Voice as a Biomarker of Health – Accessing and Applying Data from the Bridge2AI-Voice Program

Presentation Time: 08:30 AM - 11:30 AM

Abstract Keywords: Artificial Intelligence, Patient / Person Generated Health Data (Patient Reported Outcomes), Education and Training, Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Voice is an emerging biomarker for disease diagnosis and treatment planning, offering a non-invasive, cost-effective method for detecting and monitoring health conditions. Advances in AI and biomedical informatics enable the analysis of subtle vocal changes associated with a broad variety of diseases, including neurological, respiratory, and psychiatric disorders. By leveraging machine learning, clinicians and researchers can identify patterns in pitch, tone, and speech rhythm to aid early diagnosis and track disease progression. Integrating voice biomarkers into predictive modeling can enhance precision health paradigms, allowing for real-time monitoring and personalized interventions, ultimately improving patient outcomes and reducing healthcare costs. In response to emerging opportunity provided by the use of such data, the Voice as a Biomarker project (one of four data-generating projects funded under the NIH Bridge2AI Program) is seeking to build and disseminate equitably sourced and high-quality voice and phenotype data sets. This workshop aims to present users with voice physiology, motivations, case studies, standards, analytical tools, and data access options for projects using voice as a biomarker. Participants will learn the promises and challenges of using voice as a biomarker for screening, diagnosis, monitoring, prognosis, and management of health and disease. They will access a synthetic subset of the data set being developed as well as tools for analyzing and using it. They will learn how they can collaborate with other users and access the full data set for their own vocal biomarker research.

Authors:
William Hersh, MD, FACMI, FAMIA - Oregon Health & Science University; Steven Bedrick - Oregon Health & Science University; Andrea Krussel, MA - Washington University in St. Louis; David Dorr, MD, MS, FACMI, FAMIA, FIAHSI - Oregon Health & Science University; Zachary Abrams, PhD - Institute for Informatics at Washington University School of Medicine in St. Louis; Phillip Jenkins, MD - Oregon Health & Science University; Anaïs Rameau, MD - Weill Cornell Medical College;

---