Credit: Getty Images

A new voice analysis app may be able to detect worsening heart failure in home care patients prior to hospitalization, a new study has found.

Researchers from The Ohio State University studied the use of a speech analysis app that was previously used to detect fluids in the lung of patients with acute heart failure to study its ability to predict worsening heart failure in patients living at home.

“In this community-based study, a voice analysis app was able to predict most cases of worsening heart failure well in advance, with very few false alarms,” said study author Professor William Abraham of The Ohio State University in Columbus.

The findings were presented on May 21 at Heart Failure 2022, a scientific congress of the European Society of Cardiology.

The study followed 180 home-based patients that were being monitored for heart failure and were taking recommended medications. The app recorded the patients’ speech patterns every day during the study period to evaluate changes in speech caused by fluid buildup in the lungs that may be predictive of heart failure. In a total of 47 heart failure events that occurred in 37 patients, the app accurately predicted 80% of events before symptoms worsened.

“The current standard of care just isn’t good enough for keeping patients with heart failure well and out of the hospital,” said Abraham. “The system tested in this study was able to predict 80% of worsening heart failure in advance, compared to a 10–20% success rate for daily weight monitoring shown in previous studies. In the future, speech analysis, together with other clinical information, could be used to modify treatments before a patient’s condition deteriorates and thereby avoid hospital admission.”

The study found that weight gain and other symptoms often occur too late to allow medical interventions to keep patients out of the hospital. Researchers said further research is needed to determine whether changes in patient management following an alert can help prevent hospitalizations.