CBS 2019
CBSMD教育中心
中 文

Other Relevant Articles

Abstract

Recommended Article

Predicting the 10-Year Risks of Atherosclerotic Cardiovascular Disease in Chinese Population: The China-PAR Project (Prediction for ASCVD Risk in China) Long-Term Effect of Ultrathin-Strut Versus Thin-Strut Drug-Eluting Stents in Patients With Small Vessel Coronary Artery Disease Undergoing Percutaneous Coronary Intervention: A Subgroup Analysis of the BIOSCIENCE Randomized Trial Timing and Causes of Unplanned Readmissions After Percutaneous Coronary Intervention: Insights From the Nationwide Readmission Database LOX-1 in Atherosclerosis and Myocardial Ischemia: Biology, Genetics, and Modulation The year in cardiovascular medicine 2020: interventional cardiology The Year in Cardiovascular Medicine 2020: Coronary Intervention Percutaneous coronary intervention in stable angina (ORBITA): a double-blind, randomised controlled trial Defining High Bleeding Risk in Patients Undergoing Percutaneous Coronary Intervention: A Consensus Document From the Academic Research Consortium for High Bleeding Risk

Volume 74, Issue 16, October 2019

JOURNAL:J Am Coll Cardiol. Article Link

Nonproportional Hazards for Time-to-Event Outcomes in Clinical Trials: JACC Review Topic of the Week

J Gregson, L Sharples, GW Stone et al. Keywords: clinical trials; Cox proportional hazards; nonproportional hazards; statistics; time-to-event outcomes; trial design

ABSTRACT


Most major clinical trials in cardiology report time-to-event outcomes using the Cox proportional hazards model so that a treatment effect is estimated as the hazard ratio between groups, accompanied by its 95% confidence interval and a log-rank p value. But nonproportionality of hazards (non-PH) over time occurs quite often, making alternative analysis strategies appropriate. This review presents real examples of cardiology trials with different types of non-PH: an early treatment effect, a late treatment effect, and a diminishing treatment effect. In such scenarios, the relative merits of a Cox model, an accelerated failure time model, a milestone analysis, and restricted mean survival time are examined. Some post hoc analyses for exploring any specific pattern of non-PH are also presented. Recommendations are made, particularly regarding how to handle non-PH in pre-defined Statistical Analysis Plans, trial publications, and regulatory submissions.