No description available.

PhD thesis assessing the role of non-randomized studies with randomized in evidence syntheses of health interventions. / Randomized studies (RS) are considered the best source of evidence for knowledge syntheses (e.g., systematic reviews, health technology assessments, health guidelines, among others) about healthcare interventions. Historically, non-randomized studies (NRS) have been usually discarded from knowledge syntheses of interventions due to their intrinsic risk of bias and confounding, and they are used only when RS are considered unfeasible or unethical to conduct. With better research methods in observational studies and new tools for the evaluation of risk of bias, NRS are more likely to be a helpful source of information when used as replacement, sequential, or complementary evidence. This, together with the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach, provide an opportunity for guiding decisions about using RS and NRS in knowledge synthesis and increasing our certainty in a body of evidence. This work aims to improve research synthesis methods by assessing the role and use of RS and NRS in knowledge syntheses using GRADE. This can help health professionals, researchers, guideline developers, and policy-makers build better and more complete healthcare recommendations. / Thesis / Doctor of Philosophy (PhD) / All recommendations about healthcare interventions (from common medicines to strategies to prevent diseases) should ideally come from an adequate synthesis (e.g., systematic reviews) of the least biased studies. Many researchers and authors of health syntheses consider randomized studies (RS), the ‘gold standard’ to demonstrate if an intervention is truly effective. Unfortunately, they are not always available, feasible, or ethical to conduct. Non-randomized studies (NRS), also called observational studies, can potentially provide complementary evidence for a research question. Unfortunately, they are usually considered of poorer quality because of their intrinsic nature of being prone to bias and confounding. In most circumstances, authors of syntheses discard these types of studies from the outset, without considering their potential for providing evidence that could complement or even replace that from randomized studies. This work aims to improve this situation by offering methods for evaluating the appropriateness of integrating both RS and NRS, guiding authors and researchers in cases where this is possible, hence increasing the certainty in a body of evidence and help all stakeholders reach decisions.

acase@tulane.edu

No description available.

Healthcare decision-makers need high quality evidence to inform policy and practice decisions. Systematic reviews of randomized controlled trials (RCTs), including meta- analyses of study effects, are considered one of the highest forms of evidence to inform such decisions. Most applications of systematic reviews and meta-analyses are based on a standardized cannon of methods that seek to collect, abstract, assess, and synthesize evidence from primary studies to produce a comprehensive and unbiased summary of the evidence. While useful, standard synthesis methods tend to assume simple data structures (e.g., two-arm comparison of a single intervention vs. a similar control evaluated in a parallel individual randomized design) and some practices (e.g., author contact) may not always be supported by empirical evidence. Complex interventions are of increasing focus in healthcare and public health and pose challenges to the standard methods of systematic review and meta-analysis. While different definitions of complex interventions have been proposed, most definitions assume: i) multiple intervention ‘components’ that may or may not interact with each other to increase or decrease observed intervention effects and ii) effect modification by study-specific characteristics (e.g., healthcare setting, patient population). At least three challenges may result from this complexity. First, reviewers will likely have to contact authors for additional information about intervention components and contextual factors that may operate as effect modifiers. Unfortunately, evidence supporting optimal strategies for achieving response from author contact is lacking. Second, complex interventions are often evaluated using a cluster randomized trial (CRT) design that