Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Multimodal, Multi-scale Framework for Ethical AI Model Development

Award Number: OT2OD038065
ORGANIZATION: OFFICE OF THE DIRECTOR, NIH
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: OTHER
PERIOD OF PERFORMANCE START DATE: 06/30/2025
PERIOD OF PERFORMANCE END DATE: 06/29/2027

Group Awards By:

View Award Description

Multimodal, Multi-scale Framework for Ethical AI Model Development - Current unimodal approaches to attain precision medicine have been difficult to adopt at scale due to cost of tests, and variable clinical output that results in undertreatment or overtreatment of some patients. Multimodal approaches for precision medicine are advancing rapidly due to the growing availability of varied data sources and advanced AI systems, with demonstrated ability to capture health complexity of many patients. However, multimodal predictive models are limited by lack of standardized approaches to tackle data heterogeneity, including limited options for handling missing data. Our proposal aims to address these gaps by developing novel digital phenotypes through the integration of multimodal datasets—imaging, pathology and electronic health records (EHR). Leveraging advanced techniques in radiopathomics extraction, data fusion, novel graph architectures, and unsupervised clustering, we aim to discover biologically relevant patient populations to improve risk stratification and treatment optimization. To achieve this, we will first develop an open-source fusion framework for multimodal data integration. This robust framework will incorporate tools for data harmonization, radiopathomics feature extraction, multimodal data embedding, and graph neural networks. We will apply this framework to discover biologically relevant digital phenotypes for breast and prostate cancer, and train phenotypespecific risk prediction models which will be robustly validated at 4 external sites. Our proposal emphasizes an open-source AI framework that incorporates privacy and accountability throughout the model development process with a goal of ensuring reproducibility and scale across different dataset types and diseases. We will adopt an iterative model co-development approach, engaging multidisciplinary stakeholders, including physicians, collaborators, and industry partners, to continuously refine our data and models. This co-design process ensures that our models remain clinically relevant to actualize the promise of multimodal data for precision medicine.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $1,449,052 )
2026	2026	EMORY UNIVERSITY	201 DOWMAN DR NE	ATLANTA	GA	30322	DEKALB	USA	Trans-NIH Research Support	002	1	6/15/2026	SUPPLEMENT FOR EXPANSION	$1,449,052
2026	2025	EMORY UNIVERSITY	201 DOWMAN DR NE	ATLANTA	GA	30322	DEKALB	USA	Trans-NIH Research Support	001	1	6/12/2026	NEW	$0
2026	2025	EMORY UNIVERSITY	201 DOWMAN DR NE	ATLANTA	GA	30322	DEKALB	USA	Trans-NIH Research Support	000	1	2/20/2026	NEW	$0
														Subtotal = $1,449,052

Issue Date FY: 2025 ( Subtotal = $1,464,652 )
2025	2025	EMORY UNIVERSITY	201 DOWMAN DR NE	ATLANTA	GA	30322	DEKALB	USA	Trans-NIH Research Support	000	1	6/30/2025	NEW	$1,464,652
														Subtotal = $1,464,652

Grand Total All Awards = $2,913,704

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Multimodal, Multi-scale Framework for Ethical AI Model Development

Award Number: OT2OD038065

ORGANIZATION: OFFICE OF THE DIRECTOR, NIH

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: OTHER

PERIOD OF PERFORMANCE START DATE: 06/30/2025

PERIOD OF PERFORMANCE END DATE: 06/29/2027

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer