Potential for using speech patterns in cardiovascular disease diagnosis: a systematic review

Authors:
Publisher website
Google Scholar
Abstract
Aim . To determine the potential of using acoustic speech signal analysis parameters and speech biomarkers in the diagnosis and monitoring of cardiovascular diseases. Material and methods . A search was conducted in accordance with the requirements and guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) in the PubMed, Google Scholar, ClinicalTrials, CyberLeninka, and eLibrary databases. The review included 14 original studies that analyzed the voice parameters of patients with cardiovascular diseases (heart failure (HF), pulmonary hypertension (PH), and coronary artery disease (CAD)). Static acoustic features and dynamic changes during therapy were examined. Parameters were compared between patients and healthy controls, as well as before and after treatment. Results . Studies examining changes in speech signal parameters in patients with HF have shown that speech indices and acoustic features differ during decompensation compared to discharge. Outpatient studies have noted independent associations with speech rate in patients with HF and/or PH. In studies examining the diagnosis of CAD, voice biomarkers are associated with coronary atherosclerosis based on coronary angiography and with incident coronary events during follow-up. Conclusion . The current systematic review demonstrated that acoustic speech analysis and the resulting voice biomarkers represent available tools for remote monitoring of cardiovascular diseases. However, for implementation into routine practice, multicenter studies and standardization of speech signal analysis methods are necessary. Its validation could form the basis for remote screening and diagnosis, as well as dynamic follow-up monitoring of patients with cardiovascular diseases.

This publication has 14 references indexed in Scilit: