Bridge2AI
LightNews LightNews
banner
bridge2ai.bsky.social
Bridge2AI
@bridge2ai.bsky.social
6 followers 16 following 19 posts
The NIH Common Fund's Bridge to Artificial Intelligence (Bridge2Al) program will propel biomedical research forward by setting the stage for widespread adoption of AI that tackles complex biomedical challenges beyond human intuition. 🔗 bridge2ai.org
Posts Replies Media Videos
bridge2ai.bsky.social
Join us on Tuesday, January 20th for a Bridge2AI Discussion Forum on Emerging ELSI Issues to learn about a value sensitive design approach to creating ethically sourced health data repositories for AI/ML with Dr. Camille Nebeker. 🚀 #AI#ML#VSD#supplychain#heathdata#datascience
Please join us on Tuesday, January 20th 2025 at 12pm-1pm PST/3pm-4pm EST for the discussion forum: “Trust Starts Upstream: Recommendations for creating ethically sourced health data repositories for AI/ML,” by Dr. Camille Nebeker. Creating ethically sourced and trustworthy health data repositories is critical for building trustworthy biomedical and behavioral research infrastructure, especially when such repositories underpin machine learning and AI systems. In Ethical sourcing in the context of health data supply chain management: a value sensitive design approach (Nebeker et al., 2025), we integrate value sensitive design (VSD) with concepts from supply chain management to operationalize ethical values across the stages of developing health data repositories. The resulting framework identifies key actors, values (e.g., traceability, security, equity), and tensions that arise during repository creation and highlights practices such as documenting data provenance, articulating expectations for data stewards, and implementing comprehensive privacy and bias mitigation strategies. During this session, Dr. Nebeker will provide an overview of this framework with a focus on developing a companion checklist that is grounded in VSD and supply chain scaffolding and can be used as actionable guidance in dataset creation. Dr. Camille Nebeker is a professor of public health with appointments in the UC San Diego Design Lab and the Herbert Wertheim School of Public Health and Human Longevity Science. In 2018, Dr. Nebeker co-founded the ReCODE Health center, which is dedicated to conducting cutting edge research to inform ethical practices in digital/AI health research – including machine learning and the use of large language models. The ReCODE Health center supports education and consultation services to guide ethical practices in technology-supported health research across diverse research sectors including traditional academic research and, increasingly, the health technology …
January 7, 2026 at 7:17 PM
bridge2ai.bsky.social
Ethical sourcing is an ongoing, value-driven process that ensures data use aligns with responsible governance and public benefit.
January 7, 2026 at 7:17 PM
bridge2ai.bsky.social
A health data repository is ethically sourced when data are collected, governed, and used through transparent and accountable practices that respect contributors’ rights and expectations, mitigate risks of harm, and document data provenance across the full data lifecycle.
January 7, 2026 at 7:17 PM
bridge2ai.bsky.social
P.S. Registered access is required for featurized versions of the datasets and access to audio data. Email [email protected] for more information about controlled access data. 🚀
December 22, 2025 at 11:06 PM
bridge2ai.bsky.social
For the first time, the Voice team is releasing a pediatric dataset, with 22,620 recordings (24.45 hours total) from 300 pediatric participants ranging from 2-18 years old.

Adult v3 dataset: physionet.org/content/b2ai...
Pediatric v1 dataset: physionet.org/content/b2ai...
Bridge2AI-Voice: An ethically-sourced, diverse voice dataset linked to health information v3.0.0
A dataset of features from voice recordings and metadata to enable the development, benchmarking, and validation of clinically applicable machine-learning models for diagnosing a wide range of health ...
physionet.org
December 22, 2025 at 11:06 PM
bridge2ai.bsky.social
"This release builds on previous iterations, offering researchers a robust resource for developing and validating AI models that explore voice as a biomarker for health"
Dashboard of Bridge2AI Voice dataset V3.0. Dataset overview: 833 adult participants, 33,041 recordings and 157.5 hours of recordings. 300 pediatric participants, 22,620 recordings and 24.45 hours of recordings. Clinical metadata: demographics, severity, treatments, and confounders. Includes charts of acoustic tasks and validated questionnaires, as well of % of cohorts in dataset and clinically validated diagnoses within cohorts.
December 22, 2025 at 11:06 PM
bridge2ai.bsky.social
In this lecture, we’ll explore:
• Why ethical principles must be built into AI-based mental health apps
• How the FUTURE-AI framework defines trustworthy, human-centered AI
• How to apply FUTURE-AI to evaluate a mental health mobile app for robustness
December 15, 2025 at 2:59 PM