Improving diagnosis accuracy using AI models
Official title: Developing and Evaluating Multi-Modal Clinical Diagnostic Reasoning Models for Automated Diagnosis Generation
Funded at University of Colorado Denver · NIH-11170047 · Data updated 2026-11-12
This study is working on smart computer programs that help doctors make better diagnoses by looking at patient health records, so they can avoid mistakes and provide you with the best care possible.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Colorado Denver NIH-funded |
| Lab location | 1 site (Aurora, UNITED STATES) |
| Project start | September 1, 2024 |
| Project end | August 31, 2027 |
| Funding year | 2024 |
| Award (this year) | $248,999 |
| NIH project number | 4R00LM014308-02 |
| Project ID | NIH-11170047 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients who have experienced diagnostic errors or are at risk of misdiagnosis due to complex medical conditions.
✕Less likely to help
Patients with straightforward diagnoses or those who do not utilize electronic health records may not benefit from this research.
What this research studies
This research focuses on developing advanced AI models to enhance the accuracy of clinical diagnoses by analyzing electronic health records (EHR). It aims to address common diagnostic errors caused by cognitive biases and information overload that clinicians face. By utilizing clinical Natural Language Processing (cNLP), the project seeks to automate the analysis of EHR data, helping healthcare providers make more informed decisions. The approach involves synthesizing multi-modal data and reasoning over a vast medical knowledge base to generate accurate diagnoses.
Why it matters
Potential benefit: If successful, this research could significantly reduce diagnostic errors, leading to better patient outcomes and potentially saving lives.
How similar studies have gone: Previous research has shown promise in using AI and cNLP for improving diagnostic accuracy, indicating that this approach could be effective.
Where this research is happening
-
University of Colorado Denver
Aurora, United States Active
Researchers
- Principal investigator: Gao, Yanjun — University of Colorado Denver
- Study coordinator: Gao, Yanjun
Related research
Other NIH-funded projects on the same topics.
-
Understanding how alcohol and how couples talk about consent affect intimate partner sexual violence
This project studies how alcohol use and how partners communicate about consent influence intimate partner sexual violence among sexual minority and heterosexual couples.
-
How proteins change and move as heart cells develop
This grant aims to map how protein turnover changes as human iPSCs turn into cardiomyocytes and other cell types, using new labeling and mass-spectrometry methods.
-
Center for Health, Work and Environment
A national center dedicated to improving health in people who work, by studying how jobs affect well-being and safety.
-
Subtyping Core for Research on the Causes of Type 2 Diabetes (SCORE-T2D)
A new U01 grant from a university research team aims to understand why Type 2 diabetes differs so much between people and how to tailor prevention and treatment.
-
Expanded antibody-based clues to TB risk in people with HIV
A clinician-scientist seeks to understand how antibodies in people with HIV may drive the progression from latent TB to active TB, with the goal of identifying clues that could guide future care.
-
Human Trisome Project in Latin America Network
A large, multi-site study of people with Down syndrome across Latin America to better understand health and aging in DS.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.