My UM
My UM
Search

Smartphone app detects the onset of a respiratory attack in people with asthma and COPD

Changes in the voice, measured via a smartphone app, may indicate the onset of a respiratory attack in people with asthma or COPD. This is according to research by pulmonologist Sami Simons (NUTRIM) and his team, published in ERJ Open Research. The voice undergoes measurable changes during the onset, peak and recovery phases of a respiratory episode. This offers opportunities for accessible home monitoring and earlier treatment of respiratory episodes.
 

People with asthma or COPD, in addition to their daily symptoms, regularly experience sudden worsening of their condition, also known as lung attacks. Such episodes are accompanied by increased shortness of breath, coughing and mucus production. Asthma attacks can lead to hospital admissions, accelerated decline in lung function and a lower quality of life. Precisely because these exacerbations often begin at home, researchers sought a simple way to detect them earlier. Voice analysis via a smartphone appears to be a promising option for this. During an asthma attack, the airflow changes whilst speaking, causing the voice to sound different.

Onset of symptoms measurable

For the study, 73 participants with asthma or COPD recorded their voices three times a day using a specially developed app on their own mobile phones. At the same time, they kept a record of their symptoms. A total of 38 respiratory attacks were recorded. The researchers observed that the voice changes during a respiratory attack. Vocal characteristics such as pitch, volume and the number of pauses whilst speaking changed as soon as symptoms began to worsen.

“During a respiratory attack, breathing becomes more difficult and the airflow needed to speak is reduced,” explains pulmonologist and lead researcher Sami Simons. “As a result, the voice sounds less stable, hoarse or more breathless. People take more pauses whilst speaking and sound more breathless. Our results show that we can measure these changes at an early stage.”

Remote care

Participants used the app at home for three months and carried out short speech exercises every day. This proved easy to maintain: participants completed at least one speech recording on 83 per cent of the days. As a result, researchers were able to monitor the progression of a lung attack on a daily basis for the first time.

According to Simons, voice technology could contribute to better remote care in the future. “If follow-up research confirms that voice changes can reliably predict lung attacks, patients may be warned earlier and start treatment more quickly. This could help prevent health problems and hospital admissions.”

Earlier prediction

The researchers are currently working on algorithms designed to detect lung attacks even earlier. Initial analyses suggest that certain vocal characteristics may change several days before symptoms appear. Later this year, the SPEAK study will also begin in the Netherlands, in which the accuracy of voice-based detection will be further tested. The researchers emphasise that the technology is still under development and is currently only being used in a research context. 

The research was carried out at the NUTRIM research institute at Maastricht UMC+ and Maastricht University. The app (TACTICAS) was developed in collaboration with patients and technology partner Zana Technologies. The research was co-funded by the Lung Fund, Boehringer Ingelheim and AstraZeneca.

This article was previously published on the Maastricht UMC+ website..

Also read