Propensity score (PS) methods are increasingly used, even when sample sizes are small or treatments are seldom used. However, the relative performance of the two mainly recommended PS methods, namely ...PS-matching or inverse probability of treatment weighting (IPTW), have not been studied in the context of small sample sizes.
We conducted a series of Monte Carlo simulations to evaluate the influence of sample size, prevalence of treatment exposure, and strength of the association between the variables and the outcome and/or the treatment exposure, on the performance of these two methods.
Decreasing the sample size from 1,000 to 40 subjects did not substantially alter the Type I error rate, and led to relative biases below 10%. The IPTW method performed better than the PS-matching down to 60 subjects. When N was set at 40, the PS matching estimators were either similarly or even less biased than the IPTW estimators. Including variables unrelated to the exposure but related to the outcome in the PS model decreased the bias and the variance as compared to models omitting such variables. Excluding the true confounder from the PS model resulted, whatever the method used, in a significantly biased estimation of treatment effect. These results were illustrated in a real dataset.
Even in case of small study samples or low prevalence of treatment, PS-matching and IPTW can yield correct estimations of treatment effect unless the true confounders and the variables related only to the outcome are not included in the PS model.
Assessments of the discriminative performance of prognostic models have led to the development of several measures that extend the concept of discrimination as evaluated by the receiver operating ...characteristics curve and the area under the receiver operating characteristic curve (AUC) of diagnostic settings. Thus, several time-dependent-receiver operating characteristic curve and AUC(t) have been proposed. One of the most used, the cumulative/dynamic AUCC,D(t) is the probability that, given two randomly chosen patients, one having failed before t and the other having failed after t, the prognostic marker will be correctly ranked. In this paper, we propose a weighted AUCC,D(t) with time- and data-dependent weights as a summary measure of the mean AUCC,D(t), restricted to a finite time range to ensure its clinical relevance. A simulation study shows that estimated restricted mean AUC increased with the strength of association of the covariate with the outcome, with low impact of censoring, and adequate coverage of bootstrap confidence intervals. We illustrate this methodology to two real datasets from two randomized clinical trials to assess the prognostic factors of the overall mortality in patients who have compensated cirrhosis and to assess the prognostic factors of event-free survival in patients who have acute myeloid leukemia.
Abstract
Objectives
Temporal artery biopsy (TAB) is a reference test for the diagnosis of GCA but reveals inflammatory changes only in a subset of patients. The lack of knowledge of TAB sensitivity ...hampers comparisons with non-invasive techniques such as temporal artery ultrasonography. We performed a systematic literature review and meta-analysis to estimate the sensitivity of TAB in GCA and to identify factors that may influence the estimate.
Methods
A systematic literature review involved searching electronic databases and cross-references. Eligibility criteria included publications reporting at least 30 GCA cases fulfilling the original or modified 1990 ACR classification criteria. The pooled proportion of TAB-positive GCA cases was calculated by using aggregated-data meta-analysis with a random-effects model and assessment of heterogeneity with the I2 statistic. Subgroup analyses and meta-regression were used to examine the effect of patient and study characteristics on TAB positivity.
Results
Among 3820 publications screened, 32 studies (3092 patients) published during 1993–2017 were analysed. The pooled proportion of TAB-positive GCA cases was 77.3% (95% CI: 71.8, 81.9%), with high between-study heterogeneity (I2 = 90%). The proportion of TAB-positive cases was slightly higher in publications before than in 2012 and after (P = 0.001).
Conclusion
The estimated sensitivity of 77% provides indirect evidence that TAB is not less sensitive than temporal artery imaging. The unexplained high between-study heterogeneity could result from differences in TAB sampling, processing or interpretation. The decrease in TAB-positive GCA cases over time could reflect an increasing propensity for clinicians to accept a GCA diagnosis without proof by TAB.
Adaptive clinical trials have been increasingly commonly employed to select a potential target population for one trial without conducting trials separately. Such enrichment designs typically consist ...of two or three stages, where the first stage serves as a screening process for selecting a specific subpopulation.
We propose a Bayesian design for randomized clinical trials with a binary outcome that focuses on restricting the inclusion to a subset of patients who are likely to benefit the most from the treatment during trial accrual. Several Bayesian measures of efficacy and treatment-by-subset interactions were used to dictate the enrichment, either based on Gail and Simon's or Millen's criteria. A simulation study was used to assess the performance of our design. The method is exemplified in a real randomized clinical trial conducted in patients with respiratory failure that failed to show any benefit of high flow oxygen supply compared with standard oxygen.
The use of the enrichment rules allowed the detection of the existence of a treatment-by-subset interaction more rapidly compared with Gail and Simon's criteria, with decreasing proportions of enrollment in the whole sample, and the proportions of enrichment lower, in the presence of interaction based on Millen's criteria. In the real dataset, this may have allowed the detection of the potential interest of high flow oxygen in patients with a SOFA neurological score ≥ 1.
Enrichment designs that handle the uncertainty in treatment efficacy by focusing on the target population offer a promising balance for trial efficiency and ease of interpretation.
Cerebral autosomal dominant arteriopathy with subcortical infarcts and leukoencephalopathy, which is caused by mutations of the NOTCH3 gene, has a large heterogeneous progression, presenting with ...declines of various clinical scores and occurrences of various clinical event. To help assess disease progression, this work focused on predicting the composite endpoint of stroke-free survival time by comparing the performance of Cox proportional hazards regression to that of machine learning models using one of four feature selection approaches applied to demographic, clinical and magnetic resonance imaging observational data collected from a study cohort of 482 patients. The quality of the modeling process and the predictive performance were evaluated in a nested cross-validation procedure using the time-dependent Brier Score and AUC at 5 years from baseline, the former measuring the overall performance including calibration and the latter highlighting the discrimination ability, with both metrics taking into account the presence of right-censoring. The best model for each metric was the componentwise gradient boosting model with a mean Brier score of 0.165 and the random survival forest model with a mean AUC of 0.773, both combined with the LASSO feature selection method.
The randomized, phase III ALFA-0701 trial showed that a reduced and fractionated dose of gemtuzumab ozogamicin added to standard front-line chemotherapy significantly improves event-free survival ...(EFS) in adults with
acute myeloid leukemia (AML). Here we report an independent review of EFS, final overall survival (OS), and additional safety results from ALFA-0701. Patients (n=271) aged 50-70 years with
AML were randomized to receive conventional front-line induction chemotherapy (3+7daunorubicin+cytarabine) with/without gemtuzumab ozogamicin 3 mg/m
on days 1, 4, and 7 during induction. Patients in remission following induction therapy received 2 courses of consolidation therapy (daunorubicin+cytarabine) with/without gemtuzumab ozogamicin (3 mg/m
/day on day 1) according to their initial randomization. The primary end point was investigator-assessed EFS. Secondary end points included OS and safety. A blinded independent review confirmed the investigator-assessed EFS results August 1, 2011; hazard ratio (HR) 0.66; 95% Confidence Interval (CI): 0.49-0.89; 2-sided
=0.006, corresponding to a 34% reduction in risk of events in the gemtuzumab ozogamicin
control arm. Final OS at April 30, 2013 favored gemtuzumab ozogamicin but was not significant. No differences in early death rate were observed between arms. The main toxicity associated with gemtuzumab ozogamicin was prolonged thrombocytopenia. Veno-occlusive disease (including after transplant) was observed in 6 patients in the gemtuzumab ozogamicin arm and 2 in the control arm. In conclusion, gemtuzumab ozogamicin added to standard intensive chemotherapy has a favorable benefit/risk ratio. These results expand front-line treatment options for adult patients with previously untreated AML. (Trial registered at
).
Summary Background Gemtuzumab ozogamicin was the first example of antibody-directed chemotherapy in cancer, and was developed for acute myeloid leukaemia. However, randomised trials in which it was ...combined with standard induction chemotherapy in adults have produced conflicting results. We did a meta-analysis of individual patient data to assess the efficacy of adding gemtuzumab ozogamicin to induction chemotherapy in adult patients with acute myeloid leukaemia. Methods We searched PubMed for reports of randomised controlled trials published in any language up to May 1, 2013, that included an assessment of gemtuzumab ozogamicin given to adults (aged 15 years and older) in conjunction with the first course of intensive induction chemotherapy for acute myeloid leukaemia (excluding acute promyelocytic leukaemia) compared with chemotherapy alone. Published data were supplemented with additional data obtained by contacting individual trialists. The primary endpoint of interest was overall survival. We used standard meta-analytic techniques, with an assumption-free (or fixed-effect) method. We also did exploratory stratified analyses to investigate whether any baseline features predicted a greater or lesser benefit from gemtuzumab ozogamicin. Findings We obtained data from five randomised controlled trials (3325 patients); all trials were centrally randomised and open label, with overall survival as the primary endpoint. The addition of gemtuzumab ozogamicin did not increase the proportion of patients achieving complete remission with or without complete peripheral count recovery (odds ratio OR 0·91, 95% CI 0·77–1·07; p=0·3). However, the addition of gemtuzumab ozogamicin significantly reduced the risk of relapse (OR 0·81, 0·73–0·90; p=0·0001), and improved overall survival at 5 years (OR 0·90, 0·82–0·98; p=0·01). At 6 years, the absolute survival benefit was especially apparent in patients with favourable cytogenetic characteristics (20·7%; OR 0·47, 0·31–0·73; p=0·0006), but was also seen in those with intermediate characteristics (5·7%; OR 0·84, 0·75–0·95; p=0·005). Patients with adverse cytogenetic characteristics did not benefit (2·2%; OR 0·99, 0·83–1·18; p=0·9). Doses of 3 mg/m2 were associated with fewer early deaths than doses of 6 mg/m2 , with equal efficacy. Interpretation Gemtuzumab ozogamicin can be safely added to conventional induction therapy and provides a significant survival benefit for patients without adverse cytogenetic characteristics. These data suggest that the use of gemtuzumab ozogamicin should be reassessed and its licence status might need to be reviewed. Funding None.
PDF
