In a longitudinal clinical study to compare two groups, the primary end point is often the time to a specific event (eg, disease progression, death). The hazard ratio estimate is routinely used to empirically quantify the between-group difference under the assumption that the ratio of the two hazard functions is approximately constant over time. When this assumption is plausible, such a ratio estimate may capture the relative difference between two survival curves. However, the clinical meaning of such a ratio estimate is difficult, if not impossible, to interpret when the underlying proportional hazards assumption is violated (ie, the hazard ratio is not constant over time). Although this issue has been studied extensively and various alternatives to the hazard ratio estimator have been discussed in the statistical literature, such crucial information does not seem to have reached the broader community of health science researchers. In this article, we summarize several critical concerns regarding this conventional practice and discuss various well-known alternatives for quantifying the underlying differences between groups with respect to a time-to-event end point. The data from three recent cancer clinical trials, which reflect a variety of scenarios, are used throughout to illustrate our discussions. When there is not sufficient information about the profile of the between-group difference at the design stage of the study, we encourage practitioners to consider a prespecified, clinically meaningful, model-free measure for quantifying the difference and to use robust estimation procedures to draw primary inferences.

IMPORTANCE Cholesterol is a common nutrient in the human diet and eggs are a major source of dietary cholesterol. Whether dietary cholesterol or egg consumption is associated with cardiovascular disease (CVD) and mortality remains controversial. OBJECTIVE To determine the associations of dietary cholesterol or egg consumption with incident CVD and all-cause mortality. DESIGN, SETTING, AND PARTICIPANTS Individual participant data were pooled from 6 prospective US cohorts using data collected between March 25, 1985, and August 31, 2016. Self-reported diet data were harmonized using a standardized protocol. EXPOSURES Dietary cholesterol (mg/day) or egg consumption (number/day). MAIN OUTCOMES AND MEASURES Hazard ratio (HR) and absolute risk difference (ARD) over the entire follow-up for incident CVD (composite of fatal and nonfatal coronary heart disease, stroke, heart failure, and other CVD deaths) and all-cause mortality, adjusting for demographic, socioeconomic, and behavioral factors. RESULTS This analysis included 29 615 participants (mean [SD] age, 51.6 [13.5] years at baseline) of whom 13 299 (44.9%) were men and 9204 (31.1%) were black. During a median follow-up of 17.5 years (interquartile range, 13.0-21.7; maximum, 31.3), there were 5400 incident CVD events and 6132 all-cause deaths. The associations of dietary cholesterol or egg consumption with incident CVD and all-cause mortality were monotonic (all P values for nonlinear terms, .19-.83). Each additional 300 mg of dietary cholesterol consumed per day was significantly associated with higher risk of incident CVD (adjusted HR, 1.17 [95% CI, 1.09-1.26]; adjusted ARD, 3.24% [95% CI, 1.39%-5.08%]) and all-cause mortality (adjusted HR, 1.18 [95% CI, 1.10-1.26]; adjusted ARD, 4.43% [95% CI, 2.51%-6.36%]). Each additional half an egg consumed per day was significantly associated with higher risk of incident CVD (adjusted HR, 1.06 [95% CI, 1.03-1.10]; adjusted ARD, 1.11% [95% CI, 0.32%-1.89%]) and all-cause mortality (adjusted HR, 1.08 [95% CI, 1.04-1.11]; adjusted ARD, 1.93% [95% CI, 1.10%-2.76%]). The associations between egg consumption and incident CVD (adjusted HR, 0.99 [95% CI, 0.93-1.05]; adjusted ARD, −0.47% [95% CI, −1.83% to 0.88%]) and all-cause mortality (adjusted HR, 1.03 [95% CI, 0.97-1.09]; adjusted ARD, 0.71% [95% CI, −0.85% to 2.28%]) were no longer significant after adjusting for dietary cholesterol consumption. CONCLUSIONS AND RELEVANCE Among US adults, higher consumption of dietary cholesterol or eggs was significantly associated with higher risk of incident CVD and all-cause mortality in a dose-response manner. These results should be considered in the development of dietary guidelines and updates.

Polycystic ovary syndrome (PCOS) is the most frequent endocrinopathy in women of reproductive age. It is difficult to treat PCOS because of its complex etiology and pathogenesis. Here, we characterized the roles of gut microbiota on the pathogenesis and treatments in letrozole (a nonsteroidal aromatase inhibitor) induced PCOS rat model. Changes in estrous cycles, hormonal levels, ovarian morphology and gut microbiota by PCR-DGGE and real-time PCR were determined. The results showed that PCOS rats displayed abnormal estrous cycles with increasing androgen biosynthesis and exhibited multiple large cysts with diminished granulosa layers in ovarian tissues. Meanwhile, the composition of gut microbiota in letrozole-treated rats was different from that in the controls. Lactobacillus, Ruminococcus and Clostridium were lower while Prevotella was higher in PCOS rats when compared with control rats. After treating PCOS rats with Lactobacillus and fecal microbiota transplantation (FMT) from healthy rats, it was found that the estrous cycles were improved in all 8 rats in FMT group, and in 6 of the 8 rats in Lactobacillus transplantation group with decreasing androgen biosynthesis. Their ovarian morphologies normalized. The composition of gut microbiota restored in both FMT and Lactobacillus treated groups with increasing of Lactobacillus and Clostridium, and decreasing of Prevotella. These results indicated that dysbiosis of gut microbiota was associated with the pathogenesis of PCOS. Microbiota interventions through FMT and Lactobacillus transplantation were beneficial for the treatments of PCOS rats.

R package, source code, and simulation study are available at https://github.com/YinanZheng/HIMA CONTACT: lei.liu@northwestern.edu.

For designing, monitoring, and analyzing a longitudinal study with an event time as the outcome variable, the restricted mean event time (RMET) is an easily interpretable, clinically meaningful summary of the survival function in the presence of censoring. The RMET is the average of all potential event times measured up to a time point τ and can be estimated consistently by the area under the Kaplan-Meier curve over $[0, \tau ]$. In this paper, we study a class of regression models, which directly relates the RMET to its "baseline" covariates for predicting the future subjects' RMETs. Since the standard Cox and the accelerated failure time models can also be used for estimating such RMETs, we utilize a cross-validation procedure to select the "best" among all the working models considered in the model building and evaluation process. Lastly, we draw inferences for the predicted RMETs to assess the performance of the final selected model using an independent data set or a "hold-out" sample from the original data set. All the proposals are illustrated with the data from the an HIV clinical trial conducted by the AIDS Clinical Trials Group and the primary biliary cirrhosis study conducted by the Mayo Clinic.