Dataset Information

Low-back electromyography (EMG) data-driven load classification for dynamic lifting tasks.

ABSTRACT:

Objective

Numerous devices have been designed to support the back during lifting tasks. To improve the utility of such devices, this research explores the use of preparatory muscle activity to classify muscle loading and initiate appropriate device activation. The goal of this study was to determine the earliest time window that enabled accurate load classification during a dynamic lifting task.

Methods

Nine subjects performed thirty symmetrical lifts, split evenly across three weight conditions (no-weight, 10-lbs and 24-lbs), while low-back muscle activity data was collected. Seven descriptive statistics features were extracted from 100 ms windows of data. A multinomial logistic regression (MLR) classifier was trained and tested, employing leave-one subject out cross-validation, to classify lifted load values. Dimensionality reduction was achieved through feature cross-correlation analysis and greedy feedforward selection. The time of full load support by the subject was defined as load-onset.

Results

Regions of highest average classification accuracy started at 200 ms before until 200 ms after load-onset with average accuracies ranging from 80% (±10%) to 81% (±7%). The average recall for each class ranged from 69-92%.

Conclusion

These inter-subject classification results indicate that preparatory muscle activity can be leveraged to identify the intent to lift a weight up to 100 ms prior to load-onset. The high accuracies shown indicate the potential to utilize intent classification for assistive device applications.

Significance

Active assistive devices, e.g. exoskeletons, could prevent back injury by off-loading low-back muscles. Early intent classification allows more time for actuators to respond and integrate seamlessly with the user.

SUBMITTER: Totah D

PROVIDER: S-EPMC5814006 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveThe aim of this study was to assess the feasibility and potential effectiveness of an 8-week virtual EMG biofeedback intervention for patients with CLBP.MethodsPatients with CLBP completed validated baseline and post-intervention assessments of pain intensity and interference (Brief Pain Inventory), back pain-related disability (Oswestry Disability Index), anxiety and depression (Hospital Anxiety and Depression Scale). Participants underwent a series of Quantitative Sensory Testing (QST) procedures assessing responses to mechanical stimuli during two separate visits (baseline and post-intervention). In addition, we assessed, using surface EMG, the muscle tension in the trapezius, latissimus, and low back muscles at each session. Patients were randomized into the EMG biofeedback intervention or usual care group. Factorial analysis of variance including the interaction between treatment group and time was used to analyze the changes in pain intensity (primary outcome), pain interference, disability (secondary outcomes), anxiety, and depression (secondary outcomes).ResultsCompared to the treatment as usual comparison group, patients in the EMG biofeedback group reported lower pain intensity after completing the intervention (mean group difference 0.9, 95% CI -1.07, -0.32; p≤0.01). Compared to baseline, participants in the EMG biofeedback group demonstrated statistically significant reductions in pain interference (mean difference 1.3, 95% CI 0.42, 2.1; p≤0.01), disability (mean difference 4.32, 95% CI 1.2, 7.3; p≤0.01), and significant increases in low back pain thresholds (mean difference 0.5, 95% CI -0.87, -0.05; p≤0.01), assessed by QST. However, no significant group by time effects were observed for secondary outcomes: pain interference, disability, and low back pain thresholds. In addition, significant changes were observed in muscle tension for the trapezius, latissimus, and low back muscles in the EMG biofeedback group (p<0.001).ConclusionsVirtual EMG biofeedback shows promise as a potential therapy for reducing pain and disability in individuals with chronic nonspecific low back pain.