Predicting walking response to ankle exoskeletons using data-driven models.
Ontology highlight
ABSTRACT:
SUBMITTER: Rosenberg MC
PROVIDER: S-EPMC7653383 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BACKGROUND:Controllers for assistive robotic devices can be divided into two main categories: controllers using neural signals and controllers using mechanically intrinsic signals. Both approaches are prevalent in research devices, but a direct comparison between the two could provide insight into their relative advantages and disadvantages. We studied subjects walking with robotic ankle exoskeletons using two different control modes: dynamic gain proportional myoelectric control based on soleus muscle activity (neural signal), and timing-based mechanically intrinsic control based on gait events (mechanically intrinsic signal). We hypothesized that subjects would have different measures of metabolic work rate between the two controllers as we predicted subjects would use each controller in a unique manner due to one being dependent on muscle recruitment and the other not. METHODS:The two controllers had the same average actuation signal as we used the control signals from walking with the myoelectric controller to shape the mechanically intrinsic control signal. The difference being the myoelectric controller allowed step-to-step variation in the actuation signals controlled by the user's soleus muscle recruitment while the timing-based controller had the same actuation signal with each step regardless of muscle recruitment. RESULTS:We observed no statistically significant difference in metabolic work rate between the two controllers. Subjects walked with 11% less soleus activity during mid and late stance and significantly less peak soleus recruitment when using the timing-based controller than when using the myoelectric controller. While walking with the myoelectric controller, subjects walked with significantly higher average positive and negative total ankle power compared to walking with the timing-based controller. CONCLUSIONS:We interpret the reduced ankle power and muscle activity with the timing-based controller relative to the myoelectric controller to result from greater slacking effects. Subjects were able to be less engaged on a muscle level when using a controller driven by mechanically intrinsic signals than when using a controller driven by neural signals, but this had no affect on their metabolic work rate. These results suggest that the type of controller (neural vs. mechanical) is likely to affect how individuals use robotic exoskeletons for therapeutic rehabilitation or human performance augmentation.
| S-EPMC5970476 | biostudies-literature
Project description:Unpowered exoskeletons with springs in parallel to human plantar flexor muscle-tendons can reduce the metabolic cost of walking. We used ultrasound imaging to look 'under the skin' and measure how exoskeleton stiffness alters soleus muscle contractile dynamics and shapes the user's metabolic rate during walking. Eleven participants (4F, 7M; age: 27.7 ± 3.3 years) walked on a treadmill at 1.25 m s-1 and 0% grade with elastic ankle exoskeletons (rotational stiffness: 0-250 Nm rad-1) in one training and two testing days. Metabolic savings were maximized (4.2%) at a stiffness of 50 Nm rad-1. As exoskeleton stiffness increased, the soleus muscle operated at longer lengths and improved economy (force/activation) during early stance, but this benefit was offset by faster shortening velocity and poorer economy in late stance. Changes in soleus activation rate correlated with changes in users' metabolic rate (p = 0.038, R2 = 0.44), highlighting a crucial link between muscle neuromechanics and exoskeleton performance; perhaps informing future 'muscle-in-the loop' exoskeleton controllers designed to steer contractile dynamics toward more economical force production.
| S-EPMC7046782 | biostudies-literature
Project description:Ankle exoskeletons alter whole-body walking mechanics, energetics, and stability by altering center-of-mass (CoM) motion. Controlling the dynamics governing CoM motion is, therefore, critical for maintaining efficient and stable gait. However, how CoM dynamics change with ankle exoskeletons is unknown, and how to optimally model individual-specific CoM dynamics, especially in individuals with neurological injuries, remains a challenge. Here, we evaluated individual-specific changes in CoM dynamics in unimpaired adults and one individual with post-stroke hemiparesis while walking in shoes-only and with zero-stiffness and high-stiffness passive ankle exoskeletons. To identify optimal sets of physically interpretable mechanisms describing CoM dynamics, termed template signatures, we leveraged hybrid sparse identification of nonlinear dynamics (Hybrid-SINDy), an equation-free data-driven method for inferring sparse hybrid dynamics from a library of candidate functional forms. In unimpaired adults, Hybrid-SINDy automatically identified spring-loaded inverted pendulum-like template signatures, which did not change with exoskeletons (p > 0.16), except for small changes in leg resting length (p < 0.001). Conversely, post-stroke paretic-leg rotary stiffness mechanisms increased by 37-50% with zero-stiffness exoskeletons. While unimpaired CoM dynamics appear robust to passive ankle exoskeletons, how neurological injuries alter exoskeleton impacts on CoM dynamics merits further investigation. Our findings support Hybrid-SINDy's potential to discover mechanisms describing individual-specific CoM dynamics with assistive devices.
| S-EPMC10781730 | biostudies-literature
Project description:A recent experiment demonstrated that when humans wear unpowered elastic ankle exoskeletons with intermediate spring stiffness, they can reduce their metabolic energy cost to walk by ?7%. Springs that are too compliant or too stiff have little benefit. The purpose of this study was to use modeling and simulation to explore the muscle-level mechanisms for the "sweet spot" in stiffness during exoskeleton assisted walking.We developed a simple lumped uniarticular musculoskeletal model of the plantarflexors operating in parallel with an elastic "exo-tendon." Using an inverse approach with constrained kinematics and kinetics, we rapidly simulated human walking over a range of exoskeleton stiffness values and examined the underlying neuromechanics and energetics of the biological plantarflexors.Stiffer ankle exoskeleton springs resulted in larger decreases in plantarflexor muscle forces, activations, and metabolic energy consumption. However, in the process of unloading the compliant biological muscle-tendon unit, the muscle fascicles experienced larger excursions that negatively impacted series elastic element recoil that is characteristic of a tuned "catapult mechanism."The combination of disrupted muscle-tendon dynamics and the need to produce compensatory forces/moments to maintain overall net ankle moment invariance could explain the "sweet spot" in metabolic performance at intermediate ankle exoskeleton stiffness. Future work will aim to provide experimental evidence to support the model predictions presented here using ultrasound imaging of muscle-level dynamics during walking with elastic ankle exoskeletons.Engineers must account for the muscle-level effects of exoskeleton designs in order to achieve maximal performance objectives.
| S-EPMC4874912 | biostudies-literature
Project description:This study investigated the association of high ankle-brachial index difference (ABID) and systolic inter-ankle blood pressure difference (IAND) with short- and long-term outcomes in acute ischemic stroke patients without peripheral artery disease (PAD). Consecutive patients with acute ischemic stroke who underwent ankle-brachial index (ABI) measurement were enrolled. ABID was calculated as |right ABI-left ABI|. IAND and systolic inter-arm blood pressure difference (IAD) were calculated as |right systolic blood pressure - left systolic blood pressure|. Poor functional outcome was defined as modified Rankin Scale score ≥3 at 3 months. Major adverse cardiovascular events (MACEs) were defined as stroke recurrence, myocardial infarction, or death. A total of 2901 patients were enrolled and followed up for a median of 3.1 (interquartile range, 1.6-4.7) years. Among them, 2643 (84.9%) patients did not have PAD. In the logistic regression analysis, ABID ≥ 0.15 and IAND ≥ 15 mmHg were independently associated with poor functional outcome (odds ratio (OR), 1.970, 95% confidence interval (CI), 1.175‒3.302; OR, 1.665, 95% CI, 1.188‒2.334, respectively). In Cox regression analysis, ABID ≥0.15 and IAND ≥ 15 mmHg were independently associated with MACEs (hazard ratio (HR), 1.514, 95% CI, 1.058‒2.166; HR, 1.343, 95% CI, 1.051‒1.716, respectively) and all-cause mortality (HR, 1.524, 95% CI, 1.039‒2.235; HR, 1.516, 95% CI, 1.164‒1.973, respectively) in patients without PAD. High ABID and IAND are associated with poor short-term outcomes, long-term MACE occurrence, and all-cause mortality in acute ischemic stroke without PAD.
| S-EPMC7231112 | biostudies-literature
Project description:Augmenting the physical strength of a human operator during unpredictable human-directed (volitional) movements is a relevant capability for several proposed exoskeleton applications, including mobility augmentation, manual material handling, and tool operation. Unlike controllers and augmentation systems designed for repetitive tasks (e.g., walking), we approach physical strength augmentation by a task-agnostic method of force amplification-using force/torque sensors at the human-machine interface to estimate the human task force, and then amplifying it with the exoskeleton. We deploy an amplification controller that is integrated into a complete whole-body control framework for controlling exoskeletons that includes human-led foot transitions, inequality constraints, and a computationally efficient prioritization. A powered lower-body exoskeleton is used to demonstrate behavior of the control framework in a lab environment. This exoskeleton can assist the operator in lifting an unknown backpack payload while remaining fully backdrivable.
| S-EPMC8502972 | biostudies-literature
Project description:Producing timely, well-informed and reliable forecasts for an ongoing epidemic of an emerging infectious disease is a huge challenge. Epidemiologists and policy makers have to deal with poor data quality, limited understanding of the disease dynamics, rapidly changing social environment and the uncertainty on effects of various interventions in place. Under this setting, detailed computational models provide a comprehensive framework for integrating diverse data sources into a well-defined model of disease dynamics and social behavior, potentially leading to better understanding and actions. In this paper, we describe one such agent-based model framework developed for forecasting the 2014-2015 Ebola epidemic in Liberia, and subsequently used during the Ebola forecasting challenge. We describe the various components of the model, the calibration process and summarize the forecast performance across scenarios of the challenge. We conclude by highlighting how such a data-driven approach can be refined and adapted for future epidemics, and share the lessons learned over the course of the challenge.
| S-EPMC5568513 | biostudies-literature
Project description:Antiretroviral treatment history and past HIV-1 genotypes have been shown to be useful predictors for the success of antiretroviral therapy. However, this information may be unavailable or inaccurate, particularly for patients with multiple treatment lines often attending different clinics. We trained statistical models for predicting drug exposure from current HIV-1 genotype. These models were trained on 63,742 HIV-1 nucleotide sequences derived from patients with known therapeutic history, and on 6,836 genotype-phenotype pairs (GPPs). The mean performance regarding prediction of drug exposure on two test sets was 0.78 and 0.76 (ROC-AUC), respectively. The mean correlation to phenotypic resistance in GPPs was 0.51 (PhenoSense) and 0.46 (Antivirogram). Performance on prediction of therapy-success on two test sets based on genetic susceptibility scores was 0.71 and 0.63 (ROC-AUC), respectively. Compared to geno2pheno[resistance], our novel models display a similar or superior performance. Our models are freely available on the internet via www.geno2pheno.org. They can be used for inferring which drug compounds have previously been used by an HIV-1-infected patient, for predicting drug resistance, and for selecting an optimal antiretroviral therapy. Our data-driven models can be periodically retrained without expert intervention as clinical HIV-1 databases are updated and therefore reduce our dependency on hard-to-obtain GPPs.
| S-EPMC5386274 | biostudies-literature
Project description:BackgroundMental health disorders affect multiple aspects of patients' lives, including mood, cognition, and behavior. eHealth and mobile health (mHealth) technologies enable rich sets of information to be collected noninvasively, representing a promising opportunity to construct behavioral markers of mental health. Combining such data with self-reported information about psychological symptoms may provide a more comprehensive and contextualized view of a patient's mental state than questionnaire data alone. However, mobile sensed data are usually noisy and incomplete, with significant amounts of missing observations. Therefore, recognizing the clinical potential of mHealth tools depends critically on developing methods to cope with such data issues.ObjectiveThis study aims to present a machine learning-based approach for emotional state prediction that uses passively collected data from mobile phones and wearable devices and self-reported emotions. The proposed methods must cope with high-dimensional and heterogeneous time-series data with a large percentage of missing observations.MethodsPassively sensed behavior and self-reported emotional state data from a cohort of 943 individuals (outpatients recruited from community clinics) were available for analysis. All patients had at least 30 days' worth of naturally occurring behavior observations, including information about physical activity, geolocation, sleep, and smartphone app use. These regularly sampled but frequently missing and heterogeneous time series were analyzed with the following probabilistic latent variable models for data averaging and feature extraction: mixture model (MM) and hidden Markov model (HMM). The extracted features were then combined with a classifier to predict emotional state. A variety of classical machine learning methods and recurrent neural networks were compared. Finally, a personalized Bayesian model was proposed to improve performance by considering the individual differences in the data and applying a different classifier bias term for each patient.ResultsProbabilistic generative models proved to be good preprocessing and feature extractor tools for data with large percentages of missing observations. Models that took into account the posterior probabilities of the MM and HMM latent states outperformed those that did not by more than 20%, suggesting that the underlying behavioral patterns identified were meaningful for individuals' overall emotional state. The best performing generalized models achieved a 0.81 area under the curve of the receiver operating characteristic and 0.71 area under the precision-recall curve when predicting self-reported emotional valence from behavior in held-out test data. Moreover, the proposed personalized models demonstrated that accounting for individual differences through a simple hierarchical model can substantially improve emotional state prediction performance without relying on previous days' data.ConclusionsThese findings demonstrate the feasibility of designing machine learning models for predicting emotional states from mobile sensing data capable of dealing with heterogeneous data with large numbers of missing observations. Such models may represent valuable tools for clinicians to monitor patients' mood states.
| S-EPMC8088855 | biostudies-literature
Project description:BackgroundIn the Diabetes domain, events such as meals and exercises play an important role in the disease management. For that, many studies focus on automatic meal detection, specially as part of the so-called artificial [Formula: see text]-cell systems. Meals are associated to blood glucose (BG) variations, however such variations are not peculiar to meals, it mostly comes as a combination of external factors. Thus, general approaches such as the ones focused on glucose signal rate of change are not enough to detect personalized influence of such factors. By using a data-driven individualized approach for meal detection, our method is able to fit real data, detecting personalized meal responses even when such external factors are implicitly present.MethodsThe method is split into model training and selection. In the training phase, we start observing meal responses for each individual, and identifying personalized patterns. Occurrences of such patterns are searched over the BG signal, evaluating the similarity of each pattern to each possible signal subsequence. The most similar occurrences are then selected as possible meal event candidates. For that, we include steps for excluding less relevant neighbors per pattern, and grouping close occurrences in time globally. Each candidate is represented by a set of time and response signal related qualitative variables. These variables are used as input features for different binary classifiers in order to learn to classify a candidate as MEAL or NON-MEAL. In the model selection phase, we compare all trained classifiers to select the one that performs better with the data of each individual.ResultsThe results show that the method is able to detect daily meals, providing a result with a balanced proportion between detected meals and false alarms. The analysis on multiple patients indicate that the approach achieves good outcomes when there is enough reliable training data, as this is reflected on the testing results.ConclusionsThe approach aims at personalizing the meal detection task by relying solely on data. The premise is that a model trained with data that contains the implicit influence of external factors is able to recognize the nuances of the individual that generated the data. Besides, the approach can also be used to improve data quality by detecting meals, opening opportunities to possible applications such as detecting and reminding users of missing or wrongly informed meal events.
| S-EPMC10709931 | biostudies-literature