Improving AI algorithms for better diagnosis in medicine
Official title: A physiologically-focused approach to training multi-modality AI algorithms in medicine
Funded at University of California, San Francisco · NIH-10687584 · Data updated 2026-11-12
This study is working on smart computer programs that can look at different types of medical information all at once to help doctors make better diagnoses for conditions like heart failure, so patients can get more accurate insights about their health.
Quick facts
| Grant type | NIH-funded research |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of California, San Francisco NIH-funded |
| Lab location | 1 site (San Francisco, United States) |
| Project start | September 6, 2023 |
| Project end | August 31, 2026 |
| Funding year | 2023 |
| Award (this year) | $1,453,500 |
| NIH project number | 1DP2HL174046-01 |
| Project ID | NIH-10687584 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients with heart failure or other conditions requiring multi-faceted diagnostic approaches.
✕Less likely to help
Patients with conditions that can be diagnosed effectively using single-modality tests may not benefit from this research.
What this research studies
This research focuses on developing advanced artificial intelligence (AI) algorithms that can analyze multiple types of medical data simultaneously, rather than just one at a time. By mimicking how expert physicians integrate information from various sources, the project aims to enhance the accuracy and complexity of medical diagnoses, particularly for conditions like heart failure. The approach involves training these AI systems to understand and process physiological data in a more holistic manner, which could lead to better patient outcomes. Patients may benefit from improved diagnostic tools that provide more comprehensive insights into their health.
Why it matters
Potential benefit: If successful, this research could lead to more accurate and timely diagnoses for patients with complex medical conditions.
How similar studies have gone: Other research has shown promise in using multi-modal AI approaches, indicating potential for success in this novel application.
Where this research is happening
-
University of California, San Francisco
San Francisco, United States Active
Researchers
- Principal investigator: Tison, Geoffrey H — University of California, San Francisco
- Study coordinator: Tison, Geoffrey H
Related research
Other NIH-funded projects on the same topics.
-
How cancer cells use exosomes to evade the immune system
This study is looking at how cancer cells use tiny bubbles called exosomes to hide proteins that can keep your immune system from fighting the tumor, and by figuring this out, the researchers hope to help doctors understand why some people respond well to cancer treatments while others don’t, ultimately aiming to creat
-
Reducing harm from smoking using electronic cigarettes
This study is looking at whether using electronic cigarettes can be a safer option for people who smoke traditional cigarettes, by comparing the health effects and exposure to harmful substances between the two.
-
Understanding how knee pain and knee obesity and muscle loss affect knee osteoarthritis
This project looks at how knee swelling, excess knee fat, and muscle loss relate to pain and structural changes in knee osteoarthritis in adults.
-
Cutaneous opioid signals in skin inflammation
A mentor-identified clinician-researcher at UCSF is studying how natural skin opioids regulate itch and pain in inflammatory skin conditions like eczema and hidradenitis, with plans to map where these opioids come from and how they affect skin nerves.
-
Pooling international data to understand long-term bisphosphonate use and atypical femur fractures
This project combines large patient datasets from multiple countries to understand how long-term bisphosphonate use relates to rare hip and thigh bone fractures, helping doctors and patients make safer treatment choices.
-
Airway cell and immune cell talks in lung transplant failure
This grant tests how airway cells and immune cells interact to drive chronic rejection after lung transplant, with the goal of slowing or preventing scar-like damage.
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.