Dataset Information

A comparison of statistical methods for the study of etiologic heterogeneity.

ABSTRACT: Cancer epidemiologic research has traditionally been guided by the premise that certain diseases share an underlying etiology, or cause. However, with the rise of molecular and genomic profiling, attention has increasingly focused on identifying subtypes of disease. As subtypes are identified, it is natural to ask the question of whether they share a common etiology or in fact arise from distinct sets of risk factors. In this context, epidemiologic questions of interest include (1) whether a risk factor of interest has the same effect across all subtypes of disease and (2) whether risk factor effects differ across levels of each individual tumor marker of which the subtypes are comprised. A number of statistical models have been proposed to address these questions. In an effort to determine the similarities and differences among the proposed methods, and to identify any advantages or disadvantages, we use a simplified data example to elucidate the interpretation of model parameters and available hypothesis tests, and we perform a simulation study to assess bias in effect size, type I error, and power. The results show that when the number of tumor markers is small enough that the cross-classification of markers can be evaluated in the traditional polytomous logistic regression framework, then the statistical properties are at least as good as the more complex modeling approaches that have been proposed. The potential advantage of more complex methods is in the ability to accommodate multiple tumor markers in a model of reduced parametric dimension.

SUBMITTER: Zabor EC

PROVIDER: S-EPMC5677262 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A comparison of statistical methods for the study of etiologic heterogeneity.

Zabor Emily C EC Begg Colin B CB

Statistics in medicine 20170726 25

Cancer epidemiologic research has traditionally been guided by the premise that certain diseases share an underlying etiology, or cause. However, with the rise of molecular and genomic profiling, attention has increasingly focused on identifying subtypes of disease. As subtypes are identified, it is natural to ask the question of whether they share a common etiology or in fact arise from distinct sets of risk factors. In this context, epidemiologic questions of interest include (1) whether a ris ...[more]

PMID: 28748599

Similar Datasets

Project description:BackgroundIn randomized clinical trials, treatment effects may vary, and this possibility is referred to as heterogeneity of treatment effect (HTE). One way to quantify HTE is to partition participants into subgroups based on individual's risk of experiencing an outcome, then measuring treatment effect by subgroup. Given the limited availability of externally validated outcome risk prediction models, internal models (created using the same dataset in which heterogeneity of treatment analyses also will be performed) are commonly developed for subgroup identification. We aim to compare different methods for generating internally developed outcome risk prediction models for subject partitioning in HTE analysis.MethodsThree approaches were selected for generating subgroups for the 2,441 participants from the United States enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial. An extant proportional hazards-based outcomes predictive risk model developed on the overall ASPREE cohort of 19,114 participants was identified and was used to partition United States' participants by risk of experiencing a composite outcome of death, dementia, or persistent physical disability. Next, two supervised non-parametric machine learning outcome classifiers, decision trees and random forests, were used to develop multivariable risk prediction models and partition participants into subgroups with varied risks of experiencing the composite outcome. Then, we assessed how the partitioning from the proportional hazard model compared to those generated by the machine learning models in an HTE analysis of the 5-year absolute risk reduction (ARR) and hazard ratio for aspirin vs. placebo in each subgroup. Cochran's Q test was used to detect if ARR varied significantly by subgroup.ResultsThe proportional hazard model was used to generate 5 subgroups using the quintiles of the estimated risk scores; the decision tree model was used to generate 6 subgroups (6 automatically determined tree leaves); and the random forest model was used to generate 5 subgroups using the quintiles of the prediction probability as risk scores. Using the semi-parametric proportional hazards model, the ARR at 5 years was 15.1% (95% CI 4.0-26.3%) for participants with the highest 20% of predicted risk. Using the random forest model, the ARR at 5 years was 13.7% (95% CI 3.1-24.4%) for participants with the highest 20% of predicted risk. The highest outcome risk group in the decision tree model also exhibited a risk reduction, but the confidence interval was wider (5-year ARR = 17.0%, 95% CI= -5.4-39.4%). Cochran's Q test indicated ARR varied significantly only by subgroups created using the proportional hazards model. The hazard ratio for aspirin vs. placebo therapy did not significantly vary by subgroup in any of the models. The highest risk groups for the proportional hazards model and random forest model contained 230 participants each, while the highest risk group in the decision tree model contained 41 participants.ConclusionsThe choice of technique for internally developed models for outcome risk subgroups influences HTE analyses. The rationale for the use of a particular subgroup determination model in HTE analyses needs to be explicitly defined based on desired levels of explainability (with features importance), uncertainty of prediction, chances of overfitting, and assumptions regarding the underlying data structure. Replication of these analyses using data from other mid-size clinical trials may help to establish guidance for selecting an outcomes risk prediction modelling technique for HTE analyses.

Project description:BackgroundIn preventive drug trials such as intermittent preventive treatment for malaria prevention during pregnancy (IPTp), where there is repeated treatment administration, recurrence of adverse events (AEs) is expected. Challenges in modelling the risk of the AEs include accounting for time-to-AE and within-patient-correlation, beyond the conventional methods. The correlation comes from two sources; (a) individual patient unobserved heterogeneity (i.e. frailty) and (b) the dependence between AEs characterised by time-dependent treatment effects. Potential AE-dependence can be modelled via time-dependent treatment effects, event-specific baseline and event-specific random effect, while heterogeneity can be modelled via subject-specific random effect. Methods that can improve the estimation of both the unobserved heterogeneity and treatment effects can be useful in understanding the evolution of risk of AEs, especially in preventive trials where time-dependent treatment effect is expected.MethodsUsing both a simulation study and the Chloroquine for Malaria in Pregnancy (NCT01443130) trial data to demonstrate the application of the models, we investigated whether the lognormal shared frailty models with restricted cubic splines and non-proportional hazards (LSF-NPH) assumption can improve estimates for both frailty variance and treatment effect compared to the conventional inverse Gaussian shared frailty model with proportional hazard (ISF-PH), in the presence of time-dependent treatment effects and unobserved patient heterogeneity. We assessed the bias, precision gain and coverage probability of 95% confidence interval of the frailty variance estimates for the models under varying known unobserved heterogeneity, sample sizes and time-dependent effects.ResultsThe ISF-PH model provided a better coverage probability of 95% confidence interval, less bias and less precise frailty variance estimates compared to the LSF-NPH models. The LSF-NPH models yielded unbiased hazard ratio estimates at the expense of imprecision and high mean square error compared to the ISF-PH model.ConclusionThe choice of the shared frailty model for the recurrent AEs analysis should be driven by the study objective. Using the LSF-NPH models is appropriate if unbiased hazard ratio estimation is of primary interest in the presence of time-dependent treatment effects. However, ISF-PH model is appropriate if unbiased frailty variance estimation is of primary interest.Trial registrationClinicalTrials.gov; NCT01443130.

Dataset Information

A comparison of statistical methods for the study of etiologic heterogeneity.

Publications

A comparison of statistical methods for the study of etiologic heterogeneity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets