App predicts worsening heart failure weeks before symptom onset -- by sound of your voice - Study Finds

A new speech analysis app predicts worsening heart failure weeks before the onset of symptoms. The app, used by heart failure patients at home, recognizes fluid in the lungs an average of 21 days before an unplanned hospitalization or escalation in outpatient drug treatment.

“The current standard of care just isn’t good enough for keeping patients with heart failure well and out of the hospital,” explains study co-author William Abraham, of The Ohio State University, in a statement. “The system tested in this study was able to predict 80 per cent of worsening heart failure in advance, compared to a 10 to 20 per cent 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.”.

Abraham explains that in patients with heart failure, the heart does not pump blood around the body as well as it should.

The study included 180 patients with heart failure taking guideline-recommended medications. At the beginning of the study the participants recorded five sentences on a standard smartphone using the voice analysis app. During the study period, every morning before breakfast patients recorded the same five sentences using the app.

The researchers examined whether the lung congestion alerts predicted heart failure events, defined as at least one worsening symptom which led to hospitalization or escalation in outpatient drug treatment.

They did so by comparing the date of the alert with the dates of subsequent heart failure events. “True alerts” were those issued within a 31-day window before the heart failure event.

Professor Abraham notes that a “true alert” would continue to be issued daily until the heart failure event occurred.

In real life, notifications would be sent to the patient’s physician until it was responded to,” he explains. “Here we followed patients longitudinally for worsening heart failure events and then looked to see if there was an alert prior to that event – i.e.

Alerts not followed by a worsening heart failure event were ‘false alerts.’”.

A total of 49 heart failure events occurred in 37 patients, of which 80 percent were correctly predicted by the app and 20 percent were missed. True alerts were issued an average of 21 days before worsening symptoms.

“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. Weight gain and symptoms occur too late to allow medical interventions that keep patients out of the hospital,” says Abraham. “Future studies will investigate whether changing patient management following an alert, for example by increasing the diuretic dose to get rid of excess fluid, can prevent hospitalizations.”.