Use of a Low-Cost, Chest-Mounted Accelerometer to Evaluate Transfer Skills of Wheelchair Users During Everyday Activities: Observational Study

Aiding Clinical Decision-Making at the Individual and Community Level Using Mobile Sensor Data: Study Protocol for an Experimental Design

Background Mobile sensor data can provide vital information about patients' behavior and physical activity. In particular, the mobile accelerometer sensor data, if monitored effectively, can be used further for keeping watch on the physical activity of an individual and planning an intervention to improve it. These sensor data can also be used for improving clinical decision-making in sedentary lifestyle-related diseases. However, despite the availability of smartphone devices to the majority of the population, the sensor statistics captured by those devices are underused because of the lack of awareness about sensor metadata and the absence of clear-cut guidelines for using them. Objective The objective of this study is to study and encourage the use of the accelerometer sensor metadata of the mobile device in facilitating the delivery of interventions to enhance physical activity. At the end of the study, it should be able to lay down the basic guidelines for using the accelerometer sensor data of the mobile device for monitoring patients' activity and aiding the clinical decision monitoring. Methods A sequential explanatory mixed-method research design will be used between July 2023 and December 2024. Firstly, individuals between the ages of 30 and 45 visiting the clinic of healthcare workers and having lifestyle-related diseases will be screened for a sedentary lifestyle with the pre-tested sedentary lifestyle measuring tool. After enrolling patients with a sedentary lifestyle in the study, physical activity-related accelerometer sensor data will be collected from them. Based on the initial data recorded, an individualized activity plan will be created. Periodic monitoring of physical activity levels will be conducted over a three-month period. Participants will receive a message from clinicians based on their current physical activity levels to encourage them to adhere to the prescribed regimen suggested by clinicians. The improvement in physical activity over the period will be monitored, and feedback from clinicians to improve the mechanism will be recorded. Results The proposed research will help in exploring the role of remote monitoring of sensor data in improving adherence to physical activity plans as prescribed by their clinicians. It will also help in studying the variables that influence the monitoring of remote data collection. Conclusions This study will help create a protocol to bring improvement in the physical activity levels of patients with a sedentary lifestyle and with confirmed hypertension and type 2 diabetes through remote capturing and monitoring of mobile sensor data, ongoing messaging, and facilitation through clinical decision-making.

Automating the Clinical Assessment of Independent Wheelchair Sitting Pivot Transfer Techniques

Background

Using proper transfer technique can help to reduce forces and prevent secondary injuries. However, current assessment tools rely on the ability to subjectively identify harmful movement patterns.

Objectives

The purpose of the study was to determine the accuracy of using a low-cost markerless motion capture camera and machine learning methods to evaluate the quality of independent wheelchair sitting pivot transfers. We hypothesized that the algorithms would be able to discern proper (low risk) and improper (high risk) wheelchair transfer techniques in accordance with component items on the Transfer Assessment Instrument (TAI).

Methods

Transfer motions of 91 full-time wheelchair users were recorded and used to develop machine learning classifiers that could be used to discern proper from improper technique. The data were labeled using the TAI item scores. Eleven out of 18 TAI items were evaluated by the classifiers. Motion variables from the Kinect were inputted as the features. Random forests and k-nearest neighbors algorithms were chosen as the classifiers. Eighty percent of the data were used for model training and hyperparameter turning. The validation process was performed using 20% of the data as the test set.

Results

The area under the receiver operating characteristic curve of the test set for each item was over 0.79. After adjusting the decision threshold, the precisions of the models were over 0.87, and the model accuracies were over 71%.

Conclusion

The results show promise for the objective assessment of the transfer technique using a low cost camera and machine learning classifiers.

Chest-Worn Inertial Sensors: A Survey of Applications and Methods

Inertial Measurement Units (IMUs) are frequently implemented in wearable devices. Thanks to advances in signal processing and machine learning, applications of IMUs are not limited to those explicitly addressing body movements such as Activity Recognition (AR). On the other hand, wearing IMUs on the chest offers a few advantages over other body positions. AR and posture analysis, cardiopulmonary parameters estimation, voice and swallowing activity detection and other measurements can be approached through chest-worn inertial sensors. This survey tries to introduce the applications that come with the chest-worn IMUs and summarizes the existing methods, current challenges and future directions associated with them. In this regard, this paper references a total number of 57 relevant studies from the last 10 years and categorizes them into seven application areas. We discuss the inertial sensors used as well as their placement on the body and their associated validation methods based on the application categories. Our investigations show meaningful correlations among the studies within the same application categories. Then, we investigate the data processing architectures of the studies from the hardware point of view, indicating a lack of effort on handling the main processing through on-body units. Finally, we propose combining the discussed applications in a single platform, finding robust ways for artifact cancellation, and planning optimized sensing/processing architectures for them, to be taken more seriously in future research.

The Validity, Reliability, and Sensitivity of a Smartphone-Based Seated Postural Control Assessment in Wheelchair Users: A Pilot Study

Seated postural control is essential for wheelchair users to maintain proper position while performing activities of daily living. Clinical tests are commonly used to measure seated postural control, yet they are subjective and lack sensitivity. Lab-based measures are highly sensitive but are limited in scope and restricted to research settings. Establishing a valid, reliable, and accessible measurement tool of seated postural control is necessary for remote, objective assessments. Therefore, the purpose of this study was to examine the validity, reliability, and sensitivity of smartphone-based postural control assessments in wheelchair users. Eleven participants (age: 35.4 ± 17.9) completed two experimental visits 1-week apart consisting of three clinical tests: Trunk Control Test (TCT), Function in Sitting Test (FIST), and Tee-shirt Test, as well as, standardized instrumented balance tasks that manipulated vision (eyes open and closed), and trunk movement (functional reach and stability boundary). During these tasks, participants held a smartphone instrumented with a research-grade accelerometer to their chest. Maximum and root mean square (RMS) acceleration in the medial-lateral (ML) and anterior-posterior (AP) axes were derived. Participants were grouped into non-impaired and impaired postural groups based on FIST scores. Spearman rank-order correlations were conducted between the two devices' outcome measurements and between these measures and those of the clinical tests. Receiver operating characteristic (ROC) curves and the area under the curves (AUC) were determined to distinguish participants with and without impaired postural control. The reliability of outcome variables was assessed using inter-class correlations. Strong correlations between outputs derived from the smartphone and research-grade accelerometer were seen across balance tasks (ρ = −0.75–1.00; p ≤ 0.01). Numerous significant moderate correlations between clinical test outcomes and smartphone and research-grade RMS ML accelerometry were seen (ρ = −0.62 to 0.83 (p ≤ 0.044)]. On both devices, the AUC for ROC plots were significant for RMS ML sway during the eyes open task and functional stability boundary (p < 0.05). Reliability of smartphone accelerometry was comparable to the research-grade accelerometer and clinical tests. This pilot study illustrated that smartphone-based accelerometry may be able to provide a valid and reliable assessment of seated postural control and have the ability to distinguish between those with and without impaired postural control.