A novel approach to spinal 3-D kinematic assessment using inertial sensors: Towards effective quantitative evaluation of low back pain in clinical settings

Ashouri, Sajad; Abedi, Mohsen; Abdollahi, Masoud; Manshadi, Farideh Dehghan; Parnianpour, Mohamad; Khalaf, Kinda

doi:10.1016/j.compbiomed.2017.08.002

Cited by 32 publications

(58 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noteworthy to mention that a recent study was successful in discriminating between healthy subjects and lower back pain sufferers based on trunk kinematics [21]. However, differences in trunk kinematic data between a healthy cohort and a patient group are likely to be more significant in comparison to differences within groups of LBP patients at variable risk levels.…”

Section: Discussionmentioning

confidence: 99%

“…In other words, although stratifying patients into different groups and assigning different treatment approaches has led to better therapeutic outcomes (e.g., decreasing disability from LBP and reducing the time off work), this classification approach tends to be prone to error due to the low reliability of the subjective information collected from patients [20]. In contrast, advancements in sensor technology are leading to efforts to augment subjective measures with objective approaches, such as measuring patient movements during walking or other controlled tasks [21][22][23][24][25]. The core concept of these studies involves utilizing differences in trunk motion (i.e., trunk kinematics) for people suffering from LBP.…”

Section: Introductionmentioning

confidence: 99%

“…Researchers continue to investigate kinematic approaches for their diagnostic potential, or even as a tool to make a clinical decision in primary care [21,[26][27][28][29][30][31]. Some earlier studies involving LBP sufferers have confirmed a correlation between the quality of motion in people and their health status [32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

“…Marras et al implemented several models to classify healthy versus LBP people based on trunk angular motion features during flexion/extension and bending of the trunk in various symmetric and asymmetric planes of motion [33,36]. Similarly, Ashouri et al was able to distinguish healthy people from LBP patients based on a signal from an inertial measurement unit (IMU) sensor on the chest during a trunk flexion/extension task using a Support Vector Machine (SVM) classifier [21]. In addition to focusing on LBP, similar studies have focused on the neck region.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Using a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach

Abdollahi

Ashouri

Abedi

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Low back pain (LBP) remains a critical health issue impacting literally millions of people worldwide. Currently, clinical practitioners rely on subjective measures such as the STarT Back Screening Tool to categorize LBP patients, which then informs specific treatment regimens. This study sought to develop a machine learning model to classify LBP patients into different groups according to kinematic data. Specifically, an inertial measurement unit (IMU) was attached to each patient's chest while he performed trunk flexion/extension motions at a self-selected pace. Machine learning algorithms such as support vector machine (SVM) and multi-layer perceptron (MLP) were implemented to evaluate the efficiency of the models. The results showed that the kinematic data we obtained could be used to categorize the patients into two groups: high vs. low-medium risk. We achieved accuracy levels of ~75% and 60% for SVM and MLP, respectively.Additionally, among a range of variables detailed herein, we determined that time-scaled IMU signal resulted in the highest accuracy. Our findings support the use of body-motion measures in developing prognosis tools for healthcare applications. Our results could help overcome the need for objective clinic-based diagnosis approaches, which in turn would lead to assigning better treatment approaches and rehabilitation services for LBP sufferers.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach

Abdollahi

Ashouri

Abedi

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among these, some have used wearable devices for measuring kinematic and kinetic parameters of human gait. For example, the inertial measurement unit (IMU) systems have gained attention for gait analysis, since the sensors are small, light and portable, thus are minimally intrusive for a range of applications [3,4]. Recently, few researchers have used similar technologies to quantify human muscle fatigue.…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven Model to Identify Fatigue Level Based on the Motion Data from a Smartphone

Karvekar

Abdollahi

Rashedi

2019

Preprint

Self Cite

View full text Add to dashboard Cite

The fatigue due to repetitive and physically challenging jobs may result in workers' poor performance and Work-related Musculoskeletal Disorder (WMSD). Thus, it is imperative to frequently monitor fatigue and take necessary recovery actions. Our purpose was to develop a methodology to objectively classify subjects' fatigue level in the workplace utilizing the motion sensors embedded in the smartphones. An experiment consisting of twenty-four participants (12 M, 12 F) with a smartphone attached to their right shank was conducted using a fatiguing exercise (squatting), targeted mainly the lower extremity musculature. After each set of an exercise (2-min squatting), participants were asked about their ratings of perceived exertion (RPE), then a reference gait data were collected during a straight walk of 20-32 steps. This process was continued until they reported strong fatigue (≥17). Using the RPE to label the gait data, we have developed machine learning algorithms (i.e., binary and multi-class SVM models) to classify the individuals' gait into two (no-vs. strong-fatigue) and four levels (no-, low-, medium-, and strong-fatigue). The models reached the accuracies of 91% and 61% for two and four-level classification, respectively. The outcomes of this study may facilitate the implementation of a proactive approach in continuous monitoring of operators' fatigue level, which may subsequently increase the workers' performance and reduce the risk of WMSDs.

show abstract

Interpretable machine learning models for classifying low back pain status using functional physiological variables

et al. 2020

View full text Add to dashboard Cite

Purpose To evaluate the predictive performance of statistical models which distinguishes different low back pain (LBP) sub-types and healthy controls, using as input predictors the time-varying signals of electromyographic and kinematic variables, collected during low-load lifting. Methods Motion capture with electromyography (EMG) assessment was performed on 49 participants [healthy control (con) = 16, remission LBP (rmLBP) = 16, current LBP (LBP) = 17], whilst performing a low-load lifting task, to extract a total of 40 predictors (kinematic and electromyographic variables). Three statistical models were developed using functional data boosting (FDboost), for binary classification of LBP statuses (model 1: con vs. LBP; model 2: con vs. rmLBP; model 3: rmLBP vs. LBP). After removing collinear predictors (i.e. a correlation of > 0.7 with other predictors) and inclusion of the covariate sex, 31 predictors were included for fitting model 1, 31 predictors for model 2, and 32 predictors for model 3. Results Seven EMG predictors were selected in model 1 (area under the receiver operator curve [AUC] of 90.4%), nine predictors in model 2 (AUC of 91.2%), and seven predictors in model 3 (AUC of 96.7%). The most influential predictor was the biceps femoris muscle (peak = 0.047) in model 1, the deltoid muscle (peak = 0.052) in model 2, and the iliocostalis muscle (peak = 0.16) in model 3. Conclusion The ability to transform time-varying physiological differences into clinical differences could be used in future prospective prognostic research to identify the dominant movement impairments that drive the increased risk.

show abstract

A novel approach to spinal 3-D kinematic assessment using inertial sensors: Towards effective quantitative evaluation of low back pain in clinical settings

Cited by 32 publications

References 22 publications

Using a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach

Using a Motion Sensor to Categorize Low Back Pain Patients: A Machine Learning Approach

A Data-Driven Model to Identify Fatigue Level Based on the Motion Data from a Smartphone

Interpretable machine learning models for classifying low back pain status using functional physiological variables

Contact Info

Product

Resources

About