Biophone: Physiology monitoring from peripheral smartphone motions

Abstract

Abstract-The large-scale adoption of smartphones during recent years has created many opportunities to improve health monitoring and care delivery. In this work, we demonstrate that motion sensors available in off-the-shelf smartphones can capture physiological parameters of a person during stationary postures, even while being carried in a bag or a pocket. In particular, we develop methods to extract heart and breathing rates from accelerometer data and compare them with measurements obtained with FDA-cleared sensors. We evaluated their accuracy on 12 people across different still body postures (pre-and post-exercise) and were able to reach mean absolute errors of 1.16 beats per minute (STD: 3) and 0.26 breaths per minute (STD: 0.5) when considering different conditions. Furthermore, we evaluated the same methods during regular phone activities, such as when watching a video or listening to a conversation, yielding increased but still comparable error rates for some conditions.

MobileCogniTracker

“…In a similar fashion, Bluetooth scans, photo captures and ambient audio recordings are used to measure levels of sociability (Lane et al 2011;Vu et al 2015), that may be linked to cognitive functioning (Akl et al 2016). Some sophisticated approaches even measure physiological parameters such as heart rate and breathing rate through the smartphone's accelerometer using ballistocardiography (Hernandez et al 2015), which may be used to analyse cognitive stress (McDuff et al 2016). The straight application of smartphones for the measurement of cognitive functioning is, however, a fairly uncharted area.…”

Mobile devices for the remote acquisition of physiological and behavioral biomarkers in psychiatric clinical research

“…Findings from that pilot study were validated against contact sensors worn by participants during rest and during a cognitive stress condition, and the remote video parameters correctly classified participants in the rest versus stress conditions 85% of the time. Other research by the same team has demonstrated feasibility of estimating respiration and heart rates through passive data collection via built-in smartphone sensors (e.g., accelerometer) as people engage in typical activities such as sitting, standing, or using the phone (Hernandez et al, 2015). Using a software system called StressSense, researchers leveraged built-in smartphone microphones to capture young adult users’ vocal characteristics that were then analyzed to accurately classify stress in naturalistic settings (Lu et al, 2012).…”

Wearable Sensing of Cardiac Timing Intervals From Cardiogenic Limb Vibration Signals

“…Approaches to wearable cardiac parameter detection have proliferated in recent years [17] including sensing platforms for smartwatches [18]–[20] and smartphones [21]. Note that the knee based position offers an important advantage over the other two in that aortic PTT measures may be obtained.…”