randomize units of patients to different healthcare/health policy interventions. Analyses from CRTs that are not adjusted for the clustering effect are said to have unit of analysis errors, which if incorporated in meta-analyses could lead to biased summary estimates and overly precise confidence intervals (CIs). Methods for reviewers to appropriately appraise abstract evidence from CRTs are limited. Thirdly, standard meta-analyses estimate an overall effect of a singular ‘complex intervention’. Such analyses answer the question “Do complex interventions as a whole lead to a difference in observed outcomes?” and tend to exhibit high statistical heterogeneity since variation in intervention components and effect modifiers are not accounted for. Hierarchical multivariate meta-regression models have been proposed as an alternative synthesis approach for complex interventions to better account for observed heterogeneity and answer the question decision-makers are really interested in; that is “What component(s) (or combination of components) work and under what conditions?”. Hierarchical multivariate meta-regression models however have yet to be applied in the review of complex healthcare interventions. The overall aim of my doctoral research was to explore the utility of three methodological approaches to address these challenges and optimize the synthesis of complex interventions using a large systematic review of diabetes quality improvement interventions as a case study. The first objective of this thesis was to do an RCT evaluation of the effect of telephone call versus repeated email contact of non-responding authors for additional study information on response rates and research costs. We found authors contacted by telephone call were more likely to complete requests for additional information (response rate 36.7% vs. 20.2%; adjusted odds ratio 2.26 [95% CI 1.10-4.76]) but the intervention took more time to deliver in total (20 vs. 10 hours over several months vs. one month) and was more expensive overall (approximately $505 vs. $253). The second objective of this thesis was to better account for evidence from CRTs and involved a descriptive study and a methodological study. The descriptive study described the proportion of studies with unit of analysis errors and the nature of the error (inappropriate analysis versus unclear or incomplete reporting). The methodological study investigated the utility of building a database of intracluster correlation coefficients (ICCs) and use of an ICC posterior predictive distribution model to correct unit of analysis errors identified in the descriptive study. We found that although trials often adjusted for the cluster effect (67% across outcomes; range 25%-81%), most did not report enough information to extract adjusted effect estimates required for meta-analysis (an average of 77% of studies with remaining unit of analysis errors across outcomes; range 42%-100%). We were able to construct a posterior predictive distribution of the ICC for most outcomes in our review using estimates of the ICC obtained from the descriptive study combined with external estimates and use these distributions to impute missing ICCs to correct unit of analysis errors. Finally, the third objective of this thesis was to illustrate the use of hierarchical multivariate meta-regression for quantitative synthesis when estimating the effects of complex interventions and exploring effect heterogeneity. Using an arm-based analysis of post-treatment means of one continuous outcome, we demonstrated that hierarchical multivariate meta-regression models can be used to estimate a ‘response surface’ that accounts for complex intervention multiple components and study characteristics, and these models can be used to infer estimates of component effects, interactions among components, and effect modification by study covariates. Collectively the results from this thesis suggest three methodological approaches (contacting authors by telephone, imputing missing ICCs using a predictive distribution, estimating complex intervention effects using a hierarchical multivariate meta-regression) can be used to optimize the processes of synthesizing complex interventions. Further work is needed to evaluate the impact of additional study-covariates on explaining residual heterogeneity and testing these methods in other reviews of complex interventions.

