Network meta-regression for ordinal outcomes: Applications in comparing Crohn's disease treatments.
Ontology highlight
ABSTRACT:
SUBMITTER: Gwon Y
PROVIDER: S-EPMC7727029 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Ordinal outcomes arise frequently in clinical studies when each subject is assigned to a category and the categories have a natural order. Classification rules for ordinal outcomes may be developed with commonly used regression models such as the full continuation ratio (CR) model (fCR), which allows the covariate effects to differ across all continuation ratios, and the CR model with a proportional odds structure (pCR), which assumes the covariate effects to be constant across all continuation ratios. For settings where the covariate effects differ between some continuation ratios but not all, fitting either fCR or pCR may lead to suboptimal prediction performance. In addition, these standard models do not allow for nonlinear covariate effects. In this article, we propose a sparse CR kernel machine (KM) regression method for ordinal outcomes where we use the KM framework to incorporate nonlinearity and impose sparsity on the overall differences between the covariate effects of continuation ratios to control for overfitting. In addition, we provide data driven rule to select an optimal kernel to maximize the prediction accuracy. Simulation results show that our proposed procedures perform well under both linear and nonlinear settings, especially when the true underlying model is in-between fCR and pCR models. We apply our procedures to develop a prediction model for levels of anti-CCP among rheumatoid arthritis patients and demonstrate the advantage of our method over other commonly used methods.
| S-EPMC4609171 | biostudies-literature
Project description:Background No network meta-analysis has considered the relative efficacy of cilostazol, home exercise therapy, supervised exercise therapy (SET), endovascular revascularization (ER), and ER plus SET (ER+SET) in improving maximum walking distance (MWD) over short- (<1 year), moderate- (1 to <2 years), and long-term (≥2 years) follow-up in people with intermittent claudication. Methods and Results A systematic literature search was performed to identify randomized controlled trials testing 1 or more of these 5 treatments according to Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines. The primary outcome was improvement in MWD assessed by a standardized treadmill test. Secondary outcomes were adverse events and health-related quality of life. Network meta-analysis was performed using the gemtc R statistical package. The Cochrane collaborative tool was used to assess risk of bias. Forty-six trials involving 4256 patients were included. At short-term follow-up, home exercise therapy (mean difference [MD], 89.4 m; 95% credible interval [CrI], 20.9-157.7), SET (MD, 186.8 m; 95% CrI, 136.4-237.6), and ER+SET (MD, 326.3 m; 95% CrI, 222.6-430.6), but not ER (MD, 82.5 m; 95% CrI, -2.4 to 168.2) and cilostazol (MD, 71.1 m; 95% CrI, -24.6 to 167.9), significantly improved MWD (in meters) compared with controls. At moderate-term follow-up, SET (MD, 201.1; 95% CrI, 89.8-318.3) and ER+SET (MD, 368.5; 95% CrI, 195.3-546.9), but not home exercise therapy (MD, 99.4; 95% CrI, -174.0 to 374.9) or ER (MD, 84.2; 95% CrI, -35.3 to 206.4), significantly improved MWD (in meters) compared to controls. At long-term follow-up, none of the tested treatments significantly improved MWD compared to controls. Adverse events and quality of life were reported inconsistently and could not be meta-analyzed. Risk of bias was low, moderate, and high in 4, 24, and 18 trials respectively. Conclusions This network meta-analysis suggested that SET and ER+SET are effective at improving MWD over the moderate term (<2 year) but not beyond this. Durable treatments for intermittent claudication are needed.
| S-EPMC8200724 | biostudies-literature
Project description:In medicine, it is often useful to stratify patients according to disease risk, severity, or response to therapy. Since many diseases arise from complex gene-gene and gene-environment interactions, patient strata may be defined by combinations of genetic and environmental factors. Traditional statistical methods require specifying interactions a priori making it difficult to identify high order interactions. Alternatively, machine learning methods can model complex interactions, however these models are often difficult to interpret in a clinical setting. Logic regression (LR) enables modeling a binary outcome using logical combinations of binary predictors yielding easily interpretable models. However LR, as currently available, cannot model ordinal responses. This paper extends LR to model an ordinal response and the resulting method is called Ordinal Logic Regression (OLR). Several simulations comparing OLR and Classification and Regression Trees (CART) demonstrate that OLR is superior to CART for identifying variable interactions associated with an ordinal response. OLR is applied to data from a study to determine associations between genetic and health factors with severity of adult periodontitis.
| S-EPMC4397503 | biostudies-literature
Project description:We propose a novel approach to predicting disease progression in Alzheimer's disease (AD)--multivariate ordinal regression--which inherently models the ordered nature of brain atrophy spanning normal aging (CTL) to mild cognitive impairment (MCI) to AD. Ordinal regression provides probabilistic class predictions as well as a continuous index of disease progression--the ORCHID (Ordinal Regression Characteristic Index of Dementia) score. We applied ordinal regression to 1023 baseline structural MRI scans from two studies: the US-based Alzheimer's Disease Neuroimaging Initiative (ADNI) and the European based AddNeuroMed program. Here, the acquired AddNeuroMed dataset was used as a completely independent test set for the ordinal regression model trained on the ADNI cohort providing an optimal assessment of model generalizability. Distinguishing CTL-like (CTL and stable MCI) from AD-like (MCI converters and AD) resulted in balanced accuracies of 82% (cross-validation) for ADNI and 79% (independent test set) for AddNeuroMed. For prediction of conversion from MCI to AD, balanced accuracies of 70% (AUC of 0.75) and 75% (AUC of 0.81) were achieved. The ORCHID score was computed for all subjects. We showed that this measure significantly correlated with MMSE at 12 months (? =? -0.64, ADNI and ? = ?-0.59, AddNeuroMed). Additionally, the ORCHID score can help fractionate subjects with unstable diagnoses (e.g. reverters and healthy controls who later progressed to MCI), moderately late converters (12-24 months) and late converters (24-36 months). A comparison with results in the literature and direct comparison with a binary classifier suggests that the performance of this framework is highly competitive.
| S-EPMC4139338 | biostudies-literature
Project description:BACKGROUND:This study aims to compare placebo (PBO) and 7 therapeutic regimens-namely, bronchodilator agents (BAs), hypertonic saline (HS), BA ± HS, corticosteroids (CS), epinephrine (EP), EP ± CS, and EP ± HS-to determine the optimal bronchiolitis treatment. METHODS:We plotted networks using the curative outcome of several studies and specified the relations among the experiments by using mean difference, standardized mean difference, and corresponding 95% credible interval. The surface under the cumulative ranking curve (SUCRA) was used to separately rank each therapy on clinical severity score (CSS) and length of hospital stay (LHS). RESULTS:This network meta-analysis included 40 articles from 1995 to 2016 concerning the treatment of bronchiolitis in children. All 7 therapeutic regimens displayed no significant difference to PBO with regard to CSS in our study. Among the 7 therapies, BA performed better than CS. As for LHS, EP and EP ± HS had an advantage over PBO. Moreover, EP and EP ± HS were also more efficient than BA. The SUCRA results showed that EP ± CS is most effective, and EP ± HS is second most effective with regard to CSS. With regard to LHS, EP ± HS ranked first, EP ± CS ranked second, and EP ranked third. CONCLUSIONS:We recommend EP ± CS and EP ± HS as the first choice for bronchiolitis treatment in children because of their outstanding performance with regard to CSS and LHS.
| S-EPMC7166391 | biostudies-literature
Project description:It is common that in multi-arm randomized trials, the outcome of interest is "truncated by death," meaning that it is only observed or well-defined conditioning on an intermediate outcome. In this case, in addition to pairwise contrasts, the joint inference for all treatment arms is also of interest. Under a monotonicity assumption we present methods for both pairwise and joint causal analyses of ordinal treatments and binary outcomes in presence of truncation by death. We illustrate via examples the appropriateness of our assumptions in different scientific contexts.
| S-EPMC5407214 | biostudies-literature
Project description:BackgroundRecently, network meta-analysis of survival data with a multidimensional treatment effect was introduced. With these models the hazard ratio is not assumed to be constant over time, thereby reducing the possibility of violating transitivity in indirect comparisons. However, bias is still present if there are systematic differences in treatment effect modifiers across comparisons.MethodsIn this paper we present multidimensional network meta-analysis models for time-to-event data that are extended with covariates to explain heterogeneity and adjust for confounding bias in the synthesis of evidence networks of randomized controlled trials. The impact of a covariate on the treatment effect can be assumed to be treatment specific or constant for all treatments compared.ResultsAn illustrative example analysis is presented for a network of randomized controlled trials evaluating different interventions for advanced melanoma. Incorporating a covariate related to the study date resulted in different estimates for the hazard ratios over time than an analysis without this covariate, indicating the importance of adjusting for changes in contextual factors over time.ConclusionAdding treatment-by-covariate interactions to multidimensional network meta-analysis models for published survival curves can be worthwhile to explain systematic differences across comparisons, thereby reducing inconsistencies and bias. An additional advantage is that heterogeneity in treatment effects can be explored.
| S-EPMC3570315 | biostudies-literature
Project description:Precision medicine is an emerging scientific topic for disease treatment and prevention that takes into account individual patient characteristics. It is an important direction for clinical research, and many statistical methods have been proposed recently. One of the primary goals of precision medicine is to obtain an optimal individual treatment rule (ITR), which can help make decisions on treatment selection according to each patient's specific characteristics. Recently, outcome weighted learning (OWL) has been proposed to estimate such an optimal ITR in a binary treatment setting by maximizing the expected clinical outcome. However, for ordinal treatment settings, such as individualized dose finding, it is unclear how to use OWL. In this article, we propose a new technique for estimating ITR with ordinal treatments. In particular, we propose a data duplication technique with a piecewise convex loss function. We establish Fisher consistency for the resulting estimated ITR under certain conditions, and obtain the convergence and risk bound properties. Simulated examples and an application to a dataset from a type 2 diabetes mellitus observational study demonstrate the highly competitive performance of the proposed method compared to existing alternatives.
| S-EPMC6136994 | biostudies-literature
Project description:We study the application of a widely used ordinal regression model, the cumulative probability model (CPM), for continuous outcomes. Such models are attractive for the analysis of continuous response variables because they are invariant to any monotonic transformation of the outcome and because they directly model the cumulative distribution function from which summaries such as expectations and quantiles can easily be derived. Such models can also readily handle mixed type distributions. We describe the motivation, estimation, inference, model assumptions, and diagnostics. We demonstrate that CPMs applied to continuous outcomes are semiparametric transformation models. Extensive simulations are performed to investigate the finite sample performance of these models. We find that properly specified CPMs generally have good finite sample performance with moderate sample sizes, but that bias may occur when the sample size is small. Cumulative probability models are fairly robust to minor or moderate link function misspecification in our simulations. For certain purposes, the CPMs are more efficient than other models. We illustrate their application, with model diagnostics, in a study of the treatment of HIV. CD4 cell count and viral load 6 months after the initiation of antiretroviral therapy are modeled using CPMs; both variables typically require transformations, and viral load has a large proportion of measurements below a detection limit.
| S-EPMC5675816 | biostudies-literature
Project description:BackgroundLogistic random effects models are a popular tool to analyze multilevel also called hierarchical data with a binary or ordinal outcome. Here, we aim to compare different statistical software implementations of these models.MethodsWe used individual patient data from 8509 patients in 231 centers with moderate and severe Traumatic Brain Injury (TBI) enrolled in eight Randomized Controlled Trials (RCTs) and three observational studies. We fitted logistic random effects regression models with the 5-point Glasgow Outcome Scale (GOS) as outcome, both dichotomized as well as ordinal, with center and/or trial as random effects, and as covariates age, motor score, pupil reactivity or trial. We then compared the implementations of frequentist and Bayesian methods to estimate the fixed and random effects. Frequentist approaches included R (lme4), Stata (GLLAMM), SAS (GLIMMIX and NLMIXED), MLwiN ([R]IGLS) and MIXOR, Bayesian approaches included WinBUGS, MLwiN (MCMC), R package MCMCglmm and SAS experimental procedure MCMC.Three data sets (the full data set and two sub-datasets) were analysed using basically two logistic random effects models with either one random effect for the center or two random effects for center and trial. For the ordinal outcome in the full data set also a proportional odds model with a random center effect was fitted.ResultsThe packages gave similar parameter estimates for both the fixed and random effects and for the binary (and ordinal) models for the main study and when based on a relatively large number of level-1 (patient level) data compared to the number of level-2 (hospital level) data. However, when based on relatively sparse data set, i.e. when the numbers of level-1 and level-2 data units were about the same, the frequentist and Bayesian approaches showed somewhat different results. The software implementations differ considerably in flexibility, computation time, and usability. There are also differences in the availability of additional tools for model evaluation, such as diagnostic plots. The experimental SAS (version 9.2) procedure MCMC appeared to be inefficient.ConclusionsOn relatively large data sets, the different software implementations of logistic random effects regression models produced similar results. Thus, for a large data set there seems to be no explicit preference (of course if there is no preference from a philosophical point of view) for either a frequentist or Bayesian approach (if based on vague priors). The choice for a particular implementation may largely depend on the desired flexibility, and the usability of the package. For small data sets the random effects variances are difficult to estimate. In the frequentist approaches the MLE of this variance was often estimated zero with a standard error that is either zero or could not be determined, while for Bayesian methods the estimates could depend on the chosen "non-informative" prior of the variance parameter. The starting value for the variance parameter may be also critical for the convergence of the Markov chain.
| S-EPMC3112198 | biostudies-literature