Search

Purpose: Although the limitations of hazard ratios (HRs) for quantifying treatment effects in right‐censored data have been widely discussed, HRs are still preferentially reported over other, more interpretable effect measures. This may stem from the fact that there are few applied examples that directly contrast the HR and its interpretation with alternative effect measures. Methods: We analyzed data from two randomized clinical trials comparing panitumumab plus standard‐of‐care chemotherapy (SOCC) with SOCC alone as first‐ and second‐line treatment for metastatic colorectal cancer. We report the effect of treatment with panitumumab on progression‐free survival (PFS) using a Cox proportional hazards model to estimate the HR and the Kaplan‐Meier estimator of cumulative incidence (risk). Further analyses included examining the cumulative incidence curves; kernel‐smoothed, non‐parametric hazards curves; fitting the Cox model with a continuous time variable; and estimating restricted mean survival as well as median survival. Results: The HR was 0.82 (95% confidence interval [CI]: 0.71, 0.93), while the risk ratio (or relative risk [i.e., ratio of the cumulative incidence among the treated versus comparator]) was 0.99 (95% CI: 0.96, 1.02). These two measures suggest apparently different conclusions: either a treatment benefit or no effect. Through subsequent analyses, we demonstrated that, while the cumulative incidence of the outcome was similar by the end of follow‐up regardless of treatment, the panitumumab treated group experienced longer PFS than those randomized to SOCC. Substantial nonproportional hazards were evident with panitumumab treatment reducing the hazard of progression/mortality during the first ~1.75 years but associated with an increased hazard of progress/mortality thereafter. Discussion: This example underscores the difficulties in interpreting HRs, particularly in the setting of qualitative violations of proportional hazards, and the value of quantifying treatment effects via multiple effect measures. [ABSTRACT FROM AUTHOR]

Misinterpretation and abuse of statistical tests, confidence intervals, and statistical power have been decried for decades, yet remain rampant. A key problem is that there are no interpretations of these concepts that are at once simple, intuitive, correct, and foolproof. Instead, correct use and interpretation of these statistics requires an attention to detail which seems to tax the patience of working scientists. This high cognitive demand has led to an epidemic of shortcut definitions and interpretations that are simply wrong, sometimes disastrously so-and yet these misinterpretations dominate much of the scientific literature. In light of this problem, we provide definitions and a discussion of basic statistics that are more general and critical than typically found in traditional introductory expositions. Our goal is to provide a resource for instructors, researchers, and consumers of statistics whose knowledge of statistical theory and technique may be limited but who wish to avoid and spot misinterpretations. We emphasize how violation of often unstated analysis protocols (such as selecting analyses for presentation based on the P values they produce) can lead to small P values even if the declared test hypothesis is correct, and can lead to large P values even if that hypothesis is incorrect. We then provide an explanatory list of 25 misinterpretations of P values, confidence intervals, and power. We conclude with guidelines for improving statistical interpretation and reporting.

Background Many older adults with cancer have ≥2 impairments on geriatric assessment, which affects present and future frailty status, treatment tolerability, and outcomes. Our objective was to identify and describe distinct geriatric assessment impairment classes using latent class analysis (LCA) in older patients with gastrointestinal malignancies and assess 1-year mortality. Methods We used the Cancer & Aging Resilience Evaluation (CARE) Study, a registry of older adults (≥60 years) at University of Alabama at Birmingham. The analytic cohort included patients with gastrointestinal malignancies who completed a self-administered geriatric assessment (CARE tool) before chemotherapy and had ≥1 geriatric assessment impairment. Thirteen geriatric assessment impairments were used as indicators in LCA. Resultant classes were described, mortality was estimated, and risk contrasts (differences and hazard ratios) were calculated with 95% confidence intervals. For comparison, estimates were provided for frailty categories (robust, prefrail, and frail) determined from 44 items in the CARE tool. Stratified analyses included high-risk (pancreatic, hepatobiliary, and esophageal) versus low-risk gastrointestinal cancers, and stage (IV vs I–III). Results Six geriatric assessment impairment classes were identified: Mild impairment (LC1); Social support impairment (LC2); Weight loss alone (LC3); Impaired, low anxiety/depression (LC4); Impaired with anxiety/depression (LC5); and Global impairment (LC6). One-year mortality was 14%, 22%, 29%, 34%, 50%, and 50% for LC1–LC6, respectively. For frailty categories, estimates ranged from 18% (robust) to 40% (frail). In stratified analyses, LC4–LC6 consistently had higher mortality estimates compared to LC1. Conclusions The 6 geriatric assessment impairment classes showed a wider spread of mortality estimates compared to frailty categories and could be used to identify vulnerable patients and to plan interventions. [ABSTRACT FROM AUTHOR]

Background: There are few assessments evaluating associations between birth defects with neural crest cell developmental origins (BDNCOs) and embryonal tumors, which are characterized by undifferentiated cells having a molecular profile similar to neural crest cells. The effect of BDNCOs on embryonal tumors was estimated to explore potential shared etiologic pathways and genetic origins. Methods: With the use of a multistate, registry‐linkage cohort study, BDNCO–embryonal tumor associations were evaluated by generating hazard ratios (HRs) and 95% confidence intervals (CIs) with Cox regression models. BDNCOs consisted of ear, face, and neck defects, Hirschsprung disease, and a selection of congenital heart defects. Embryonal tumors included neuroblastoma, nephroblastoma, and hepatoblastoma. Potential HR modification (HRM) was investigated by infant sex, maternal race/ethnicity, maternal age, and maternal education. Results: The risk of embryonal tumors among those with BDNCOs was 0.09% (co‐occurring n = 105) compared to 0.03% (95% CI, 0.03%–0.04%) among those without a birth defect. Children with BDNCOs were 4.2 times (95% CI, 3.5–5.1 times) as likely to be diagnosed with an embryonal tumor compared to children born without a birth defect. BDNCOs were strongly associated with hepatoblastoma (HR, 16.1; 95% CI, 11.3–22.9), and the HRs for neuroblastoma (3.1; 95% CI, 2.3–4.2) and nephroblastoma (2.9; 95% CI, 1.9–4.4) were elevated. There was no notable HRM by the aforementioned factors. Conclusions: Children with BDNCOs are more likely to develop embryonal tumors compared to children without a birth defect. Disruptions of shared developmental pathways may contribute to both phenotypes, which could inform future genomic assessments and cancer surveillance strategies of these conditions. Associations between nonchromosomal birth defects of neural crest cell developmental origins and pediatric embryonal tumors were investigated based on potential shared developmental pathways. With the use of data from a multistate, registry‐linkage cohort study, children born with these birth defects were found to be more likely (hazard ratio, 4.2; 95% CI, 3.5–5.1) to be diagnosed with the selected embryonal tumors than children without a birth defect, especially hepatoblastoma (hazard ratio, 16.1; 95% CI, 11.3–22.9). [ABSTRACT FROM AUTHOR]