Global sensitivity analysis for repeated measures studies with informative drop-out: A semi-parametric approach

Healthy food prescription incentive programme for adults with type 2 diabetes who are experiencing food insecurity: protocol for a randomised controlled trial, modelling and implementation studies

INTRODUCTION

The high cost of many healthy foods poses a challenge to maintaining optimal blood glucose levels for adults with type 2 diabetes mellitus who are experiencing food insecurity, leading to diabetes complications and excess acute care usage and costs. Healthy food prescription programmes may reduce food insecurity and support patients to improve their diet quality, prevent diabetes complications and avoid acute care use. We will use a type 2 hybrid-effectiveness design to examine the reach, effectiveness, adoption, implementation and maintenance (RE-AIM) of a healthy food prescription incentive programme for adults experiencing food insecurity and persistent hyperglycaemia. A randomised controlled trial (RCT) will investigate programme effectiveness via impact on glycosylated haemoglobin (primary outcome), food insecurity, diet quality and other clinical and patient-reported outcomes. A modelling study will estimate longer-term programme effectiveness in reducing diabetes-related complications, resource use and costs. An implementation study will examine all RE-AIM domains to understand determinants of effective implementation and reasons behind programme successes and failures.

METHODS AND ANALYSIS

594 adults who are experiencing food insecurity and persistent hyperglycaemia will be randomised to a healthy food prescription incentive (n=297) or a healthy food prescription comparison group (n=297). Both groups will receive a healthy food prescription. The incentive group will additionally receive a weekly incentive (CDN$10.50/household member) to purchase healthy foods in supermarkets for 6 months. Outcomes will be assessed at baseline and follow-up (6 months) in the RCT and analysed using mixed-effects regression. Longer-term outcomes will be modelled using the UK Prospective Diabetes Study outcomes simulation model-2. Implementation processes and outcomes will be continuously measured via quantitative and qualitative data.

ETHICS AND DISSEMINATION

Ethical approval was obtained from the University of Calgary and the University of Alberta. Findings will be disseminated through reports, lay summaries, policy briefs, academic publications and conference presentations.

TRIAL REGISTRATION NUMBER

NCT04725630.

PROTOCOL VERSION

Version 1.1; February 2022.

Bayesian sensitivity analyses for longitudinal data with dropouts that are potentially missing not at random: A high dimensional pattern-mixture model

Randomized clinical trials with outcome measured longitudinally are frequently analyzed using either random effect models or generalized estimating equations. Both approaches assume that the dropout mechanism is missing at random (MAR) or missing completely at random (MCAR). We propose a Bayesian pattern-mixture model to incorporate missingness mechanisms that might be missing not at random (MNAR), where the distribution of the outcome measure at the follow-up time t k , conditional on the prior history, differs across the patterns of missing data. We then perform sensitivity analysis on estimates of the parameters of interest. The sensitivity parameters relate the distribution of the outcome of interest between subjects from a missing-data pattern at time t k with that of the observed subjects at time t k . The large number of the sensitivity parameters is reduced by treating them as random with a prior distribution having some pre-specified mean and variance, which are varied to explore the sensitivity of inferences. The missing at random (MAR) mechanism is a special case of the proposed model, allowing a sensitivity analysis of deviations from MAR. The proposed approach is applied to data from the Trial of Preventing Hypertension.

Reflection on modern methods: shared-parameter models for longitudinal studies with missing data

A primary goal of longitudinal studies is to examine trends over time. Reported results from these studies often depend on strong, unverifiable assumptions about the missing data. Whereas the risk of substantial bias from missing data is widely known, analyses exploring missing-data influences are commonly done either ad hoc or not at all. This article outlines one of the three primary recognized approaches for examining missing-data effects that could be more widely used, i.e. the shared-parameter model (SPM), and explains its purpose, use, limitations and extensions. We additionally provide synthetic data and reproducible research code for running SPMs in SAS, Stata and R programming languages to facilitate their use in practice and for teaching purposes in epidemiology, biostatistics, data science and related fields. Our goals are to increase understanding and use of these methods by providing introductions to the concepts and access to helpful tools.

Global sensitivity analysis of randomized trials with nonmonotone missing binary outcomes: Application to studies of substance use disorders

In this paper, we present a method for conducting global sensitivity analysis of randomized trials in which binary outcomes are scheduled to be collected on participants at prespecified points in time after randomization and these outcomes may be missing in a nonmonotone fashion. We introduce a class of missing data assumptions, indexed by sensitivity parameters, which are anchored around the missing not at random assumption introduced by Robins (Statistics in Medicine, 1997). For each assumption in the class, we establish that the joint distribution of the outcomes is identifiable from the distribution of the observed data. Our estimation procedure uses the plug-in principle, where the distribution of the observed data is estimated using random forests. We establish n asymptotic properties for our estimation procedure. We illustrate our methodology in the context of a randomized trial designed to evaluate a new approach to reducing substance use, assessed by testing urine samples twice weekly, among patients entering outpatient addiction treatment. We evaluate the finite sample properties of our method in a realistic simulation study. Our methods have been implemented in an R package entitled slabm.

From Real-World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges

Clinical decision making needs to be supported by evidence that treatments are beneficial to individual patients. Although randomized control trials (RCTs) are the gold standard for testing and introducing new drugs, due to the focus on specific questions with respect to establishing efficacy and safety vs. standard treatment, they do not provide a full characterization of the heterogeneity in the final intended treatment population. Conversely, real-world observational data, such as electronic health records (EHRs), contain large amounts of clinical information about heterogeneous patients and their response to treatments. In this paper, we introduce the main opportunities and challenges in using observational data for training machine learning methods to estimate individualized treatment effects and make treatment recommendations. We describe the modeling choices of the state-of-the-art machine learning methods for causal inference, developed for estimating treatment effects both in the cross-section and longitudinal settings. Additionally, we highlight future research directions that could lead to achieving the full potential of leveraging EHRs and machine learning for making individualized treatment recommendations. We also discuss how experimental data from RCTs and Pharmacometric and Quantitative Systems Pharmacology approaches can be used to not only improve machine learning methods, but also provide ways for validating them. These future research directions will require us to collaborate across the scientific disciplines to incorporate models based on RCTs and known disease processes, physiology, and pharmacology into these machine learning models based on EHRs to fully optimize the opportunity these data present.

Impact of a farmers' market nutrition coupon programme on diet quality and psychosocial well-being among low-income adults: protocol for a randomised controlled trial and a longitudinal qualitative investigation

INTRODUCTION

Low-income populations have poorer diet quality and lower psychosocial well-being than their higher-income counterparts. These inequities increase the burden of chronic disease in low-income populations. Farmers' market subsidies may improve diet quality and psychosocial well-being among low-income populations. In Canada, the British Columbia (BC) Farmers' Market Nutrition Coupon Programme (FMNCP) aims to improve dietary patterns and health among low-income participants by providing coupons to purchase healthy foods from farmers' markets. This study will assess the impact of the BC FMNCP on the diet quality and psychosocial well-being of low-income adults and explore mechanisms of programme impacts.

METHODS AND ANALYSIS

In a parallel group randomised controlled trial, low-income adults will be randomised to an FMNCP intervention (n=132) or a no-intervention control group (n=132). The FMNCP group will receive 16 coupon sheets valued at CAD$21/sheet over 10-15 weeks to purchase fruits, vegetables, dairy, meat/poultry/fish, eggs, nuts and herbs at farmers' markets and will be invited to participate in nutrition skill-building activities. Overall diet quality (primary outcome), diet quality subscores, mental well-being, sense of community, food insecurity and malnutrition risk (secondary outcomes) will be assessed at baseline, immediately post-intervention and 16 weeks post-intervention. Dietary intake will be assessed using the Automated Self-Administered 24-hour Dietary Recall. Diet quality will be calculated using the Healthy Eating Index-2015. Repeated measures mixed-effect regression will assess differences in outcomes between groups from baseline to 16 weeks post-intervention. Furthermore, 25-30 participants will partake in semi-structured interviews during and 5 weeks after programme completion to explore participants' experiences with and perceived outcomes from the programme.

ETHICS AND DISSEMINATION

Ethical approval was obtained from the University of Calgary Conjoint Health Research Ethics Board, Rutgers University Ethics and Compliance, and University of Waterloo Office of Research Ethics. Findings will be disseminated through policy briefs, conference presentations and peer-reviewed publications.

TRIAL REGISTRATION NUMBER

NCT03952338.

Sequentially additive nonignorable missing data modelling using auxiliary marginal information

We study a class of missingness mechanisms, referred to as sequentially additive nonignorable, for modelling multivariate data with item nonresponse. These mechanisms explicitly allow the probability of nonresponse for each variable to depend on the value of that variable, thereby representing nonignorable missingness mechanisms. These missing data models are identified by making use of auxiliary information on marginal distributions, such as marginal probabilities for multivariate categorical variables or moments for numeric variables. We prove identification results and illustrate the use of these mechanisms in an application.

Sensitivity analysis for non-monotone missing binary data in longitudinal studies: Application to the NIDA collaborative cocaine treatment study

Conventional approaches for handling missingness in substance use disorder trials commonly rely upon a single deterministic "worst value" imputation that posits a perfect relationship between missingness and drug use ("missing value = presumed drug use"); this yields biased estimates of treatment effects and their standard errors. Instead, deterministic imputations should be replaced by probabilistic versions that encode researchers prior beliefs that those with missing data are more likely to be using drugs at those occasions. Motivated by this problem, we present a method for handling non-monotone missing binary data in longitudinal studies. Specifically, we consider a joint model that combines a not missing at random (NMAR) selection model with a generalized linear mixed model for longitudinal binary data. The selection model links the distribution of a missing outcome to the corresponding distribution of the outcome for those observed at that occasion via a fixed and known sensitivity parameter. The mixed model for longitudinal binary data assumes the random effects have bridge distributions; the latter yields regression parameters that have both subject-specific and marginal interpretations. This approach is completely transparent about what is being assumed about missing data and can be used as the basis for sensitivity analysis.

A constructive critique of the draft ICH E9 Addendum

In this article, I review the key elements of the proposed International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use E9 Addendum, present a constructive critique, and provide recommendations of how it can be improved. To highlight ideas, I present a case study involving a confirmatory trial for a chronic pain medication.

Best (but oft-forgotten) practices: missing data methods in randomized controlled nutrition trials

Missing data ubiquitously occur in randomized controlled trials and may compromise the causal inference if inappropriately handled. Some problematic missing data methods such as complete case (CC) analysis and last-observation-carried-forward (LOCF) are unfortunately still common in nutrition trials. This situation is partially caused by investigator confusion on missing data assumptions for different methods. In this statistical guidance, we provide a brief introduction of missing data mechanisms and the unreasonable assumptions that underlie CC and LOCF and recommend 2 appropriate missing data methods: multiple imputation and full information maximum likelihood.

Bayesian Approaches for Missing Not at Random Outcome Data: The Role of Identifying Restrictions

Missing data is almost always present in real datasets, and introduces several statistical issues. One fundamental issue is that, in the absence of strong uncheckable assumptions, effects of interest are typically not nonparametrically identified. In this article, we review the generic approach of the use of identifying restrictions from a likelihood-based perspective, and provide points of contact for several recently proposed methods. An emphasis of this review is on restrictions for nonmonotone missingness, a subject that has been treated sparingly in the literature. We also present a general, fully-Bayesian, approach which is widely applicable and capable of handling a variety of identifying restrictions in a uniform manner.

Global sensitivity analysis of clinical trials with missing patient-reported outcomes

Randomized trials with patient-reported outcomes are commonly plagued by missing data. The analysis of such trials relies on untestable assumptions about the missing data mechanism. To address this issue, it has been recommended that the sensitivity of the trial results to assumptions should be a mandatory reporting requirement. In this paper, we discuss a recently developed methodology (Scharfstein et al., Biometrics, 2018) for conducting sensitivity analysis of randomized trials in which outcomes are scheduled to be measured at fixed points in time after randomization and some subjects prematurely withdraw from study participation. The methodology is explicated in the context of a placebo-controlled randomized trial designed to evaluate a treatment for bipolar disorder. We present a comprehensive data analysis and a simulation study to evaluate the performance of the method. A software package entitled SAMON (R and SAS versions) that implements our methods is available at www.missingdatamatters.org .