Automated voice analysis using a proprietary smartphone app can detect pulmonary fluid overload with high accuracy in patients admitted with acute decompensation cardiac arrest (ADHF), a new study suggests. The researchers envision the technique as a potential warning system for impending decompensation in high-risk patients.
the speech analysis app (HearOCordio Medical) identified voice alterations suggestive of changes in fluid status in these hospitalized patients, based on the comparison of specific phrases spoken on admission and discharge.
“Speech analysis technology represents a promising new approach for the detection of volume overload in patients with heart failure and other edematous disorders. If confirmed, this technology can easily be incorporated into the daily assessment of these patients,” William Abraham, MD, Division of Cardiovascular Medicine, Ohio State University Wexner Medical Center, Columbus, said. lecoeur.org | Medscape Cardiology.
“The technology can provide an early warning system indicating fluid retention and, together with the totality of clinical assessments, enable a better understanding of patients’ clinical status,” said study co-author Abraham. . published December 8 to JACC: Heart Failure with Offer Amir, MD, Hadassah Medical Center, Jerusalem, Israel, as lead author.
Other studies have suggested a relationship between water retention and vocal cord vibration. in research published last year, the authors note, a voice biomarker derived from patients’ recorded speech correlated with hospital admission and death in patients with congestive heart failure.
The current study included 40 adults requiring hospitalization for ADHF. Each recorded five sentences three to four times using the HearO speech processing and analysis app when “wet” on the day of hospital admission and when ” dry” on the day of discharge from the hospital. The app is designed to distinguish between the two states based on differences in five separate voice measurements.
A total of 1484 recordings were analyzed to reveal significant differences in voice analysis results from application to admission versus discharge.
Exit recordings were successfully labeled as different from admission recordings in 94% of cases, with distinct differences for all five speech measures in 87.5% of cases, the authors report.
“This first study using a new voice recognition system in patients demonstrated its ability to identify voice alterations reflecting changes in clinical ADHF status, and showed significant changes in measures of speech between the congested (intake) and decongested (output) states,” the authors write.
The system, they add, has the potential to help assess pulmonary congestion in patients with heart failure in other settings, “although confirmation of performance in more subtly different clinical states is still required.”
For example, “if further validated in studies of outpatients with chronic HF, this speech-based analysis could provide a simple, non-invasive approach for remote monitoring and management of these patients” , writes the group.
Although the technology is currently experimental, “ongoing and future studies could make it widely available,” Abraham said.
A link editorial says that active speech analysis as described in this study represents “an important step towards expanding the tools available to assess patients with HF.”
A potential limitation of this technology is that it requires the patient to launch the app and read the appropriate sentence to be useful, observe editorial writers, Neal Ravindra, PhD, Yale School of Medicine, New Haven, Connecticut, and David Kao. , MD, University of Colorado School of Medicine, Aurora. They suggest that engagement with the app might be “sub-optimal”.
They also warn that “an abundance of disturbing signals” generated by the app could complicate clinical workflows already involved.
“If the use of smartphones in ADHF management, as with the HearO app, is to be scaled up,” Ravindra and Kao write, “it will be important to discern what action to take based on the nature of the signal to enable accurate volume assessments and assessments on a specific schedule and on an ad hoc basis, without compromising quality of care and contributing to provider burnout.”
They propose that “extensive development and validation is required before clinical use, but success in a use case such as HearO may pave the way for even more practical and generalizable strategies.”
The study was funded by Cordio Medical Ltd, for which Amir reveals to have been a paid consultant; several other co-authors disclose relationships with the company. Abraham reveals he has received consulting fees from Abbott, Boehringer Ingelheim, CVRx, Edwards Lifesciences and Respicardia; receive a salary from V-Wave Medical; and receive research support from the National Institutes of Health/National Heart, Lung, and Blood Institute. Kao reveals that he served as an advisor for Codex Health. Ravindra disclose no relevant financial relationships.