Project Grant R21MD019360
- This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program provides $499,997 to Boston University to develop new methods for making AI models in healthcare more transparent, adjustable, and reliable. The project aims to create tools that can help clinicians and researchers understand, diagnose, and correct errors in AI systems used for disease diagnosis from medical images like CT scans and mammograms. The research...
- This Project Grant from the National Institute for Minority Health and Health Disparities, part of the Department of Health and Human Services National Institutes of Health, provides $769,755 to develop an unbiased machine learning tool for the prediction of acute coronary syndrome. The tool aims to minimize bias in predictions between patient demographic groups, as measured by equal opportunity difference and the Zemel statistic, to ensure machine learning algorithms do not exacerbate...
- This $441,404.00 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to the University of California, Berkeley aims to improve the fairness and equity of medical decision-making, both by human clinicians and by algorithmic systems. The research will focus on detecting and mitigating biases in medical decisions related to the allocation of testing resources, healthcare quality assessments, and...
- This Project Grant from the National Science Foundation's Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $300,000 to Arizona State University to develop a machine learning framework for training models across hospitals on electronic health records without sharing patient data. The framework aims to address fairness and mitigate biases by training representation learning algorithms jointly across multiple...
- This $546,385 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering program (CFDA 47.070) will support the development of a machine learning framework for training models across hospitals to address screening and treatment disparities in breast cancer. Specifically, the grant will fund research at Stanford University from September 2022 to August 2026 to create a fair federated representation learning algorithm and framework that can train...
- This Project Grant award from the National Science Foundation Division of Information and Intelligent Systems provides $350,000 in funding to the University of Illinois from September 2022 through August 2026. The award supports research under the Computer and Information Science and Engineering federal grant program (CFDA 47.070). Specifically, the University of Illinois will develop a machine learning framework for training models across hospitals to support precision population health and...
- This $175,000 project grant from the National Science Foundation's Computer and Information Science and Engineering program will fund the development of robust machine learning methods to address data disparities. The University of Michigan will receive funding from March 2022 through February 2024 to create predictive and causal machine learning tools for medical decision making that are reliable despite inaccuracies from underrepresented patient subgroups. Specifically, the university will...
- The National Heart, Lung, and Blood Institute (NHLBI) awarded a $526,890 project grant under the Cardiovascular Diseases Research program (CFDA 93.837) to Mayo Clinic in Rochester, MN. The grant, titled "Addressing Differential Performance by Socioeconomic Status in Artificial Intelligence (AI) Models for Childhood Asthma," aims to develop a framework and tool for measuring differential AI performance and address key limitations in the current approaches for assessing and mitigating AI...
- The National Science Foundation awarded a $625,000 project grant to the President And Fellows Of Harvard College from July 2021 through June 2024 under the Computer and Information Science and Engineering program (CFDA 47.070). The grant funds the "Foundations of Fair AI in Medicine: Ensuring the Fair Use of Patient Attributes" project. This project aims to support investigator-initiated research and education on developing and applying fair artificial intelligence techniques that do...
- This $597,149 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to advance fundamental research in fair algorithmic decision-making. The project at Purdue University will develop novel algorithms and software to facilitate the adoption and evaluation of fair artificial intelligence (AI) systems, with a focus on promoting health equity in applications like Alzheimer's disease research. Key...
INVESTIGATING THE EFFECT OF SYNTHETIC MEDICAL IMAGES ON FAIRNESS IN MEDICAL DEEP LEARNING RESEARCH - PROJECT ABSTRACT THIS GRANT PROPOSAL DESCRIBES A RESEARCH PROJECT THAT AIMS TO IMPROVE THE FAIRNESS OF DEEP LEARNING MODELS FOR PATHOLOGY DETECTION IN CHEST RADIOGRAPHS. HEALTH EQUITY, THE STATE IN WHICH EVERYONE HAS A FAIR AND JUST OPPORTUNITY TO ATTAIN THEIR HIGHEST LEVEL OF HEALTH, IS THE CORNERSTONE OF A FAIR AND JUST SOCIETY. HOWEVER, RACIAL AND ETHNIC MINORITY GROUPS IN THE UNITED STATES EXPERIENCE HIGHER RATES OF ILLNESS AND DEATH ACROSS A WIDE RANGE OF HEALTH CONDITIONS. WITH THE ADOPTION OF ARTIFICIAL INTELLIGENCE (AI) AND DEEP LEARNING (DL) IN HEALTHCARE, THERE IS GROWING CONCERN ABOUT INCREASED DISPARITIES THROUGH THE USE OF ALGORITHMS. TO ADDRESS THIS ISSUE, THE RESEARCH TEAM PROPOSES TO LEVERAGE GENERATIVE MODELING TO BETTER REPRESENT MINORITY GROUPS IN TRAINING DATA. SPECIFICALLY, THEY WILL TRAIN DL MODELS THAT DETECT 14 PATHOLOGIES FROM PUBLICLY AVAILABLE CHEST RADIOGRAPHS WITH PATIENT AGE, SEX AND RACE INFORMATION. THEY WILL USE DENOISING DIFFUSION PROBABILISTIC MODELS (DDPMS) TO CREATE SYNTHETIC DATA AND AUGMENT THE DATASET WITH MORE DIVERSE IMAGES. THE RESEARCH TEAM EXPECTS THAT ENGINEERED IMAGE SYNTHESIS WILL TRAIN DL MODELS THAT RELIABLY DETECT CHEST PATHOLOGIES WITHOUT BEING BIASED ON RACE OR SEX. TO ACHIEVE THIS GOAL, THEY HAVE PROPOSED THREE AIMS: 1) ESTABLISH A BASELINE FOR PATHOLOGY DETECTION IN CHEST RADIOGRAPHS; 2) AUGMENT THE REAL RADIOGRAPHS WITH SYNTHETIC CHEST RADIOGRAPHS REPRESENTING MINORITIES; AND 3) ASSESS THE IMPACT OF SYNTHETIC DATA ON MODEL FAIRNESS. THE PROPOSED RESEARCH LEVERAGES THE POWER OF DL IMAGE GENERATION ALGORITHMS TO POTENTIALLY IMPROVE THE ACCURACY AND FAIRNESS OF PATHOLOGY DETECTION IN CHEST RADIOGRAPHS. ADDITIONALLY, THE GENERATIVE MODEL WILL BE RELEASED PUBLICLY AS A FOUNDATIONAL MODEL FOR RESEARCHERS WITHOUT ACCESS TO THE REQUIRED COMPUTATIONAL RESOURCES TO TRAIN SUCH MODELS. THIS APPROACH HAS THE POTENTIAL TO IMPROVE HEALTHCARE OUTCOMES FOR UNDERSERVED POPULATIONS AND ADVANCE THE FIELD OF FAIRNESS IN AI RESEARCH.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $0 | 9/23/25 | ||
| Not listed | $201.8k | 9/9/25 | ||
| Not listed | $0 | 12/26/24 | ||
| Not listed | $0 | 12/26/24 | ||
| Not listed | $212.9k | 9/22/24 |