Key result
Machine learning combining clinical and serial CMR features predicts long-term MACCEs after STEMI.
Answers are grounded in this paper and cite their sources.
Highlights machine learning combining cardiac MRI and functional recovery to predict post-STEMI events, indicating microvascular obstruction and remote tissue injury drive long-term risk.
No abstract yet. The journal hasn't published one we can show.
No takes yet. Share an insight, caveat, or question.
Yoriyasu Suzuki (2026) conducted an editorial in ST-segment elevation myocardial infarction (STEMI) (n=483). Extreme gradient boosting (XGBoost) machine learning model integrating clinical, angiographic, and serial CMR features vs. Naive Bayes, logistic regression, k-nearest neighbors, and conventional Cox regression was evaluated on Long-term major adverse cardiac and cerebrovascular events (MACCEs). An XGBoost model using 11 clinical and serial CMR features (led by microvascular obstruction) predicted long-term MACCEs with balanced performance after STEMI.
Synapse has enriched 10 related papers. Consider them for comparative context: