Distinguishing positions and movements in bed from load cell signals

Abstract

Objective: To characterize and classify six positions and movements for individuals in a bed using the output signals of four load cell sensors. Approach: A bed equipped with four load cell sensors and synchronized video was used to assess the load cell response of 54 healthy individuals in prescribed positions and as they moved between positions. Stationary positions were characterized by the signals from the four load cells and the coordinates of the center of mass (CoM). Movements were characterized by the changes in load cell signals, four parameters associated with the trajectory of the CoM between the initial and final position (Euclidean distance, length of the trajectory, and the x- and y- variances), and the initial position’s CoM coordinates. Classification and decision tree models were used to assess the ability of these parameters to identify specific positions or movements. Main results: Six positions were classified with an accuracy of 74.9% and six movements were classified with an accuracy of 79.7%. Significance: This study demonstrates the feasibility of distinguishing certain positions and movements with load cell sensors. The identification of positions and movements for individuals in bed can be used as a tool in a variety of clinical settings.

Pressure Ulcer Monitoring Platform—A Prospective, Human Subject Clinical Study to Validate Patient Repositioning Monitoring Device to Prevent Pressure Ulcers

“…For example, pressure pad-based devices typically use an array of pressure sensors, which is costly compared to only four load cells that are used in PUMP2. There exist alternative under-bed load cells to PUMP2; however, these solutions are only validated by predefined movements among healthy subjects in a lab environment [11][12][13][14] with accuracy ranges 74.9-97%. Furthermore, existing chest-worn devices come into direct contact with patient skin opposed to the PUMP1 device that does not come into patient skin contact.…”

“…Current solutions include mattressbased, loadcell-based technologies and wearable sensors to detect and confirm repositioning (e.g., earlysense, LEAF). [8][9][10][11][12][13][14] Although the reported detection accuracy is high, most of these systems have been validated only with predefined movements performed by healthy subjects in a lab environment. Our study validates two monitoring systems (PUMP1 and PUMP2) in hospital rooms with immobile patients over a period of 10 -2 h. One of the systems is a wearable sensor, and the other is a loadcell-based system.…”

A Comparison of Inertial Measurement Units and Overnight Videography to Assess Sleep Biomechanics

“…There is no commonly accepted methodology for capturing sleep biomechanics data. Particular attention has been paid to sleep position; studies that have examined sleep position are methodologically diverse, with a variety of methods such as videography [ 12 ], pressure sensors [ 13 ] and wearable accelerometers [ 14 ] being used, rendering a synthesis of findings difficult. The current standard clinical assessment of sleep position is overnight infrared videography (typically, recorded video footage from a single camera angle), that is then visually inspected and coded by a clinician (typically, as supine/prone/left side lying/right side lying [ 15 ]).…”