An additive subdistribution hazard model for competing risks data

Comparison of waitlist and post-transplant outcomes in patients supported with total artificial heart versus continuous biventricular assist devices

BACKGROUND

Durable biventricular support may be necessary to bridge patients with end-stage biventricular failure to heart transplantation. This study compares waitlist and post-transplant outcomes between patients supported with continuous flow, durable biventricular assist devices (BiVAD), and total artificial heart (TAH).

METHODS

Using the UNOS registry, we analyzed adult (≥18 years old), first-time transplant candidates with TAH or BiVAD at the time of listing or transplantation from 10/1/2010-10/31/2020, with follow-up through 3/31/2022. Multivariable proportional subdistribution hazards models and cause-specific Cox proportional hazards models were used to compare death/deterioration or heart transplantation on the waitlist between cohorts. Kaplan-Meier and multivariable Cox proportional hazards model were used to evaluate one-year post-transplant survival and evaluate difference in outcomes based on annual transplant center volume.

RESULTS

The waitlist cohort included a total of 228 patients (25% BiVAD). Waitlist outcomes between device types were similar. The transplanted cohort included a total of 352 patients (25% BiVAD). There was a trend towards worse one-year post-transplant survival in patients bridged with TAH versus BiVAD (log-rank p-value = 0.072) that persisted after adjusting for age, gender, policy, and removing dual-organ recipients (HR 1.94 (0.94, 3.98) p-value = 0.07). There was a difference in one-year post-transplant survival amongst TAH-bridged patients when stratified by annual transplant center volume (log-rank p-value = 0.013). One-year post-transplant survival between TAH-supported patients from high annual transplant volume centers and BiVAD-supported patients was similar (p-value = 0.815).

CONCLUSIONS

BiVAD and TAH are reasonable support strategies with TAH implantation at high-volume transplant centers (51+ transplants/year) having similar 1-year post-transplant survival to BiVAD-supported patients.

Additive subdistribution hazards regression for competing risks data in case-cohort studies

In survival data analysis, a competing risk is an event whose occurrence precludes or alters the chance of the occurrence of the primary event of interest. In large cohort studies with long-term follow-up, there are often competing risks. Further, if the event of interest is rare in such large studies, the case-cohort study design is widely used to reduce the cost and achieve the same efficiency as a cohort study. The conventional additive hazards modeling for competing risks data in case-cohort studies involves the cause-specific hazard function, under which direct assessment of covariate effects on the cumulative incidence function, or the subdistribution, is not possible. In this paper, we consider an additive hazard model for the subdistribution of a competing risk in case-cohort studies. We propose estimating equations based on inverse probability weighting methods for the estimation of the model parameters. Consistency and asymptotic normality of the proposed estimators are established. The performance of the proposed methods in finite samples is examined through simulation studies and the proposed approach is applied to a case-cohort dataset from the Sister Study.

Two-stage residual inclusion for survival data and competing risks-An instrumental variable approach with application to SEER-Medicare linked data

Instrumental variable is an essential tool for addressing unmeasured confounding in observational studies. Two-stage predictor substitution (2SPS) estimator and two-stage residual inclusion (2SRI) are two commonly used approaches in applying instrumental variables. Recently, 2SPS was studied under the additive hazards model in the presence of competing risks of time-to-events data, where linearity was assumed for the relationship between the treatment and the instrument variable. This assumption may not be the most appropriate when we have binary treatments. In this paper, we consider the 2SRI estimator under the additive hazards model for general survival data and in the presence of competing risks, which allows generalized linear models for the relation between the treatment and the instrumental variable. We derive the asymptotic properties including a closed-form asymptotic variance estimate for the 2SRI estimator. We carry out numerical studies in finite samples and apply our methodology to the linked Surveillance, Epidemiology and End Results (SEER)-Medicare database comparing radical prostatectomy versus conservative treatment in early-stage prostate cancer patients.