Nonspecific low back pain (NSLBP) constitutes a critical health challenge that impacts millions of people worldwide with devastating health and socioeconomic consequences. In today’s clinical settings, practitioners continue to follow conventional guidelines to categorize NSLBP patients based on subjective approaches, such as the STarT Back Screening Tool (SBST). This study aimed to develop a sensor-based machine learning model to classify NSLBP patients into different subgroups according to quantitative kinematic data, i.e., trunk motion and balance-related measures, in conjunction with STarT output. Specifically, inertial measurement units (IMU) were attached to the trunks of ninety-four patients while they performed repetitive trunk flexion/extension movements on a balance board at self-selected pace. Machine learning algorithms (support vector machine (SVM) and multi-layer perceptron (MLP)) were implemented for model development, and SBST results were used as ground truth. The results demonstrated that kinematic data could successfully be used to categorize patients into two main groups: high vs. low-medium risk. Accuracy levels of ~75% and 60% were achieved for SVM and MLP, respectively. Additionally, among a range of variables detailed herein, time-scaled IMU signals yielded the highest accuracy levels (i.e., ~75%). Our findings support the improvement and use of wearable systems in developing diagnostic and prognostic tools for various healthcare applications. This can facilitate development of an improved, cost-effective quantitative NSLBP assessment tool in clinical and home settings towards effective personalized rehabilitation.

Background/Purpose: To prevent falling, a common incident with debilitating health consequences among stroke survivors, it is important to identify significant fall risk factors (FRFs) towards developing and implementing predictive and preventive strategies and guidelines. This review provides a systematic approach for identifying the relevant FRFs and shedding light on future directions of research.Methods: A systematic search was conducted in 5 popular research databases. Studies investigating the FRFs in the stroke community were evaluated to identify the commonality and trend of FRFs in the relevant literature.Results: twenty-seven relevant articles were reviewed and analyzed spanning the years 1995–2020. The results confirmed that the most common FRFs were age (21/27, i.e., considered in 21 out of 27 studies), gender (21/27), motion-related measures (19/27), motor function/impairment (17/27), balance-related measures (16/27), and cognitive impairment (11/27). Among these factors, motion-related measures had the highest rate of significance (i.e., 84% or 16/19). Due to the high commonality of balance/motion-related measures, we further analyzed these factors. We identified a trend reflecting that subjective tools are increasingly being replaced by simple objective measures (e.g., 10-m walk), and most recently by quantitative measures based on detailed motion analysis.Conclusion: There remains a gap for a standardized systematic approach for selecting relevant FRFs in stroke fall risk literature. This study provides an evidence-based methodology to identify the relevant risk factors, as well as their commonalities and trends. Three significant areas for future research on post stroke fall risk assessment have been identified: 1) further exploration the efficacy of quantitative detailed motion analysis; 2) implementation of inertial measurement units as a cost-effective and accessible tool in clinics and beyond; and 3) investigation of the capability of cognitive-motor dual-task paradigms and their association with FRFs.

Human movement analysis is an important part of biomechanics and rehabilitation, for which many measurement systems are introduced. Among these, wearable devices have substantial biomedical applications, primarily since they can be implemented both in indoor and outdoor applications. In this study, a Trunk Motion System (TMS) using printed Body-Worn Sensors (BWS) is designed and developed. TMS can measure three-dimensional (3D) trunk motions, is lightweight, and is a portable and non-invasive system. After the recognition of sensor locations, twelve BWSs were printed on stretchable clothing with the purpose of measuring the 3D trunk movements. To integrate BWSs data, a neural network data fusion algorithm was used. The outcome of this algorithm along with the actual 3D anatomical movements (obtained by Qualisys system) were used to calibrate the TMS. Three healthy participants with different physical characteristics participated in the calibration tests. Seven different tasks (each repeated three times) were performed, involving five planar, and two multiplanar movements. Results showed that the accuracy of TMS system was less than 1.0°, 0.8°, 0.6°, 0.8°, 0.9°, and 1.3° for flexion/extension, left/right lateral bending, left/right axial rotation, and multi-planar motions, respectively. In addition, the accuracy of TMS for the identified movement was less than 2.7°. TMS, developed to monitor and measure the trunk orientations, can have diverse applications in clinical, biomechanical, and ergonomic studies to prevent musculoskeletal injuries, and to determine the impact of interventions.

Human muscle fatigue is the main result of diminishing muscle capability, leading to reduced performance and increased risk of falls and injury. This study provides a classification model to identify the human fatigue level based on the motion signals collected by a smartphone. 24 participants were recruited and performed the fatiguing exercise (i.e. squatting). Upon completing each set of squatting, they walked for a fixed distance while the smartphone attached to their right shank and the gait data were associated with the Borg’s Rating of Perceived Exertion (i.e. data label). Our machine-learning model of two (no- vs. strong-fatigue), three (no-, medium-, and strong-fatigue) and four (no-, low-, medium-, and strong-fatigue) levels of fatigue reached the accuracy of 91, 78, and 64%, respectively. The outcomes of this study may facilitate the accessibility of a fatigue-monitoring tool in the workplace, which improves the workers’ performance and reduce the risk of falls and injury. Practitioner Summary: This study aimed to develop a machine-learning model to identify human fatigue level using motion data captured by a smartphone attached to the shank. Our results can facilitate the development of an accessible fatigue-monitoring system that may improve the workers’ performance and reduce the risk of falls and injury. Abbreviations: WMSD: work-related musculoskeletal disorders; IMU: inertial measurement unit; RPE: rating of perceived exertion; SVM: support vector machine; IRB: institutional review board; SOM: self-organizing map; LDA: linear discriminant analysis; PCA: principal component analysis; FT: fourier transformation; RBF: radial basis function; CUSUM: cumulative sum; ROM: range of motion; MVC: maximum voluntary contractions