Columbus, Ohio- Could the sound of your voice reveal hidden heart problems? A new speech analysis app predicts worsening heart failure weeks before symptoms appear. 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 of outpatient drug treatment.
“The current standard of care is simply not good enough to keep patients with cardiac arrest well and out of the hospital,” says study co-author William Abraham of Ohio State University in a statement. “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, combined with other clinical information, could be used to modify treatments before a patient’s condition deteriorates and thus avoid hospitalization.
Abraham explains that in patients with heart failure, the heart does not pump blood around the body as well as it should. The liquid is poorly eliminated by the kidneys and excess fluid accumulates in the lungs or legs. Pulmonary congestion is a common cause of hospitalization and can be life threatening.
Currently, pulmonary congestion is monitored by asking patients to weigh themselves daily and report any substantial gain. Patients are also asked to report worsening symptoms such as shortness of breath, the need to raise their head at night to breathe comfortably and sleep, and swelling in the feet or ankles.
The study included 180 patients with heart failure taking guideline-recommended medications. At the start of the study, participants recorded five sentences on a regular smartphone using voice analysis app. During the study period, every morning before breakfast patients recorded the same five phrases using the app.
The app compared each day’s recordings with the original versions and alerted research staff when it detected lung congestion. “The system establishes a baseline for each patient during a period of stability,” says Abraham. “It then detects changes in speech over time that indicate the presence of fluid in the lungs.”
Researchers examined whether lung congestion alerts predicted heart failure events, defined as at least one worsening symptom that resulted in hospitalization or escalation in outpatient drug treatment. They did this 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 prior to the heart failure event. “False alerts” were those issued outside the 31-day window preceding an event.
Professor Abraham notes that a “true alert” would continue to be issued daily until the heart failure event occurs.
“In this study, the alerts were not taken into account by the clinicians since the objective was to determine the diagnostic performance of the tool. In real life, notifications would be sent to the patient’s doctor until they receive a response,” he explains. “Here, we followed the patients longitudinally for worsening heart failure events then looked to see if there had been an alert prior to this event – i.e. a “true alert”. If there was no alert, the system could not predict the event. Alerts not followed by an aggravation of the heart failure event were “false alerts”.
During the study, patients provided recordings for an average of 512 days. A total of 49 heart failure events occurred in 37 patients, of which 80% were correctly predicted by the app and 20% were missed. True alerts were issued an average of 21 days before symptoms worsened. Each patient received a false alarm every 4.8 months on average, resulting in an average of 2.5 false warnings each year.
“In this community study, a voice analytics 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 for enable medical interventions that prevent patients from going to the hospital,” says Abraham. “Future studies will examine whether changing patient care following an alert, for example increasing the dose of diuretics to get rid of excess fluid, can prevent hospitalizations.”
The findings were presented at Heart Failure 2022, a scientific congress of the European Society of Cardiology (ESC) in Madrid, Spain.
Stephen Beech, editor of the South West News Service, contributed to this report.
#App #predicts #worsening #heart #failure #weeks #symptoms #sound #voice