Patient Posture Monitoring System Based on Flexible Sensors

Abstract

Monitoring patients using vision cameras can cause privacy intrusion problems. In this paper, we propose a patient position monitoring system based on a patient cloth with unobtrusive sensors. We use flexible sensors based on polyvinylidene fluoride, which is a flexible piezoelectric material. Theflexiblesensorsareinsertedintopartsclosetothekneeandhipoftheloosepatientcloth. We measure electrical signals from the sensors caused by the piezoelectric effect when the knee and hip in the cloth are bent. The measured sensor outputs are transferred to a computer via Bluetooth. We use a custom-made program to detect the position of the patient through a rule-based algorithm and the sensor outputs. The detectable postures are based on six human motions in and around a bed. The proposed system can detect the patient positions with a success rate over 88 percent for three patients.

Keywords: patient cloth; piezoelectric material; real-time monitoring; flexible sensor.

Figure 1

Pictures of the (a) flexible sensor and (b) sensing module.

Figure 2

Schematic of the sensing system consisting of two flexible sensors and one sensing module.

Figure 3

Pictures of the (a) patient pants with two pockets for the flexible sensors and (b) patient wearing the sensing system.

Figure 4

Patient postures with the (a) standing; (b) sitting; (c) sitting knee extension; and (d) supine positions. In the inset, the red and blue lines are the sensor shapes at the knee and hip, respectively.

Figure 5

Digitalized sensor outputs at the transition (a) from the standing to sitting position; (b) from the sitting to standing position; (c) from the sitting to sitting knee extension position; (d) from the sitting knee extension to sitting position; (e) from the sitting knee extension to supine position; and (f) from the supine to sitting knee extension position. The red and blue lines are the data of the sensor at the knee and hip, respectively.

Figure 6

Signal processed values from the sensor outputs at the transition (a) from the standing to sitting position; (b) from the sitting to standing position; (c) from the sitting to sitting knee extension position; (d) from the sitting knee extension to sitting position; (e) from the sitting knee extension to supine position; and (f) from the supine to sitting knee extension position. The red and blue lines are the data of the sensor at the knee and hip, respectively.

Figure 7

Histograms of the difference $D_{\mathrm{n}}$. (a) $D_{\mathrm{n}}^{\mathrm{knee}}$ and (b) $D_{\mathrm{n}}^{\mathrm{hip}}$ at the transition from the standing to sitting. (c) $D_{\mathrm{n}}^{\mathrm{knee}}$ and (d) $D_{\mathrm{n}}^{\mathrm{hip}}$ at the transition from the sitting to standing. “M” and “SD” indicate their mean and standard deviation.

Figure 8

Flow chart for posture decisions.

Figure 9

Snapshots of the computer screen showing the estimated patient postures and signal processed values from the sensor outputs at the transition (a) from the standing to sitting position (i); (b) from the sitting to standing position (ii); (c) from the sitting to sitting knee extension position (iii); (d) from the sitting knee extension to sitting position (iv); (e) from the sitting knee extension to supine position (v); and (f) from the supine to sitting knee extension position (vi). The arrows are added to represent the transitions from the previous positions.