Using machine learning to improve detection of pulmonary embolism
Official title: Clinical Decision Support for Assessing Pulmonary Embolism using Machine Learning
Funded at Minnesota Healthsolutions Corporation · NIH-10576273 · Data updated 2026-11-12
This study is working on a new software that helps doctors quickly and accurately find blood clots in the lungs using routine CT scans, making it easier for patients to get the right treatment faster.
Quick facts
| Grant type | Sbir 2 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Minnesota Healthsolutions Corporation NIH-funded |
| Lab location | 1 site (Saint Paul, United States) |
| Project start | February 17, 2022 |
| Project end | January 31, 2026 |
| Funding year | 2023 |
| Award (this year) | $935,869 |
| NIH project number | 5R44HL152825-03 |
| Project ID | NIH-10576273 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients undergoing pulmonary CT angiograms who are at risk for pulmonary embolism.
✕Less likely to help
Patients who do not require a CT angiogram or those with conditions unrelated to pulmonary embolism may not benefit from this research.
What this research studies
This research aims to develop a software tool that utilizes machine learning to automatically detect and stage pulmonary embolisms (PEs) from routine pulmonary CT angiograms. By integrating this tool into the existing radiology workflow, it seeks to enhance the accuracy and speed of PE diagnosis, which is crucial for timely treatment. The project combines advanced technology with clinical expertise to address the variability in detection rates among radiologists and improve patient outcomes in emergency departments.
Why it matters
Potential benefit: If successful, this research could lead to faster and more accurate diagnoses of pulmonary embolism, potentially saving lives and improving treatment outcomes.
How similar studies have gone: Other research has shown success in using machine learning for medical imaging, indicating a promising potential for this approach in detecting pulmonary embolism.
Where this research is happening
-
Minnesota Healthsolutions Corporation
Saint Paul, United States Active
Researchers
- Principal investigator: Kramer, Kevin M. — Minnesota Healthsolutions Corporation
- Study coordinator: Kramer, Kevin M.
Related research
Other NIH-funded projects on the same topics.
-
AI-powered tool to better predict and manage acute pulmonary embolism
A new AI system uses imaging and patient data to improve how doctors predict short-term risk and tailor treatment for people with acute pulmonary embolism.
-
Endovascular vortex ultrasound to treat blood clots in the lungs
A new therapy uses a tiny ultrasound device inside the blood vessels to rapidly dissolve clots in the lungs of people with pulmonary embolism, aiming to reduce the need for high doses of clot-busting drugs.
-
Supplemental Oxygen for Pulmonary Embolism: A Mechanistic Look at How Oxygen Helps the Heart and Lungs
This NIH grant tests how giving extra oxygen affects lung pressure and heart strain in people with acute pulmonary embolism, with supportive animal studies to understand the biology.
-
Pulmonary embolism: catheter-directed clot removal for better outcomes
This trial tests whether delivering clot-dissolving medication directly to the lungs via a catheter helps people with submassive pulmonary embolism feel better and function better, with fewer bleeding risks.
-
Pulmonary embolism treatment with catheter-directed thrombus removal versus no catheter therapy
This study tests whether removing clot with a targeted catheter approach helps people with submassive pulmonary embolism feel better and move more easily, compared with not using catheter therapy.
-
Molecular and imaging study of blood clots and inflammation in pulmonary embolism
A research project uses a mouse model to understand how blood clots and inflammatory cells affect pulmonary embolism and its outcomes, with the goal of better diagnosis and treatment for people with PE.
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.