Le design standard des essais randomisés de phase III suppose le recrutement d'un grand nombre de patients pour assurer un risque α de 0.025 unilatéral et une puissance d'au moins 80%. Ceci s'avérer difficile dans les maladies rares, ou encore si le traitement cible une population spécifique définie par un sous-type moléculaire rare. Nous avons évalué par simulation la performance d'une série d'essais randomisés. Au terme de chaque essai, s'il est associé à une amélioration significative, le traitement expérimental devient le contrôle de l'essai suivant. Les designs ont été évalués pour différents taux de recrutement, différentes sévérités de la maladie, et différentes distributions hypothétiques des effets d'un futur traitement. Nous avons montré, que sous des hypothèses raisonnables, une série d'essais de plus petite taille et avec un risque α relâché est associée à un plus grand bénéfice à long terme que deux essais de design standard. Nous avons enrichi cette approche avec des designs plus flexibles incluant des analyses intermédiaires d'efficacité et/ou futilité, et des designs adaptatifs à trois bras avec sélection de traitement. Nous avons montré qu'une analyse intermédiaire avec une règle d'arrêt pour futilité était associé à un gain supplémentaire et à une meilleure maitrise du risque, contrairement aux règles d'arrêt pour efficacité qui ne permettent pas d'améliorer la performance. Les séries d'essais à trois bras sont systématiquement plus performants que les séries d'essais à deux bras. Dans la troisième de la thèse, nous avons étudié les essais randomisés évaluant un algorithme de traitement plutôt que l'efficacité d'un seul traitement. Le traitement expérimental est déterminé selon la mutation. Nous avons comparé deux méthodes basées sur le modèles de Cox à effets aléatoires pour l'estimation de l'effet traitement dans chaque mutation : Maximum Integrated Partial Likellihood (MIPL) en utilisant le package coxme et Maximum H-Likelihood (MHL) en utilisant le package frailtyHL. La performance de la méthode MIPL est légèrement meilleure. En présence d'un effet traitement hétérogène, les deux méthodes sousestime l'effet dans les mutations avec un large effet, et le surestime dans les mutations avec un modeste effet. / Large sample sizes are required in randomized trials designed to meet typical one-sided α-level of 0.025 and at least 80% power. This may be unachievable in a reasonable time frame even with international collaborations. It is either because the medical condition is rare, or because the trial focuses on an uncommon subset of patients with a rare molecular subtype where the treatment tested is deemed relevant. We simulated a series of two-arm superiority trials over a long research horizon (15 years). Within the series of trials, the treatment selected after each trial becomes the control treatment of the next one. Different disease severities, accrual rates, and hypotheses of how treatments improve over time were considered. We showed that compared with two larger trials with the typical one-sided α-level of 0.025, performing a series of small trials with relaxed α-levels leads on average to larger survival benefits over a long research horizon, but also to higher risk of selecting a worse treatment at the end of the research period. We then extended this framework with more 'flexible' designs including interim analyses for futility and/or efficacy, and three-arm adaptive designs with treatment selection at interim. We showed that including an interim analysis with a futility rule is associated with an additional survival gain and a better risk control as compared to series with no interim analysis. Including an interim analysis for efficacy yields almost no additional gain. Series based on three-arm trials are associated with a systematic improvement of the survival gain and the risk control as compared to series of two-arm trials. In the third part of the thesis, we examined the issue of randomized trials evaluating a treatment algorithm instead of a single drugs' efficacy. The treatment in the experimental group depends on the mutation, unlike the control group. We evaluated two methods based on the Cox frailty model to estimate the treatment effect in each mutation: Maximum Integrated Partial Likellihood (MIPL) using package coxme and Maximum H-Likelihood (MHL) using package frailtyHL. MIPL method performs slightly better. In presence of a heterogeneous treatment effect, the two methods underestimate the treatment effect in mutations where the treatment effect is large, and overestimates the treatment effect in mutations where the treatment effect is small.

