Novel Speech Recognizing App may help Predict HF by recognising fluid buildup in lungs: Study
Key findings of the study:
- The researchers analyzed a total of 1,484 recordings and found that the discharge recordings were successfully tagged as distinctly different from baseline (wet) in 94% of cases, with distinct differences shown for all 5 SMs in 87.5% of cases.
- The largest change from baseline was documented for SM2 (218%).
- As a complementary test, they further evaluated 72 untagged admissions and the discharge recordings from 9 patients and demonstrated for all 5 SMs. The system successfully segregated the recordings into 2 distinct unknown sets, which, when unblinded, were shown to correspond to the 2 different clinical statuses (ie, admission/discharge), with the exception of only 1 recording (2.2%).
The current observations provided substantial proof of concept that this novel automated speech processing and analysis approach can reliably identify these differences between 2 states of pulmonary congestion in patients with HF at the time of hospitalization for ADHF and following a full course of inpatient treatment.
The authors concluded, “Automated speech analysis technology can identify voice alterations reflective of HF status. This platform is expected to provide a valuable contribution to in-person and remote follow-up of patients with HF, by alerting to imminent deterioration, thereby reducing hospitalization rates.”
In an accompanying editorial, Dr Ravindra and Dr Kao wrote, “ Active speech analysis as described by Dr Amir et al. is an important advance toward expanding the tools available to assess patients with HF. Although nascent, the use of commonly available mobile technologies suggests the potential for wide use compared with highly invasive strategies requiring dedicated hardware. Extensive development and validation are required before clinical use, but success in a use case such as HearO may pave the way for even more convenient and generalizable strategies.”
For further information:
Heart failure (HF) is a progressive condition that affects approximately 26 million people worldwide. Most patients with HF present to the hospital with fluid retention, which manifests as worsening dyspnea caused by pulmonary edema. In a recent study, researchers have developed a novel mobile app, HearO that detects changes in speech which predicts clinical congestion in patients with HF. The study findings were published in the journal JACC: Heart Failure on December 8, 2021.
Recent advances in speech, voice, and sound analysis enabled the identification of speech features of clinical significance. Various speech processing algorithms have been developed to use such features in screening for depression, pneumonia-asthma, coronary artery disease, and an autism spectrum disorder. Pulmonary edema is the main cause of heart failure (HF)−related hospitalizations. It is an important predictor of poor prognosis after discharge. Frequent monitoring is often recommended, but signs of decompensation are overlooked. Recently, Dr Offer Amir and his team conducted a study to assess the performance of an automated speech analysis technology in detecting pulmonary fluid overload in patients with acute decompensated heart failure (ADHF). They distinguishing between ADHF on admission ("wet") versus at discharge ("dry") by using a novel speaker verification, speech processing, and analysis technology, implemented within a proprietary Smartphone application (app) (HearO Cordio Medical Ltd, Or Yehuda, Israel).
In this observational open-label study, the researchers included a total of 40 patients with ADHF and recorded 5 sentences, in 1 of 3 languages, using HearO app, upon admission (wet) to and discharge (dry) from the hospital. HerO app is a proprietary speech processing application that was used to record and digitize the patients' speech. The researchers uploaded the speech files to the server, where they were stored and analyzed. Recordings were analyzed for 5 distinct speech measures (SMs), each a distinct time, frequency resolution, and linear versus perceptual (ear) model. They further calculated the mean change from baseline SMs.
Disclaimer: This site is primarily intended for healthcare professionals. Any content/information on this website does not replace the advice of medical and/or health professionals and should not be construed as medical/diagnostic advice/endorsement/treatment or prescription. Use of this site is subject to our terms of use, privacy policy, advertisement policy. © 2024 Minerva Medical Treatment Pvt Ltd