AI reading of heart ultrasound to detect Takotsubo syndrome and predict outcomes
Implications of Spatiotemporal Deep Learning Neural Networks in Echocardiographic Diagnosis and Prognostication of Takotsubo Syndrome
This project trains artificial intelligence to read heart ultrasound videos to tell Takotsubo syndrome apart from heart attack and to predict patients' likely outcomes.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Iowa NIH-funded |
| Lab location | 1 site (Iowa City, United States) |
| Project ID | NIH-11249939 on NIH RePORTER |
What this research studies
Researchers will improve a spatiotemporal deep learning algorithm using large collections of 2D/3D echocardiogram videos and linked clinical information from multiple hospitals. The AI will learn subtle heart motion patterns that are hard for clinicians to see and will be optimized to work across different ultrasound machines and sites. A separate model will look for patient subgroups and predict longer-term risks to help tailor follow-up and treatment. The team will also add features to make the AI's decisions more interpretable to clinicians.
Who could benefit from this research
Good fit: Ideal candidates are people who had chest pain and underwent echocardiography for suspected heart attack or Takotsubo syndrome, or patients with confirmed TTS who can share their echo images and medical records.
Not a fit: People without echocardiogram images or with unrelated heart conditions are unlikely to directly benefit from this project.
Why it matters
Potential benefit: If successful, this could help clinicians diagnose Takotsubo syndrome faster and more accurately, avoid unnecessary heart attack treatments, and personalize follow-up care to reduce long-term risks.
How similar studies have performed: Early work, including the team's prior model, showed promising accuracy for AI-based echo diagnosis of TTS, but large-scale validation and prognostic phenomapping remain relatively new.
Where this research is happening
Iowa City, United States
- University of Iowa — Iowa City, United States (Active)
Researchers
- Principal investigator: Wu, Xiaodong — University of Iowa
- Study coordinator: Wu, Xiaodong
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 below.