Aditi Kaveti ‘23
While heart conditions including high blood pressure and cardiac arrest are well-known, heart rhythm disorders, such as cardiac arrhythmia, are actually more common. The improper beating of the heart can lead to serious diseases like strokes but can be difficult to diagnose and identify because they do not present a periodic pattern in the data.
Shyam Gollakota, an associate professor in the Paul G. Allen School of Computer Science and Engineering at the University of Wisconsin, is tackling the problem of detecting the variability in heart beats of cardiac patients without physical contact. The researchers in his group are expanding on at-home heartbeat monitoring systems to develop a device that can detect cardiac arrests or monitor infantile breathing. The team is enabling a new skill on smart speakers using a system that sends inaudible sounds into a room and deciphers the way the sounds are reflected back to the speaker to identify and monitor individual heartbeats.
To ensure the efficacy and accuracy of this new, innovative system, the researchers designed an experiment to test a prototype smart speaker using 26 healthy participants and 24 hospitalized patients with many different cardiac conditions that affect the rate of the heartbeat, including atrial fibrillation and heart failure. The speaker functions differently than a traditional monitor because it uses specific algorithms to measure the vibrations on the skin when the heart beats rather than the electric signal of the heart during contractions. The team measured around 12,300 heartbeats of healthy participants and determined that the median inter-beat interval was within 28 milliseconds of a standard heartbeat monitor.
While this smart speaker system requires a bit more troubleshooting before it can be effectively used to diagnose health conditions concerning heartbeats, it is an important innovation for the future of cardiology and individualized health care.
 Wang, A., Nguyen, D., Sridhar, A.R. et al. Using smart speakers to contactlessly monitor heart rhythms. Commun Biol 4, 319 (2021). https://doi.org/10.1038/s42003-021-01824-9