: 87.83 ± 7.81% vs. 80.49 ± 9.85%); during IW systems performed similarly. These findings suggest that choice of testing protocol and sensing system may have a direct impact on ML PD classification results and highlight the need for standardization for wide scale implementation.

Selecting Clinically Relevant Gait Characteristics for Classification of Early Parkinson's Disease: A Comprehensive Machine Learning Approach

Parkinson's disease (PD) is the second most common neurodegenerative disease; gait impairments are typical and are associated with increased fall risk and poor quality of life. Gait is potentially a useful biomarker to help discriminate PD at an early stage, however the optimal characteristics and combination are unclear. In this study, we used machine learning (ML) techniques to determine the optimal combination of gait characteristics to discriminate people with PD and healthy controls (HC). 303 participants (119 PD, 184 HC) walked continuously around a circuit for 2-minutes at a self-paced walk. Gait was quantified using an instrumented mat (GAITRite) from which 16 gait characteristics were derived and assessed. Gait characteristics were selected using different ML approaches to determine the optimal method (random forest with information gain and recursive features elimination (RFE) technique with support vector machine (SVM) and logistic regression). Five clinical gait characteristics were identified with RFE-SVM (mean step velocity, mean step length, step length variability, mean step width, and step width variability) that accurately classified PD. Model accuracy for classification of early PD ranged between 73-97% with 63-100% sensitivity and 79-94% specificity. In conclusion, we identified a subset of gait characteristics for accurate early classification of PD. These findings pave the way for a better understanding of the utility of ML techniques to support informed clinical decision-making.

A modular, extensible approach to massive ecologically valid behavioral data

We explore here the application of modern computer hardware and software to the collection and analysis of behavioral data. We discuss the issues of ecological validity, storage and processing, data permanence, automation, validity, and algorithmic determinism. Taking the modern landscape into account, we demonstrate several varying projects we have recently undertaken as proofs of concept of the viability and utility of this approach. In particular, we describe four research projects, which involve work on child-directed speech; the application of automatic methods to clinical populations, including children with hearing loss; quality control and the assessment of validity; and the sharing of data in a public database. We conclude by pointing out how the methodology described here can be extended to a wide variety of interdisciplinary and detailed projects that are likely to lead to better science and improved outcomes for populations served by the behavioral, social, and health sciences.

Machine learning algorithms can classify outdoor terrain types during running using accelerometry data

BACKGROUND

Running is a popular physical activity that benefits health; however, running surface characteristics may influence loading impact and injury risk. Machine learning algorithms could automatically identify running surface from wearable motion sensors to quantify running exposures, and perhaps loading and injury risk for a runner.

RESEARCH QUESTION

(1) How accurately can machine learning algorithms identify surface type from three-dimensional accelerometer sensors? (2) Does the sensor count (single or two-sensor setup) affect model accuracy?

METHODS

Twenty-nine healthy adults (23.3 ± 3.6 years, 1.8 ± 0.1 m, and 63.6 ± 8.5 kg) participated in this study. Participants ran on three different surfaces (concrete, synthetic, woodchip) while fit with two three-dimensional accelerometers (lower-back and right tibia). Summary features (n = 208) were extracted from the accelerometer signals. Feature-based Gradient Boosting (GB) and signal-based deep learning Convolutional Neural Network (CNN) models were developed. Models were trained on 90% of the data and tested on the remaining 10%. The process was repeated five times, with data randomly shuffled between train-test splits, to quantify model performance variability.

RESULTS

All models and configurations achieved greater than 90% average accuracy. The highest performing models were the two-sensor GB and tibia-sensor CNN (average accuracy of 97.0 ± 0.7 and 96.1 ± 2.6%, respectively).

SIGNIFICANCE

Machine learning algorithms trained on running data from a single- or dual-sensor accelerometer setup can accurately distinguish between surfaces types. Automatic identification of surfaces encountered during running activities could help runners and coaches better monitor training load, improve performance, and reduce injury rates.

[Wearables in the treatment of neurological diseases-where do we stand today?]

Fitness and lifestyle trackers raise the awareness for wearable sensors in medical applications for clinical trials and healthcare. Various functional impairments of patients with neurological diseases are an ideal target to generate wearable-derived and patient-centered parameters that have the potential to support prevention, prediction, diagnostic procedures and therapy monitoring during the clinical work-up; however, substantial differences between clinical grade wearables and fitness trackers have to be acknowledged. For the application in clinical trials or individualized patient care distinct technical and clinical validation trials have to be conducted. The different test environments under laboratory conditions during standardized tests or under unsupervised home monitoring conditions have to be included in the algorithmic processing of sensor raw data in order to enable a clinical decision support under real-life conditions. This article presents the general understanding of the technical application for the most relevant functional impairments in neurology. While wearables used for sleep assessment have already reached a high level of technological readiness due to the defined test environment (bed, sleep), other wearable applications, e.g. for gait and mobility during home monitoring require further research in order to transfer the technical capabilities into real-life patient care.

