AI-powered echocardiography reporting with visual-linguistic models
Official title: Toward Artificial Intelligence-enabled Automatic Echocardiography Reporting: A Study of Visual-Linguistic Foundation Model Frameworks
Funded at Mayo Clinic Rochester · NIH-11413667 · Data updated 2026-11-12
A Mayo Clinic physician aims to train and grow an AI-enabled system that helps automatically interpret echocardiograms and generate reports for patients with heart problems.
Quick facts
| Grant type | Career grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Mayo Clinic Rochester NIH-funded |
| Lab location | 1 site (Rochester, United States) |
| Project start | September 15, 2025 |
| Project end | August 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $188,136 |
| NIH project number | 5K08HL175205-02 |
| Project ID | NIH-11413667 on NIH RePORTER |
Who could benefit from this research
✓Could help
Patients having suspected or known heart conditions who undergo echocardiography could benefit from improved interpretation.
✕Less likely to help
Patients whose imaging data are not suitable for AI interpretation or who have conditions not primarily assessed by echocardiography may see no direct benefit.
What this research studies
This project focuses on using visual-linguistic models and large language models to create an AI-assisted echocardiography interpretation tool. The goal is to speed up accurate readings and reduce misdiagnoses for people with cardiac issues. Dr. Chieh-Ju Chao will receive mentored training from renowned AI and medical imaging experts to develop and test the system on real-world echocardiography data.
Why it matters
Potential benefit: If successful, patients could receive faster, more accurate echocardiogram interpretations and clearer reports.
How similar studies have gone: Previous AI efforts in medical imaging show promise, but this project targets a broader, integrated AI interpretation system with translation-ready reports.
Where this research is happening
-
Mayo Clinic Rochester
Rochester, United States Active
Researchers
- Principal investigator: Chao, Chieh-Ju — Mayo Clinic Rochester
- Study coordinator: Chao, Chieh-Ju
Related research
Other NIH-funded projects on the same topics.
-
Four-Chamber Echo Insights to Improve Cardiac Diagnosis
A new AI-based approach uses routine echocardiograms to map the heart’s four chambers and flow patterns, helping doctors diagnose acute heart conditions more accurately.
-
AI-powered automatic echocardiography reporting for better heart care
A Mayo Clinic team is developing an AI-enabled system to automatically interpret echocardiograms and generate reports for patients with heart problems.
-
AI-powered echocardiography to spot common heart defects in newborns
A new AI tool analyzes infant heart ultrasound images to help non-specialist health workers identify five common, treatable heart defects early.
-
AI help for newborn heart ultrasound images in Sub‑Saharan Africa
This project uses AI to help health workers capture better heart ultrasound images so newborns in Sub‑Saharan Africa can get quicker, more accurate diagnosis of congenital heart defects.
-
New approaches to making transesophageal echocardiography safer and easier for patients
A novel NIH-funded project aims to improve how transesophageal echocardiography (TEE) is done, reducing sedation risks and expanding access for adults who need heart imaging.
-
Combined fetal heart electrical and structural imaging with quantum sensors
Aims to make prenatal heart diagnoses safer and more accurate by using a new quantum sensor to combine fetal heart electrical activity with ultrasound imaging.
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.