Sarah Dudgeon, MPH, is a PhD Candidate in the Computational Biology and Bioinformatics program at Yale University. Here, she presents a lightning talk on “Quantum Clique Detection in Biological Graph Networks”. This talk was recorded at the 2024 AI in Medicine Symposium, hosted by the Section of Biomedical Informatics & Data Science.
USF Health Leads in Voice AI Training
USF Health and the USF AI+X Institute are advancing voice AI research with their first course on voice as a health biomarker. Led by Dr. Yael Bensoussan and the NIH-funded Bridge2AI-Voice program, the initiative trains students to analyze voice data and develop AI models for disease diagnosis, offering hands-on experience through the Voice AI Summer School.
Health and engineering students at the University of South Florida are learning how voices and artificial intelligence could help diagnose medical conditions.
Your Voice as a Health Window
Speaking and breathing engage multiple systems, offering clues to health. Conditions like depression, Parkinson’s, and cancer can alter voice and speech patterns, aiding diagnosis. Dr. Yael Bensoussan’s team is creating the largest voice-health database to enhance diagnostic tools. Though full phone-based health assessments aren’t available yet, noticing persistent voice changes could signal early health issues.
Voice as a Biomarker: Pioneering Dataset Release
USF Health and Weill Cornell Medicine have released the first clinically validated voice dataset as part of the NIH-funded Voice as a Biomarker of Health project. Featuring over 12,500 recordings from 306 participants, this dataset aims to advance AI-driven healthcare by enabling disease diagnosis through voice analysis. Part of the Bridge2AI program, the project addresses challenges in data security, bias, and standardization, setting a new benchmark for AI in health research.
Voice as a Biomarker: Pioneering Dataset Release
USF Health and Weill Cornell Medicine have released the first clinically validated voice dataset as part of the NIH-funded Voice as a Biomarker of Health project. Featuring over 12,500 recordings from 306 participants, this dataset aims to advance AI-driven healthcare by enabling disease diagnosis through voice analysis. Part of the Bridge2AI program, the project addresses challenges in data security, bias, and standardization, setting a new benchmark for AI in health research.
Join the 2024 Bridge2AI Voice Symposium
The Bridge2AI Voice Symposium is an interactive event exploring the intersection of people, ethics, and data in AI/ML. Submit your work and connect with a global network of patients, scientists, clinicians, and industry leaders. Together, let’s shape the future of AI. See you in sunny Tampa, Florida, April 22–24!
AI-READI Research Internship
Part of the NIH Bridge2AI program, the AI-READI internship builds skills at the intersection of AI, data science, and biomedical research. It includes a two-week bootcamp at UC San Diego, mentored research projects nationwide, and a year-end symposium. Monthly stipends range from $2,200 (predoctoral) to $4,500–$5,500 (postdoctoral), with a focus on supporting underrepresented groups.
November 8, 2024
The AI-READI project aims to create an ethically-sourced, high-quality dataset to advance AI/ML research in type 2 diabetes mellitus (T2DM). By collecting multimodal data from a diverse cohort of 4,000 participants, it seeks to provide insights into disease trajectories and pathways to health. The project will set a standard for equitable, inclusive AI/ML research while enabling breakthroughs in understanding and reversing T2DM.
November 27, 2024
The Bridge2AI-Voice project aims to advance AI research on voice as a health biomarker for conditions like dementia and mood disorders. Its initial release, Bridge2AI-Voice v1.0, includes 12,523 derived recordings from 306 participants, along with demographic and clinical data, ensuring ethical use by excluding original voice recordings.
November 13, 2024
AIM-AHEAD Traineeship in Advanced Data Analysis using the Bridge2AI AI/ML for Clinical Care Network
The AIM-AHEAD Bridge2AI for Clinical Care Training Program is intended to increase researcher diversity in AI/ML by leveraging Bridge2AI AI/ML for Clinical Care Network data and tools.
October 21, 2024
Congratulations to Dr. Christopher G Chute, MD, DrPH, on his election to the National Academy of Medicine.Dr. Chute is joined by 99 other new members of the Academy, recognized for their professional achievement and commitment to service in the fields of health and medicine.
May 29, 2024
The Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) program seeks to increase the participation and engagement of the researchers and communities currently underrepresented in AI/ML modeling and applications through mutually beneficial partnerships.
April 4, 2023
The NIH Common Fund issued two new notice of funding opportunity announcements from the Common Fund Data Ecosystem (CFDE): OTA-23-004 and RFA-RM-23-002. The purpose of these funding announcements is to establish the CFDE Data Resource Center, Knowledge Center, and Integration and Coordination Center.
April 01, 2024
Here & Now’s Scott Tong talks with Dr. Yael Bensoussan. She is one of the leaders of a study on Voice AI called Bridge2AI funded by the National Institutes of Health. She also directs the Health Voice Center at the University of South Florida.
February 23, 2024
With deep learning methods revolutionizing life sciences, researchers bet on de novo proteins and cell mapping models to deliver customized precision medicines.
September 13, 2022
The National Institutes of Health will invest $130 million over four years, pending the availability of funds, to accelerate the widespread use of artificial intelligence (AI) by the biomedical and behavioral research communities.
September 15, 2021
The U.S. Department of Energy (DOE) announced $1 million for a one-year collaborative research project to develop artificial intelligence (AI) and machine learning (ML) algorithms for biomedical, personal healthcare, or other privacy-sensitive datasets.