Bridge2AI

@bridge2ai.bsky.social

16 Followers 17 Following

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

ApplyPolygenicScore functionality. Application of ApplyPolygenicScore functions demonstrated in a case study of 1071 individuals from the TCGA database, diagnosed with bladder (BLCA), liver (LIHC), or uterine (UCEC) cancer. A. Recommended workflow when implementing functions provided by ApplyPolygenicScore . A set of preprocessing functions convert polygenic risk score model (PGM) weight files into BED-formatted genomic coordinate files for suggested use in filtering VCF genotype data to desired coordinates. PGM application functions facilitate genetic data importation and weighted sum computation. Visualization functions provide summary information on computed PGSs and phenotype data. Solid arrows indicate required inputs and dotted arrows indicate optional inputs. B. BMI PGS densities, cohort-wide and by categorical phenotypes, computed in the case study cohort and automatically plotted by the create.pgs.density.plot function. C. Correlations of PGSs from (B) with continuous phenotypes automatically plotted by the create.pgs.with.continuous.phenotype.plot function. D. Receiver-operator curves plotted by the analyze.pgs.binary.predictiveness function depicting the performance of the PGSs from (B) to predict obesity status as a sole predictor (top) and with covariates age at diagnosis, sex, and the first 10 principal components of genetic ancestry (bottom). Positive obesity status is defined as BMI ≥ 30. E. From top to bottom: percentile rank of PGSs from (B) for each individual in ascending order, decile and quartile covariate bars, categorical phenotype covariate bars, and continuous phenotype heatmaps.
Nicole Zeltser; Rachel M.A. Dang; Rupert Hugh-White; Daniel Knight; Jaron Arbet; Paul C.
Boutros

Bridge2AI March Events:

Tuesday, March 17th (12:00 PM PT/3:00 PM ET): Bridge2AI Discussion Forum on Emerging ELSI Issues with Dr. Nicholas Evans: Conjoint Analysis of Perspectives on Ethical Tradeoffs in Data Generation Project

Thursday, March 19th (12:00 PM PT/3:00 PM ET): Bridge2AI TRM Novel AI Technology Module Lecture with Dr. William Speier: Multimodal Deep Learning Models for Thyroid Cancer Risk Stratification

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 …

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.