Detecting Heart Failure Through Voice Analysis using Self-Supervised Mode-Based Memory Fusion

• DOI: 10.21437/interspeech.2022-643
• Publication Date: 2022-09-16T15:42:06Z
• Authors: Darshana Priyasad; Andi Partovi; Sridha Sridharan; Maryam Kashefpoor; Tharindu Fernando; Simon Denman; Clinton Fookes; Jia Tang; David Kaye
• Keywords: Chronic Heart Failure; 0202 electrical engineering, electronic engineering, information engineering; Geometric Deep Learning; 02 engineering and technology; Data Fusion; Mode Based Explicit Memory; 004

Congestive Heart Failure (CHF) is a progressive disease that affects millions of people worldwide, severely impacting their quality of life. Missed detection of CHF and its progression affects life expectancy, thus it is critical to develop applications to continuously monitor CHF symptoms and disease progression in a patient-centric and cost-effective manner. This paper focuses on a novel non-invasive technique to identify CHF using patients' speech traits. Pulmonary congestion and breathlessness is the most common symptom of heart failure and one of the major contributors to hospitalisation. Since pulmonary congestion results in impairment of a patient's voice, we propose a novel, non invasive method for monitoring CHF through analysis of the patient's speech. We also introduce a new balanced dataset, containing voice recordings from both healthy participants and participants diagnosed with CHF, which contains voice alterations reflective of CHF status. We propose a novel deep machine learning architecture based on mode driven memory fusion for CHF recognition from audio recordings of subject's speech. We have achieved 90% accuracy under a subject-independent evaluation setting, highlighting the applicability of such methods for tele-health and home monitoring applications.