A random-forest machine learning model leveraging cardiac MRI and patient health history improves prediction of major adverse cardiovascular events.
Key Details
- 1Study involved 2,159 patients referred for adenosine perfusion cardiac MRI.
- 2Random-forest model used both MRI/demographics and 10 years of historical health registry data.
- 3Primary outcome was major adverse cardiovascular events—including death, MI, unstable angina, or intervention (MACE occurred in 9.1% of patients).
- 4Random-forest model with historical data achieved a C-index of 0.81, outperforming Cox regression's 0.77 (p < 0.001).
- 5Presenting institution: Lund University, Sweden; data presented at 2026 ISMRM meeting.
Why It Matters
Integrating routinely collected health registry data with imaging AI can improve cardiovascular risk stratification, potentially resulting in better patient management. This supports the broader value of combining multi-source data and advanced analytics in clinical radiology.
Source
AuntMinnie
Related News
•AuntMinnie
Radiologists Struggle to Spot AI-Generated Radiology Images
Radiologists correctly identify AI-generated images 75% of the time, with CT and MRI images being particularly challenging to spot.
•AuntMinnie
Radiology Leads FDA AI Device Approvals Over Three Decades
Radiology accounts for 76% of all FDA-cleared AI/ML-enabled medical devices as of the end of 2025.
•Radiology Business
Automation Bias: How AI Can Compromise Radiologist Accuracy
AI decision support can induce automation bias, leading radiologists to accept incorrect interpretations and potentially reduce their diagnostic accuracy.