A LASSO-derived model for the prediction of coagulation disorders after coronary artery bypass grafting

Highlight box

Key findings

• A prediction model for assessing the risk of coagulation disorders after coronary artery bypass grafting (CABG) was developed and demonstrated good prediction performance in elderly individuals, employing the least absolute shrinkage and selection operator (LASSO) regression.

What is known and what is new?

• Preoperative variables associated with coagulation disorders included weight, baseline estimated glomerular filtration rate, B-type natriuretic peptide, platelet count, preoperative use of heparin and angiotensin receptor-neprilysin inhibitor.

• Intraoperative variables associated with coagulation disorders included utilization of epinephrine, norepinephrine, dopamine, cephalosporins, cardiopulmonary bypass, intra-aortic balloon pump, extracorporeal membrane oxygenation, operation duration, and total intraoperative fluid input.

What is the implication, and what should change now?

• This LASSO-derived model exhibited a good predictive performance and is helpful for early detection of elderly Chinese patients at high risk for coagulation disorders post-CABG surgery.

Publication: Zhao H, Li X, Li H, Peng W. A LASSO-derived model for the prediction of coagulation disorders after coronary artery bypass grafting. J Thorac Dis 2025;17(1):231-242. doi: 10.21037/jtd-24-1321