<p>Correlated data with complex association structures arise from longitudinal studies and cluster randomized trials. However, some methodological challenges in the design and analysis of such studies or trials have not been overcome. In this thesis, we address three of the challenges: 1) <em>Power analysis for population based longitudinal study investigating gene-environment interaction effects on chronic disease:</em> For longitudinal studies with interest in investigating the gene-environment interaction in disease susceptibility and progression, rigorous statistical power estimation is crucial to ensure that such studies are scientifically useful and cost-effective since human genome epidemiology is expensive. However conventional sample size calculations for longitudinal study can seriously overestimate the statistical power due to overlooking the measurement error, unmeasured etiological determinants, and competing events that can impede the occurrence of the event of interest. 2) <em>Comparing the performance of different multiple imputation strategies for missing binary outcomes in cluster randomized trials</em>: Though researchers have proposed various strategies to handle missing binary outcome in cluster randomized trials (CRTs), comprehensive guidelines on the selection of the most appropriate or optimal strategy are not available in the literature. 3) <em>Comparison of population-averaged and cluster-specific models for the analysis of cluster randomized trials with missing binary outcome</em>: Both population-averaged and cluster-specific models are commonly used for analyzing binary outcomes in CRTs. However, little attention has been paid to their accuracy and efficiency when analyzing data with missing outcomes. The objective of this thesis is to provide researchers recommendations and guidance for future research in handling the above issues.</p> / Doctor of Philosophy (PhD)

Dans les essais randomisés conduits en oncologie médicale, l'effet des traitements est le plus souvent évalué sur plusieurs critères de jugement, dont un ou plusieurs critères de type temps jusqu'à événement. Une analyse globale de l'effet d'un traitement intègre les résultats observés sur l'ensemble des critères de jugement pertinent. Un des objectifs de notre travail était de réaliser une revue systématique de la littérature évaluant les méthodes de recueil, d'analyse et de rapport des événements indésirables et des critères de jugement rapportés par les patients dans les essais de phase III en oncologie médicale. Cette revue a mis en évidence une grande hétérogénéité des méthodes utilisées. De plus les rapports des essais omettaient souvent certaines informations indispensables pour évaluer la validité des résultats rapportés en toxicité ou sur les critères de jugement rapportés par les patients. Un autre objectif de cette thèse était de développer une extension de la méthode des comparaisons par paire généralisées permettant d'évaluer de façon non biaisée la propension au succès en présence de censure lorsqu'un des critères de jugement est de type temps jusqu'à événement. Cette thèse avait également pour objectif de montrer comment les comparaisons par paire pouvaient être utilisées afin d'évaluer la balance bénéfice-risque de traitements innovants dans les essais randomisés. De la même façon, la propension globale au succès permet d'évaluer le bénéfice thérapeutique global lorsqu'un effet positif est attendu sur plusieurs critères de jugement / In medical oncology randomized trials, treatment effect is usually assessed on several endpoints, including one or more time-to-event endpoints. An overall analysis of the treatment effect may include the outcomes observed on all the relevant endpoints. A systematic review of medical oncology phase III trials was conducted. We extracted the methods used to record, analyze and report adverse events and patient-reported outcomes. Our findings show that some methodological aspects of adverse events or patient-reported outcomes collection and analysis were poorly reported. Even when reported, the methods used were highly heterogeneous. Another objective was to develop an extension of the generalized pairwise comparison procedure for time-to-event variables. The extended procedure provides an unbiased estimation of the chance of a better outcome even in presence of highly censored observations. Then, we show how the chance of an overall better outcome can be used to assess the benefit-risk balance of treatment in randomized trials. When a benefit is expected on more than one endpoint, the chance of an overall better outcome assesses the overall therapeutic benefit. The test of the null hypothesis is more powerful than the test based on one single endpoint