Artificial intelligence for assisting diagnostics and assessment of Parkinson's disease-A review

Artificial intelligence, specifically machine learning, has found numerous applications in computer-aided diagnostics, monitoring and management of neurodegenerative movement disorders of parkinsonian type. These tasks are not trivial due to high inter-subject variability and similarity of clinical presentations of different neurodegenerative disorders in the early stages. This paper aims to give a comprehensive, high-level overview of applications of artificial intelligence through machine learning algorithms in kinematic analysis of movement disorders, specifically Parkinson's disease (PD). We surveyed papers published between January 2007 and January 2019, within online databases, including PubMed and Science Direct, with a focus on the most recently published studies. The search encompassed papers dealing with the implementation of machine learning algorithms for diagnosis and assessment of PD using data describing motion of upper and lower extremities. This systematic review presents an overview of 48 relevant studies published in the abovementioned period, which investigate the use of artificial intelligence for diagnostics, therapy assessment and progress prediction in PD based on body kinematics. Different machine learning algorithms showed promising results, particularly for early PD diagnostics. The investigated publications demonstrated the potentials of collecting data from affordable and globally available devices. However, to fully exploit artificial intelligence technologies in the future, more widespread collaboration is advised among medical institutions, clinicians and researchers, to facilitate aligning of data collection protocols, sharing and merging of data sets.

Turning Analysis during Standardized Test Using On-Shoe Wearable Sensors in Parkinson's Disease

Mobile gait analysis systems using wearable sensors have the potential to analyze and monitor pathological gait in a finer scale than ever before. A closer look at gait in Parkinson’s disease (PD) reveals that turning has its own characteristics and requires its own analysis. The goal of this paper is to present a system with on-shoe wearable sensors in order to analyze the abnormalities of turning in a standardized gait test for PD. We investigated turning abnormalities in a large cohort of 108 PD patients and 42 age-matched controls. We quantified turning through several spatio-temporal parameters. Analysis of turn-derived parameters revealed differences of turn-related gait impairment in relation to different disease stages and motor impairment. Our findings confirm and extend the results from previous studies and show the applicability of our system in turning analysis. Our system can provide insight into the turning in PD and be used as a complement for physicians’ gait assessment and to monitor patients in their daily environment.

Development and clinical validation of inertial sensor-based gait-clustering methods in Parkinson's disease

BACKGROUND

Gait symptoms and balance impairment are characteristic indicators for the progression in Parkinson's disease (PD). Current gait assessments mostly focus on straight strides with assumed constant velocity, while acceleration/deceleration and turning strides are often ignored. This is either due to the set up of typical clinical assessments or technical limitations in capture volume. Wearable inertial measurement units are a promising and unobtrusive technology to overcome these limitations. Other gait phases such as initiation, termination, transitioning (between straight walking and turning) and turning might be relevant as well for the evaluation of gait and balance impairments in PD.

METHOD

In a cohort of 119 PD patients, we applied unsupervised algorithms to find different gait clusters which potentially include the clinically relevant information from distinct gait phases in the standardized 4x10 m gait test. To clinically validate our approach, we determined the discriminative power in each gait cluster to classify between impaired and unimpaired PD patients and compared it to baseline (analyzing all straight strides).

RESULTS

As a main result, analyzing only one of the gait clusters constant, non-constant or turning led in each case to a better classification performance in comparison to the baseline (increase of area under the curve (AUC) up to 19% relative to baseline). Furthermore, gait parameters (for turning, constant and non-constant gait) that best predict motor impairment in PD were identified.

CONCLUSIONS

We conclude that a more detailed analysis in terms of different gait clusters of standardized gait tests such as the 4x10 m walk may give more insights about the clinically relevant motor impairment in PD patients.

Development of a Strategy to Predict and Detect Falls Using Wearable Sensors

Falls are a prevalent problem in actual society. Some falls result in injuries and the cost associated with their treatment is high. This is a complex problem that requires several steps in order to be tackled. Firstly, it is crucial to develop strategies that recognize the locomotion mode, indicating the state of the subject in various situations. This article aims to develop a strategy capable of identifying normal gait, the pre-fall condition, and the fall situation, based on a wearable system (IMUs-based). This system was used to collect data from healthy subjects that mimicked falls. The strategy consists, essentially, in the construction and use of classifiers as tools for recognizing the locomotion modes. Two approaches were explored. Associative Skill Memories (ASMs) based classifier and a Convolutional Neural Network (CNN) classifier based on deep learning. Finally, these classifiers were compared, providing for a tool with a good accuracy in recognizing the locomotion modes. Results have shown that the accuracy of the classifiers was quite acceptable. The CNN presented the best results with 92.71% of accuracy considering the pre-fall step different from normal steps, and 100% when not considering.

