USF Health Voice Center: Landmark Research to Establish Voice as a Clinical Care Biomarker

Through a collaboration with USF Health, Tampa General Hospital patients have access to the USF Health Voice Center, led by Dr. Yaël Bensoussan, a fellowship-trained laryngologist. A multi-specialty center of excellence, specialists at the USF Voice Center offer cutting-edge treatments for patients with voice, swallowing and upper airway disorders.

LED BY PIONEERING VOICE AI RESEARCHER

Dr. Bensoussan has advanced expertise in voice, swallowing and upper airway evaluation and treat- ment. She has researched machine learning models to study the acoustic features of voice and detect cues that can predict conditions such as throat cancers, neurological disorders and even depression.

Dr. Bensoussan co-founded the VoiceCollab.ai, a multidisciplinary and multi-institutional collaborative of researchers interested in linking voice to various pathologies by using machine learning algorithms. Her previous work includes the application of machine learning to detect gender to provide gender-affirming voice care to transgender patients. Dr. Bensoussan’s team is currently working on using acoustic voice signals to detect throat cancers and create accessible tools for clinicians working in settings with fewer resources.

LANDMARK PROJECT TO ESTABLISH VOICE AS A CLINICAL CARE BIOMARKER

USF serves as the lead institution on a data generation project funded by the National Institutes of Health’s (NIH) Common Fund’s Bridge to Artificial Intelligence (Bridge2AI). This multi-institution project brings together medical, voice, AI, engineering and ethics experts to create a human voice database using privacy-preserving AI, giving doctors a new tool for diagnosing conditions known to have associations with voice alterations.

In collaboration with Weill Cornell Medicine in New York City, the project involves USF Health and 10 other institutions in the United States and Canada, and French-American AI biotech startup Owkin. The first year of the project includes $3.8 million from the NIH, with subsequent funding over the following three years contingent upon annual NIH appropriations by Congress that could bring the overall award to $14 million.

Called Voice as a Biomarker of Health, the project is one of several recently funded by the Bridge2AI program. Using the project’s data, machine learning models will be trained to spot diseases by detecting changes in the human voice, which could empower doctors with a low-cost diagnostic tool to be used alongside other clinical methods. Based on existing literature and ongoing research, the research team has identified five disease cohort categories for which voice changes have been associated with specific diseases with well-recognized, unmet needs. Data collected for this project will center on the following disease categories:

• Voice disorders (laryngeal cancers, vocal fold paralysis, benign laryngeal lesions)

• Neurological and neurodegenerative disorders (Alzheimer’s, Parkinson’s, stroke, ALS)

• Mood and psychiatric disorders (depression, schizophrenia, bipolar disorders)

• Respiratory disorders (pneumonia, COPD)

• Pediatric voice and speech disorders (speech and language delays, autism)

Supported by AI experts, bioethicists and social scientists, the project aims to transform fundamental understanding of diseases and introduce a revolutionary new method of diagnosing and treating diseases into clinical settings. As the human voice is low-cost, easy to store and readily available, diagnosing voice diseases through AI could prove a transformative step in precision medicine and accessibility.

Voice as a Biomarker of Health is co-led by Dr. Bensoussan and Olivier Elemento, PhD, from Weill Cornell Medicine, who are co-principal invest- igators for the project. “Voice has the potential to be a biomarker for several health conditions,” Dr. Bensoussan said. “Creating an effective frame- work that incorporates huge datasets using the best of today’s technology in a collaborative manner will revolutionize the way that voice is used as a tool for helping clinicians diagnose diseases and disorders.”

USF serves as the lead institution on a data generation project funded by the National Institutes of Health’s (NIH) Common Fund’s Bridge to Artificial Intelligence (Bridge2AI). This multi-institution
project brings together medical, voice, AI, engineering and ethics experts to create a human voice database using privacy-preserving AI, giving doctors a new tool for diagnosing conditions known to have associations with voice alterations.