The article presents a machine learning model designed to predict mortality rates in heart failure patients using voice biomarkers. The model uses a logistic regression system trained with patients’ speech as input. The integration of NT-proBNP, a diagnostic biomarker in heart failure, significantly improves the model’s predictive accuracy. The model’s implementation in routine patient monitoring could enhance patient outcomes, optimize resource allocation, and advance patient-centered heart failure management.
Publication date: 23 Feb 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2402.13812
