Sensing Tool Measures Lung Function over the Phone

A server receives the data of degraded audio quality, calculates clinically relevant lung function measures using multiple regression algorithms, and reports the results using an audio message, text message, or both. The researchers also found several significant usability challenges more difficult to mitigate, such as how a user holds the phone, the distance from the user’s mouth to the phone, and how wide a user opens their mouth.

The researchers therefore designed a simple, low-cost 3D printed whistle accessory, which generates vortices as the user exhales through it, changing its resonating pitch in proportion to the flow rate. The whistle does not have any moving parts and is as simple as any spirometer mouthpiece. Advantages of the whistle include more consistent acoustic properties, audible sound at lower flow rates, removing the effect of distance from the user’s mouth, and precisely controlling mouth shape and phone orientation.

In a study to investigate viability of the call-in service approach with and without the whistle, the researchers evaluated SpiroCall in 50 patients, comparing it to approved spirometers and evaluating the effect of using the voice communication channel on performance. Each patient performed spirometry efforts with and without the whistle on two different phones, recording the audio through the cell phone network, and two smartphones recording the audio locally through an app. Participants also used two different sizes of vortex whistles to determine if different sizes work better for different individuals.

The results show that without a whistle, SpiroCall has a mean error of 7.2% for the four major clinically relevant lung function measures; for forced expiratory volume percentage (FEV1%), the mean error is 6.2%. With a whistle, SpiroCall has a mean error of 8.3% for the four measures, and 7.3% for FEV1%. Although the whistle shows higher average error in lung function estimates, it is more consistent for people with lower lung function and produces fewer overestimations. The study was presented at the Association for Computing Machinery conference, held during May 2016 in San Jose (CA, USA).

"People have to manage chronic lung diseases for their entire lives, so there's a real need to have a device that allows patients to accurately monitor their condition at home without having to constantly visit a medical clinic,” said lead author Mayank Goel, MSc, a computer science and engineering doctoral student. “Because this project has been around for four years, we've been able to talk to a lot of patients about how they're able to use the technology, and that feedback has really helped us make smart improvement.”

Related Links:
University of Washington