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
•Radiology Business
AI-Generated Report Summaries Improve Patient Understanding at Emory Radiology
Emory University demonstrated that LLM-based tools can enhance patient comprehension of radiology reports.
•AuntMinnie
AI Tool Enhances Quality and Efficiency of MSK Ultrasound for Novices
A China-developed MSK ultrasound AI tool significantly improves scanning quality and efficiency for novice sonologists.
•Radiology Business
AI Predicts Breast Cancer Up to Six Years Before Diagnosis
AI technology using mammograms can predict breast cancer risk up to six years in advance.