Tampa, FL (September 13, 2022) – Artificial intelligence could help doctors diagnose and treat diseases like cancer and depression based on the voice of the patient, with 12 major research institutes launching a landmark. National Institutes of HealthA funded academic project with the potential to establish a voice as a biomarker for use in clinical care.
The University of South Florida in Tampa, Florida, is the lead institution for the project, along 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 included his $3.8 million from the NIH, and his funding for the next three years is contingent on his annual NIH budget by Congress, giving him an overall award of $14 million. could be dollars.
called voice as a biomarker of health, of This project is one of several recently funded by the Bridge2AI program of the NIH Common Fund. The program is designed to use AI to tackle complex biomedical challenges. The Voice Project aims to build a database of diverse, ethically sourced human voices while protecting patient privacy. We will use this data to train a machine learning model to detect disease by detecting changes in human voice. This will allow physicians to combine low-cost diagnostic tools with other clinical methods.
Based on existing literature and ongoing research, the research team identified five disease cohort categories associated with specific diseases with well-recognized unmet needs for voice change. 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 disease, Parkinson’s disease, stroke, ALS)
- Mood and psychiatric disorders (depression, schizophrenia, bipolar disorder)
- Respiratory disease (pneumonia, COPD)
- Speech and speech disorders in children (speech and language delays, autism)
Although preliminary studies using voice data have been promising, limitations to integrating voice as a biomarker in clinical practice include small datasets, ethical concerns about data ownership and privacy, and data bias and diversity. related to the lack of To resolve these, Voice as a biomarker of health The project is creating a large, high-quality, multi-institutional, diverse speech database linked to identity-protected/non-identifiable biomarkers from other data such as demographics, medical imaging, and genomics. increase. Federated learning technology, a new AI framework that allows machine learning models to be trained on data without the data leaving the source, was deployed by Owkin across multiple research centers to ensure privacy-preserving AI across centers. Demonstrate that you can conduct research. Security of sensitive voice data.
With the support of AI experts, bioethicists, and social scientists, the project aims to transform our fundamental understanding of disease and bring innovative new ways of diagnosing and treating disease to clinical settings. intended to be introduced into Because the human voice is low-cost, easy to store, and readily available, using AI to diagnose disease by voice could be a transformative step in precision medicine and accessibility.

Dr. Yael Bensusan. Credit Allison Long/USF Health.
Voice as a biomarker of health The project’s co-principal investigators, Yaël Bensoussan, M.D., Ph.D., USF Health Morsani College of Medicine, and Olivier Elemento, Ph.D., Weill Cornell Medicine, are co-led. The project also includes principal investigators from his ten 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 School of Medicine). AI startup Owkin is deploying his Learning He technology federated to multiple research institutions to protect the security and privacy of sensitive voice data.
“Voice has the potential to be a biomarker for several health conditions. Huge datasets jointly using today’s best technology will help clinicians use voice as a tool for diagnosing diseases and disorders. It will revolutionize the way you use it.”
“The potential for voice and sound to be used in combination with advanced AI algorithms to accurately diagnose specific diseases is amazing. Our future discoveries could revolutionize healthcare.” and continuous voice monitoring could alert doctors to certain conditions, such as infections and neurological disorders, earlier than today.PhD in Physiology and Biophysics from Weill Cornell Medicine. I am getting
“By analyzing subtle changes in the human voice with AI, we hope to help doctors diagnose and treat diseases ranging from cancer to depression. Owkin co-founder and CEO Thomas Clozel MD said:
This project is supported by National Institutes of Health award number: OT2OD032720.
About USF Health
USF Health’s mission is to envision and execute the future of health. This is a partnership of USF Health Morsani College of Medicine, Nursing College, College of Public Health, Taneja College of Pharmacy, School of Physical Therapy and Rehabilitation Sciences, Biomedical Sciences Graduate and Postdoctoral Programs, and USF Health’s. A group of multi-specialty doctors. The University of South Florida is an influential global research university dedicated to student success. No other public university has risen as fast as USF in the U.S. News and World Report National University Rankings in the past decade. For more information, visit health.usf.edu.
About Weill Cornell Medicine
Weill Cornell Medicine is committed to excellence in patient care, scientific discovery, and education of future physicians in New York City and around the world. Weill Cornell Medicine physicians and scientists (faculty members of Weill Cornell Medical College, Weill Cornell Graduate School of Medical Sciences, and Weill Cornell Physician Organization) are dedicated to world-class clinical care and cutting-edge research that connects patients to the latest treatments. It is working. Innovation and prevention strategies. Located at the heart of the Upper East Side science corridor, Weill Cornell Medicine’s strong network of collaborators extends to its parent university, Cornell University. In Qatar, Weill Cornell Medicine-Qtar offers medical degrees from Cornell University. For programs in Tanzania, Haiti, Brazil, Austria and Turkey. Weill Cornell Medicine faculty provide exemplary patient care at New York Presbyterian/Weill Cornell Medical Center, New York Presbyterian Westchester Center for Behavioral Health, New York Presbyterian Lower Manhattan Hospital, New York Presbyterian Queens, and New York Presbyterian Brooklyn Methodist Hospital. Weill Cornell Medicine has also partnered with Houston Methodist. For more information, visit weill.cornell.edu.