Author + information
- Pengyuan Chen,
- Yong Liu,
- Shiqun Chen,
- Ying Xian,
- Jiyan Chen and
- Ning Tan
To develop and validate prediction tool for contrast-induced nephropathy (CIN) in patients undergoing contemporary percutaneous coronary intervention (PCI) or coronary angiogram (CAG).
A total of 3,469 patients undergoing PCI/CAG between January 2010 and December 2013 were randomly divided into a training dataset (n=2,428, 70%) and a validation dataset (n=1,041, 30%). Random forest models were developed using 40 pre-procedural variables, of which 13 variables were selected for a reduced CIN model.
The full and reduced models demonstrated improved discrimination over Mehran, ACEF risk scores (AUC: 0.842, 0.825, 0.762, and 0.701, respectively, all P<0.05) and renal dysfunction for CIN risk, providing a better fit based on comparisons in the net reclassification improvement and integrated discrimination improvement. Using the above models, 2,462 (66.7%), 661, and 346 patients were categorized into low (<1%), moderate (1% to 7%), and high (>7%) risk groups, respectively. Higher hydration volumes had a similar CIN risk to lower hydration volumes, with a trend towards more adverse events in patients with low (adjusted OR for follow-up mortality was 2.585, P=0.036) to high CIN risk.
Our CIN risk prediction algorithm (http://cincalc.com) appears to have good predictive ability.
Poster Hall, Hall A/B
Monday, March 12, 2018, 9:45 a.m.-10:30 a.m.
Session Title: Contrast Nephropathy
Abstract Category: 16. Interventional Cardiology: Angiography and Interventional CT/MR
Presentation Number: 1291-306
- 2018 American College of Cardiology Foundation