EVALUATION OF LONG-TERM SURVIVAL: USE OF DIAGNOSTICS AND ROBUST ESTIMATORS WITH COX'S PROPORTIONAL HAZARDS MODEL

We consider methodological problems in evaluating long-term survival in clinical trials. In particular we examine the use of several methods that extend the basic Cox regression analysis. In the presence of a long term observation, the proportional hazard (PH) assumption may easily be violated and a few long term survivors may have a large effect on parameter estimates. We consider both model selection and robust estimation in a data set of 474 ovarian cancer patients enrolled in a clinical trial and followed for between 7 and 12 years after randomization. Two diagnostic plots for assessing goodness-of-fit are introduced. One shows the variation in time of parameter estimates and is an alternative to PH checking based on time-dependent covariates. The other takes advantage of the martingale residual process in time to represent the lack of fit with a metric of the type ‘observed minus expected’ number of events. Robust estimation is carried out by maximizing a weighted partial likelihood which downweights the contribution to estimation of influential observations. This type of complementary analysis of long-term results of clinical studies is useful in assessing the soundness of the conclusions on treatment effect. In the example analysed here, the difference in survival between treatments was mostly confined to those individuals who survived at least two years beyond randomization     

Diaphragm Pacing with a Quadripolar Phrenic Nerve Electrode: An International Study

We sought to determine the international experience with the quadripolar diaphragm pacer system and to test two hypotheses: the incidence of pacer complications would be (1) increased among pediatric as compared to adult patients; and (2) highest among active pediatric patients with idiopathic congenital central hypoventilation syndrome (CCHS). Data were collected via a questionnaire coupled with the Atrotech Registry data for a total of 64 patients (35 children and 29 adults) from 14 countries. Thoracic implantation of electrodes and bilateral pacer use each occurred in 94% of all subjects. Tetraplegic (vs pediatric CCHS) patients were more typically paced 24 hours/day (P = 0.001). Pacing duration averaged 2.0 ± 1.0 years among children and 2.2 ± 1.1 years among adults. Infections occurred among 2.9% of surgical procedures, all in pediatric CCHS patients (vs pediatric tetraplegic patients, P = 0.01). The incidence of mechanical trauma was 3.8%, without significant differences among patient groups. The incidence of presumed electrode and receiver failure were 3.1% and 5.9%, respectively, with internal component failure greater among pediatric CCHS than pediatric tetraplegic patients (P < 0.01). Intermittent or absent function of 0–4 electrode combinations occurred among 19% of all patients, with increased frequency among pediatric CCHS than pediatric tetraplegic patients (P < 0.03). Complication- free successful pacing occurred in 60% of pediatric and 52% of adult patients. In all, 94 % of the pediatric and 86% of the adult patients paced successfully after the necessary intervention. Although pacer complications were not increased among pediatric as compared to adult patients, the incidence of complications was highest among the active pediatric patients with CCHS. Longitudinal study of these patients will provide invaluable information for modification and improvement of the quadripolar system.