Search

Background Acute respiratory infections have been associated with a transient increase in cardiovascular risk. However, whether such an association persists beyond 1 month and the potential modifying effect of cardiovascular risk factors on such an association are less well established. Methods The China Kadoorie Biobank enrolled 512 726 participants aged 30–79 years from 10 areas across China during 2004–2008. By the end of 2017, a total of 5444 participants with new-onset ischaemic heart disease (IHD) and 4846 with ischaemic stroke (IS) who also had at least a record of hospitalization for pneumonia during follow-up were included. We used a self-controlled case-series method and calculated the age- and season-adjusted relative incidences (RIs) and 95% confidence intervals (CIs) for ischaemic cardiovascular disease (CVD) after pneumonia. Results The risk of ischaemic CVD increased during days 1–3 after pneumonia hospitalization, with an RI (95% CI) of 4.24 (2.92–6.15) for IHD and 1.85 (1.02–3.35) for IS. The risk gradually reduced with longer duration since pneumonia hospitalization but remained elevated until days 92–365 for IHD (1.23, 1.12–1.35) and days 29–91 for IS (1.25, 1.05–1.48). Pre-existing cardiovascular risk factors amplified the associations between pneumonia and ischaemic CVD risks, such as chronic obstructive pulmonary disease for both IHD and IS, and diabetes and smoking for IHD (all Pinteraction Conclusion Among middle-aged and older Chinese adults, pneumonia hospitalization was associated with both short- and long-term increases in ischaemic CVD risk for ≤1 year.

Background Prediction of in-hospital bleeding is critical for clinical decision making for acute myocardial infarction (AMI) patients undergoing percutaneous coronary intervention (PCI). Machine learning methods can automatically select the combination of the important features and learn their underlying relationship with the outcome. Objective We aim to evaluate the predictive value of machine learning methods to predict in-hospital bleeding for AMI patients. Methods We used data from the multicenter China Acute Myocardial Infarction (CAMI) registry. We randomly partitioned the cohort into derivation set (75%) and validation set (25%). Using data from the derivation set, we applied a state-of-art machine learning algorithm, XGBoost, to automatically select features from 106 candidate variables and train a risk prediction model to predict in-hospital bleeding (BARC 3, 5 definition). Results 16736 AMI patients who underwent PCI were consecutively included in the analysis, while 70 (0.42%) patients had in-hospital bleeding followed the BARC 3,5 definition of bleeding. Fifty-nine features were automatically selected from the candidate features and were used to construct the prediction model. The area under the curve (AUC) of the XGBoost model was 0.816 (95% CI: 0.745–0.887) on the validation set, while AUC of the CRUSADE risk score was 0.723 (95% CI: 0.619–0.828). Relative contribution of the 12 most important features Feature Relative Importance Direct bilirubin 0.078 Heart rate 0.077 CKMB 0.076 Creatinine 0.064 GPT 0.052 Age 0.048 SBP 0.036 TG 0.035 Glucose 0.035 HCT 0.031 Total bilirubin 0.030 Neutrophil 0.030 ROC of the XGBoost model and CRUSADE Conclusion The XGBoost model derived from the CAMI cohort accurately predicts in-hospital bleeding among Chinese AMI patients undergoing PCI. Acknowledgement/Funding the CAMS innovation Fund for Medical Sciences (CIFMS) (2016-12M-1-009); the Twelfth Five-year Planning Project of China (2011BAI11B02)