Body posture determination for Heart Failure patients from ankle orientation measurements

Abstract

Heart-Failure (HF) is among the leading hospitalization causes in modern healthcare systems. In this paper, a method for performing continuous patient monitoring is presented with a focus on low power consumption. A prototype wearable device is being developed at the University of Sevilla to collect measurements. Among the sensing components there are two major blocks formed by a commercial biological impedance analog frontend from Analog Devices (AD5940) and an Inertial Motion Unit (IMU) capable of estimating attitude of the device. This information could provide a tremendous amount of information for the physician and help diagnose and remote monitor patients with HF. A major factor that can be analyzed to provide information on patient status is activity level and body states; time spent walking or standing, laying down or seated. In this work, a body tracking / activity estimation method is proposed for low power continuous monitoring. This study reports good results characterizing the laying down position and discriminating between laying down and standing/walking and seated. The presented results are relevant for clinical practice since body motion and position can serve as a health marker for patients. Additionally, the acquired motion information can be further processed to better understand artifacts and variations in the analog impedance measurements.