A machine-learning model using cardiac MRI and clinical parameters predicts major adverse cardiovascular events (MACE) in STEMI patients with higher accuracy than traditional methods.
Key Details
- 1Model integrates cardiac MRI and clinical data for long-term MACE prediction.
- 2Study included 1,066 STEMI patients from 2015-2023 who underwent MRI within 7 days post-PCI.
- 3ML model achieved external test set AUC of 0.91, outperforming clinical risk scores (AUC: 0.66-0.86) and Cox regression models.
- 4Sensitivity, specificity, and accuracy reached 82.7%, 84.5%, and 84.1% respectively.
- 5Stratified patients into distinct risk groups effectively (log-rank p < 0.001).
- 6Experts note need for further prospective studies and consideration of medical costs before clinical adoption.
Why It Matters
This work underscores the growing role of MRI-based AI tools in cardiovascular risk stratification, suggesting ML integration could personalize and improve outcome prediction. However, real-world impact and cost-effectiveness require further validation before routine use.
Source
AuntMinnie
Related News
•AuntMinnie
Radiology Receives Declining Share of Industry Research Funding
Radiologists received only 1.1% of industry-funded research payments in 2024, with a continuing downward trend.
•AuntMinnie
GPT-4o AI Matches Radiologists in Follow-Up Imaging Recommendations
GPT-4o matched the performance of experienced radiologists and surpassed residents in recommending follow-up imaging from routine radiology reports.
•Cardiovascular Business
AI Leverages Head CTs for Automated Heart Risk Assessments
AI models can turn routine head CT scans into automated cardiovascular risk assessments, expanding the utility of radiology studies.