App Predicts Heart Failure By Analyzing Speech Patterns

A recent study has found that a new voice analysis app may aid in detecting worsening heart failure for at-home patients before they are hospitalized, reports McKnight’s. The app was previously used to detect fluid buildup in lungs of patients diagnosed with acute heart failure. In the recent study, researchers from The Ohio State University used the app to study speech patterns to help predict worsening heart failure.

Professor William Abraham, study author from The Ohio State University in Columbus, stated, “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.”

About 180 patients participated in the study and all were home-based, taking prescribed medications and monitored for heart failure. Speech patterns were recorded every day in the app and they were evaluated for changes that is caused by fluids in the lungs which may be caused by heart failure. The app accurately predicted 80 percent of the 47 heart failures that occurred in 37 patients before the symptoms became worse.

Professor Abraham stated, “The current standard of care just isn’t good enough for keeping patients with heart failure well and out of the hospital. 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 also concluded that weight gain among other symptoms occur too late to allow timely medical interventions.