The Diagnostic Scope of Sensor-Based Gait Analysis in Atypical Parkinsonism: Further Observations

Background: Differentiating idiopathic Parkinson's disease (IPD) from atypical Parkinsonian disorders (APD) is challenging, especially in early disease stages. Postural instability and gait difficulty (PIGD) are substantial motor impairments of IPD and APD. Clinical evidence implies that patients with APD have larger PIGD impairment than IPD patients. Sensor-based gait analysis as instrumented bedside test revealed more gait deficits in APD compared to IPD. However, the diagnostic value of instrumented bedside tests compared to clinical assessments in differentiating APD from IPD patients have not been evaluated so far.

Objective: The objectives were (a) to evaluate whether sensor-based gait parameters provide additional information to validated clinical scores in differentiating APD from matched IPD patients, and (b) to investigate if objective, instrumented gait assessments have comparable discriminative power to clinical scores.

Methods: In a previous study we have recorded instrumented gait parameters in patients with APD (Multiple System Atrophy and Progressive Supranuclear Palsy). Here, we compared gait parameters to those of retrospectively pairwise disease duration-, age-, and gender-matched IPD patients in order to address this new research questions. To this aim, the PIGD score was calculated as sum of the MDS-UPDRS-3-items “gait,” “postural stability,” “arising from chair,” and “posture.” Gait characteristics were evaluated in standardized gait tests using an instrumented, sensor-based gait analysis system. Machine learning algorithms were used to extract spatio-temporal gait parameters. Receiver Operating Characteristic analysis was performed in order to detect the discriminative power of the instrumented vs. the clinical bedside tests in differentiating IPD from APD.

Results: Sensor-based stride length, gait velocity, toe off angle, and parameters representing gait variability significantly differed between IPD and APD groups. ROC analysis revealed a high Area Under the Curve (AUC) for PIGD score (0.919), and UPDRS-3 (0.848). Particularly, the objective parameters stance time variability (0.841), swing time variability (0.834), stride time variability (0.821), and stride length variability (0.804) reached high AUC's as well.

Conclusions: PIGD symptoms showed high discriminative power in differentiating IPD from APD supporting gait disorders as substantial diagnostic target. Sensor-based gait variability parameters provide metric, objective added value, and serve as complementary outcomes supporting clinical diagnostics and long-term home-monitoring concepts.

Wearable sensors for Parkinson's disease: which data are worth collecting for training symptom detection models

Machine learning algorithms that use data streams captured from soft wearable sensors have the potential to automatically detect PD symptoms and inform clinicians about the progression of disease. However, these algorithms must be trained with annotated data from clinical experts who can recognize symptoms, and collecting such data are costly. Understanding how many sensors and how much labeled data are required is key to successfully deploying these models outside of the clinic. Here we recorded movement data using 6 flexible wearable sensors in 20 individuals with PD over the course of multiple clinical assessments conducted on 1 day and repeated 2 weeks later. Participants performed 13 common tasks, such as walking or typing, and a clinician rated the severity of symptoms (bradykinesia and tremor). We then trained convolutional neural networks and statistical ensembles to detect whether a segment of movement showed signs of bradykinesia or tremor based on data from tasks performed by other individuals. Our results show that a single wearable sensor on the back of the hand is sufficient for detecting bradykinesia and tremor in the upper extremities, whereas using sensors on both sides does not improve performance. Increasing the amount of training data by adding other individuals can lead to improved performance, but repeating assessments with the same individuals—even at different medication states—does not substantially improve detection across days. Our results suggest that PD symptoms can be detected during a variety of activities and are best modeled by a dataset incorporating many individuals.

Movement Speed Estimation Based on Foot Acceleration Patterns

Wearable sensors are important in today's athlete training ecosystems and also for the monitoring of therapeutic rehabilitation processes or even the diagnosis of diseases. In the future, wearables will be integrated directly into clothing and require dedicated, low-energy consuming algorithms that still maintain high accuracy. We developed a novel algorithm for the task of movement speed determination based on wearables that track only the acceleration of one foot. It consists of three algorithm blocks that perform step segmentation, step detection and speed estimation, all having linear computation complexity and able to work in real-time on state-of-the-art embedded microprocessors. Using a reference dataset collected from a motion capturing device for nine subjects and 795 steps in total, a parametric regression algorithm was trained and evaluated using a comprehensive leave-one-subject-out crossvalidation. It is able to estimate the movement speed with a mean relative error of 6.9 ± 5.5 %. Furthermore, we evaluated our approach on lightgate-based reference measurements using 12 subjects and different running movement styles. Here, our algorithm achieved a mean relative error of 16.5 ± 8.4 %. A final evaluation with realistic football-specific movements in a three-aside cage-based soccer game was done with a GPS-based reference measurement system, where the speed profile over a 30 minutes game of our method had a Pearson correlation of 0.85 to the GPS-based reference speed profile.