Abstract
Despite major advances in recent years, the timely detection and prevention of incipient congestion in patients with chronic heart failure remains challenging. Most approaches are either invasive or require the acquisition of additional hardware. Leveraging voice analysis for the purposes of diagnosing, predicting risks, and telemonitoring clinical outcomes of patients with heart failure represents a promising, cost-effective, and convenient alternative compared with hitherto deployed methods. To expand this field, close collaboration of several disciplines of medicine and computer science is an obligatory requirement. The current review aims to lay out the state-of-the-art in this quickly advancing area of research. It elucidates the foundation for voice feature extraction, describes the prospective capabilities of this evolving technology, and outlines the challenges involved in identifying vocal biomarkers both in general and in the context of heart failure.