Millions of people worldwide suffer from chronic lung conditions that require regular, careful monitoring. The severity of these diseases is usually measured using spirometers – devices that measure patient lung function.
Traditionally, this was only conducted in clinical settings, but home spirometry is gaining acceptance in the medical community due to its ability to detect pulmonary exacerbations and improve outcomes of chronic lung ailments. However, cost and usability are often significant barriers to its widespread adoption.
Now, a new health-sensing tool has been developed by a team of computer science and engineering and electrical engineering researchers – from the University of Washington (UW) – that can accurately measure lung function over a simple phone call.
The new service, called SpiroCall, allows patients to perform spirometry on any phone. The patients take a deep breath in and exhale as hard and fast as they can until they cannot exhale any more.
The phone’s microphone senses sound and pressure from that exhalation and sends the data to a central server, which uses machine learning algorithms to convert the data into standard measurements of lung function. The server computes the lung function measurements and sends the patients a response.
“We wanted to be able to measure lung function on any type of phone you might encounter around the world – smartphones, dumb phones, landlines, pay phones,” says Shwetak Patel, Washington research foundation endowed professor of computer science and engineering and electrical Engineering at UW.
“With SpiroCall, you can call a 1-800 number, blow into the phone and use the telephone network to test your lung function.”
The SpiroCall solution builds upon earlier work by the team that involved developing a smartphone app called SpiroSmart.
Introduced in 2012, the original application records the user’s exhalation and sends the audio data generated to a central server. The server then calculates the expiratory flow rate using a physiological model of the vocal tract and a model of the reverberation of sound around the user’s head.
The development of the SpiroSmart technology was an important step in making spirometry more accessible, and since its introduction, it has been involved in numerous clinical studies and is currently deployed in multiple locations around the world, including Seattle and Tacoma in the United States, Khulna in Bangladesh, and Pune in India.
“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, which in some places requires hours or days of travel.”
Mayank Goel, UW doctoral student and lead developer
Over the last 4 years, the team has collected data from more than 4,000 patients, where clinicians have measured lung function using both SpiroSmart and a commercial spirometer.
That comparative data has improved the performance of the machine learning algorithms and laid the groundwork for team’s current Food and Drug Administration (FDA) clearance process.
In a recent paper, the team documented results from the new solution that came within 6.2 percent of results from clinical spirometers used in hospitals and doctor’s offices, meaning it meets the medical community’s standards for accuracy.
Using a smartphone app presented a number of challenges when it came to deploying the solution in many developing regions of the world that could really benefit from this type of technology.
Lack of accessibility to smartphone technology alongside the need to recalibrate the software algorithms to work with different handsets and devices meant that widespread adoption and deployment was problematic.
The new solution solves many of these issues. By using any phone, from a shared landline to a 10-year old mobile phone, the technology can now benefit anyone with access to any phone service.
When developing the call-in solution, the team needed to overcome problems with sound quality. But by combining multiple regression algorithms, they were able to provide reliable lung function estimates despite the degraded audio quality.
“We had to account for the fact that the sound quality you get over a phone line is worse,” said co-author Elliot Saba, a UW electrical engineering doctoral student. “You can imagine how listening to someone play a song over a phone line would sound compared to listening to it on your music app – there’s a similar difference with a spirometry test.”
The researchers hope that the success of the project, so far, will enable them to improve access to home-based spirometry and lung function monitoring and in turn improve the way care is administered to patients around the world.
“Our research area is not just about sensing, but human-centered sensing,” Goel said. “Because this project has been around for 4 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 improvements.”
Future steps for the research team include looking at additional data collection and figuring out how best to communicate test results in a way that will make sense to patients.