An algorithm uses the phone microphone as an uncalibrated pressure sensor. Captured audio is converted into an estimate of the flow-rate of air exiting from a patient’s mouth.
Lung function estimates are provided despite varying audio quality. One second of silence before the start of the test gauges ambient noise levels. If it is too noisy, a patient is asked to move, or to call back at another time.
SpiroCall’s results were 6.2 percent less accurate than hospital spirometers. While not perfect, this solution could save many lives in areas where regular doctor visits are not possible.
Wearable Tech + Digital Health NYC – June 7, 2016 @ the New York Academy of Sciences
NeuroTech NYC – June 8, 2016 @ the New York Academy of Sciences