USF Health and Weill Cornell Medicine receive inaugural funding in the NIH’s newly launched Bridge2AI initiative and will create an artificial intelligence platform to use speech to diagnose diseases

Tampa FL (September 13, 2022) – Artificial intelligence could soon help doctors diagnose and treat diseases, including cancer and depression, based on the sound of a patient’s voice as 12 leading research institutions set milestone National Health Institute-funded academic project that could establish voice as a biomarker for clinical care.

The University of South Florida in Tampa, FL is the lead institution on the project in collaboration with WeillCornell Medicine in New York City, 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 for the following three years dependent on annual NIH grants from Congress, which could bring the total award to $14 million.

Called voice as a biomarker of health, the The project is one of several recently funded by the NIH Common Fund’s Bridge2AI program, which aims to use AI to address complex biomedical challenges. The Voice project aims to build an ethically sound database of diverse human voices while protecting patient privacy. This data is used to train machine learning models to detect diseases by detecting changes in the human voice, which could provide physicians with an inexpensive diagnostic tool to be used alongside other clinical methods.

Based on the existing literature and ongoing research, the research team identified five categories of disease cohorts for which voice changes have been associated with specific diseases with well-recognized unmet needs. The data collected for this project will focus on the following disease categories:

• Voice Disorders: (Laryngeal Cancer, Vocal Cord Paralysis, Benign Laryngeal Lesions)
• Neurological and neurodegenerative diseases (Alzheimer’s, Parkinson’s, stroke, ALS)
• Mood and psychiatric disorders (depression, schizophrenia, bipolar disorder)
• Respiratory diseases (pneumonia, COPD)
• Pediatric voice and speech disorders (speech and language delays, autism)

Although preliminary work with voice data has been promising, limitations in integrating voice as a biomarker into clinical practice have been linked to small data sets, ethical concerns around data ownership and privacy, bias, and lack of data diversity. To solve this, the Voice as a biomarker of health The project creates a large, high-quality, multi-institutional and diverse language database linked to identity-protected/unidentifiable biomarkers from other data such as demographics, medical imaging and genomics. Federated learning technology — a novel AI framework that allows machine learning models to be trained on data without the data ever leaving its source — is being used by Owkin across multiple research centers to demonstrate that cross-centre AI research among Privacy protection can be done and security of sensitive voice data.

Supported by AI experts, bioethicists and social scientists, the project aims to change our fundamental understanding of diseases and introduce a revolutionary new way of diagnosing and treating diseases into the clinical setting. Because the human voice is inexpensive, easy to store, and readily available, diagnosing diseases by voice using AI could be a transformative step in precision medicine and accessibility.

Voice as a biomarker of health is by Dr. Yaël Bensoussan, MD, of USF Health Morsani College of Medicine and Olivier Elemento, PhD of Weill Cornell Medicine, who are co-principal investigators on the project. The project also includes senior investigators from 10 other universities in North America; Alexandros Sigaras and Anaïs Rameau (Weill Cornell Medicine), Maria Powell (Vanderbilt University), Ruth Bahr (University of South Florida College of Behavioral and Community Sciences), Alistair Johnson (SickKids), Philip Payne (Washington University in St. Louis), David Dorr (Oregon Health & Science University), Jean-Christophe Belisle-Pipon (Simon Fraser University), Vardit Ravitsky (University of Montreal), Satrajit Ghosh (Massachusetts Institute of Technology (MIT)), Kathy Jenkins (Boston Children’s Hospital), Frank Rudzizc and Jordan Lerner-Ellis (University of Toronto), Gaetane Michaud (USF Health Morsani College of Medicine). AI startup Owkin deploys its federated learning technology across multiple research institutions to protect the security and privacy of sensitive voice data.

“Voice has the potential to be a biomarker for multiple health conditions,” said Dr. Bensoussan, assistant professor in the Department of Otolaryngology and Director of the USF Health Voice Center at USF Health Morsani College of Medicine Huge datasets leveraging the best of today’s technology in a collaborative way will revolutionize the way the voice is used used as a tool to assist clinicians in diagnosing diseases and disorders.”

“The potential for using speech and sound along with advanced AI algorithms to accurately diagnose certain diseases is incredible. Our future findings could lead to a healthcare revolution, where continuous voice monitoring could alert physicians to certain conditions, such as infections or neurological disorders, earlier than currently possible,” said Dr. Elemento, Director of the England Institute for Precision Medicine and Professor of Physiology and Biophysics at Weill Cornell Medicine.

“By using AI to analyze minute changes in the human voice, we aim to help doctors diagnose and treat diseases from cancer to depression. Vocal biomarkers will play an increasingly important role in healthcare. We’re excited to use federated learning, our privacy AI framework, to connect the medical world to improve patient outcomes,” said Dr. Thomas Clozel, co-founder and CEO of Owkin.

This project is supported by National Institutes of Health award number: OT2OD032720.

About USF Health

USF Health’s mission is to design and implement the future of health. It is the partnership of USF Health Morsani College of Medicine, College of Nursing, College of Public Health, Taneja College of Pharmacy, School of Physical Therapy and Rehabilitation Sciences, Graduate and Postdoctoral Programs of Biomedical Sciences and USF Health Interdisciplinary medical group. The University of South Florida is a high-impact global research university dedicated to student success. Over the past 10 years, no other public university in the country has risen faster than USF in the US News and World Report national university rankings. Visit health.usf.edu for more information

About Weill Cornell Medicine

Weill Cornell Medicine is committed to excellence in patient care, scientific discovery and the education of future physicians in New York City and around the world. Weill Cornell Medicine’s physicians and scientists—faculties of Weill Cornell Medical College, the Weill Cornell Graduate School of Medical Sciences, and the Weill Cornell Physician Organization—are committed to providing world-class clinical care and cutting-edge research that connects patients with the latest treatments, innovations, and prevention strategies . Located in the heart of the Upper East Side’s scientific corridor, Weill Cornell Medicine’s strong network of collaborators extends to its parent institution, Cornell University; to Qatar, where Weill Cornell Medicine-Qatar offers a medical degree from Cornell University; and to programs in Tanzania, Haiti, Brazil, Austria and Turkey. The Weill Cornell Faculty of Medicine provides exemplary patient care at NewYork-Presbyterian/Weill Cornell Medical Center, NewYork-Presbyterian Westchester Behavioral Health Center, NewYork-Presbyterian Lower Manhattan Hospital, NewYork-Presbyterian Queens and NewYork-Presbyterian Brooklyn Methodist Hospital. Weill Cornell Medicine is also affiliated with Houston Methodist. For more information, see weill.cornell.edu.