Analyzing voice recordings could help detect lung congestion in heart failure patients, study suggests
The results of a new study suggest that analysis of short voice recordings could help detect lung congestion in patients with heart failure, which could help ensure timely intervention provision.
The results of a new study – presented at the virtual Heart Failure Association Discoveries event (5–19 June 2020), an initiative of the European Society of Cardiology (Biot, France) – suggest that analysis of short voice recordings by a novel smartphone app could help detect lung congestion in patients with heart failure, which could help ensure timely intervention provision.
Heart failure affects more than 26 million individuals across the globe and is a leading cause of mortality; one of the most common symptoms of the condition is shortness of breath, which manifests as a result of fluid accumulation in the lungs. Early detection of lung congestion and strict patient surveillance could help reduce hospitalizations and death associated with heart failure.
In this study, researchers investigated the ability of a novel smartphone app to leverage speech processing to distinguish between voice recordings of patients with and without lung congestion, as such build-up of lung fluid can cause subtle speech pattern alterations.
You may also be interested in:
- Mobile app could reliably determine risk of spontaneous preterm birth
- Smartphone cameras may help assess anemia using new app
- Wearable fitness trackers could improve real-time flu surveillance
For the study, 40 patients hospitalized with acute heart failure and lung congestion were asked to use standard smartphones to record their saying five sentences – for 2–5 seconds – when they were admitted to hospital and then again just prior to their hospital discharge when their congestion had been resolved.
Following analysis of the recordings by the novel app, researchers observed that the technology was able to successfully distinguish between recordings made when the patients were in congested versus non-congested states.
The study authors highlight the potential usability of the app technology for remote patent monitoring; if patients submit short voice recordings daily, the app will become more sensitive and personalized. Small deviations from the ‘healthy’ voice model that the app builds for a given patient, denoting the start of fluid accumulation, can generate alerts to physicians, which could help identify patients requiring intervention earlier and remotely.
Study author Offer Amir, Director of the Heart Institute at Hadassah Medical Centre (Jerusalem, Israel), explained: "During the current COVID-19 pandemic healthcare professionals are transitioning many outpatient visits for heart failure patients to telemedicine platforms, highlighting the importance of remote monitoring to reduce the risk of exposure to coronavirus."
"Those with early signs of lung congestion could receive adjustments to their treatment, thereby preventing the need for hospitalisation," Amir concluded.
Amir O, Abraham WT, Azzam ZS et al. Speech analysis to evaluate acute heart failure patient clinical status. Presented at HFA Discoveries 2020; www.escardio.org/The-ESC/Press-Office/Press-releases/Smartphone-app-uses-voice-recordings-to-detect-fluid-in-the-lungs