La santé publique fondée sur des données probantes doit être basée sur les meilleures preuves disponibles pour prendre des décisions éclairées, afin de mettre en place des interventions dirigées vers le maintien et l’amélioration de la santé, ainsi que vers le bien-être de toute la population. Les essais contrôlés randomisés (ECR) sont souvent utilisés en recherche clinique pour tester les effets d’un médicament, d’une thérapie ou d’une intervention sur un groupe expérimental qui bénéficiera de l’intervention, en le comparant à un groupe contrôle qui recevra un placebo ou aucun traitement. Bien que le débat persiste, les essais randomisés constituent une source importante et, apparemment, de haute qualité pour évaluer l’efficacité des interventions en santé. Dû à de multiples facteurs, les essais randomisés en grappes (ERG) sont largement utilisés pour évaluer la prestation des services de santé et des interventions en santé publique. Dans ce type d’essai, ce ne sont plus des individus qui sont randomisés, mais des groupes d’individus tels que les familles, les médecins, les villages qui vont recevoir l’intervention. Ces interventions peuvent varier pendant la mise en œuvre en raison de divers facteurs liés à la conception de l’intervention, aux participants, aux intervenants ainsi qu’aux facteurs du contexte qui influencent les résultats. Ces facteurs doivent être pris en compte au moment de l’évaluation, et avant la réplication dans d’autres contextes. L’évaluation de la fidélité de la mise en œuvre, outil clé de l’évaluation du processus et élément essentiel du processus de mise à l’échelle, vise à mesurer le degré selon lequel une intervention a été implantée telle que conçue par les concepteurs. Cette thèse a comme objectif principal examiner la fidélité de la mise en œuvre des interventions en santé publique dans le cadre des essais randomisés en grappes, pour savoir si les interventions mises en place sous un modèle contrôlé doivent prendre en compte ce type d’évaluation pour renforcer ces résultats et faciliter leur réplication à grande échelle. Cette thèse comporte deux volets : une revue systématique et une étude de cas unique à trois unités d’analyse selon une approche mixte concomitante. Le premier article évalue la pratique de la fidélité de la mise en œuvre des interventions en santé publique dans le cadre des essais randomisés en grappes des études publiées qui ont été identifiées et incluses dans la révision systématique. La révision systématique met en lumière que les interventions mises en place sous ce modèle ne tiennent pas compte de cette évaluation de façon systématique, que la façon de la faire est très hétérogène, et que l’évaluation n’est pas bien documentée. Les deuxième et troisième articles sont les résultats de recherche de l’évaluation d’une intervention, à travers une étude de cas comme méthode de recherche, qui a été menée, dans un premier temps, pour examiner la plausibilité de la théorie de l’intervention, et, dans un deuxième temps, pour évaluer leur fidélité de la mise en œuvre et leur acceptabilité auprès des participants dans le but de l’améliorer, si nécessaire, avant sa mise en place à grande échelle. L’évaluation de l’intervention met en lumière plusieurs aspects. D’abord, la théorie sous-jacente et le modèle de l’intervention évaluée sont bien conçus pour parvenir aux résultats visés. L’évaluation fournit des points clés et des actions à prendre en considération, pendant le développement des interventions, pour servir les communautés difficiles à atteindre, et pour améliorer les résultats en matière de santé. Ensuite, les résultats ont démontré une fidélité de mise en œuvre élevée. La clarté de la théorie de l'intervention, la motivation et l'engagement des intervenants, ainsi que les réunions périodiques des superviseurs avec les intervenants-terrain expliquent largement le haut niveau de fidélité obtenu. Des facteurs contextuels tels que la distance géographique, l'accès à un téléphone portable, le niveau d'éducation et les normes de genre ont contribué à l'hétérogénéité de la participation du groupe cible de l’intervention. Finalement, cette évaluation souligne que la plateforme mobile combinée à la mobilisation communautaire, composantes clés de l’intervention, ont été bien accueillies par les participants, et pourraient être mis en place à grand échelle. Cette thèse contribue au développement des connaissances sur le plan méthodologique concernant l’évaluation de la fidélité de la mise en œuvre des interventions en santé publique en mettant en relief des lacunes dans ce domaine, et en suggérant un outil pour faire avancer cette pratique évaluative. Cette thèse participe également au renforcement de la recherche dans les sciences de l’implémentation, et apporte sur le plan empirique des éléments clés essentiels pour évaluer la fidélité de la mise en œuvre de ce type d’intervention à l’aide des essais randomisés en grappes, évaluation de cette fidélité qui est l’objet de cette recherche doctorale. / Evidence-based public health should be based on the best available evidence to make informed decisions and to implement interventions aimed at maintaining and improving the health and well-being of all people. Randomized controlled trials (RCTs) are often used in clinical research to test the effects of a drug, therapy, or intervention on an experimental group that may benefit from the intervention, comparing it to a control group that received either a placebo or no intervention treatment. Although the debate persists, randomized controlled trials are an important and objectively high quality method for evaluating the effectiveness of health interventions. Due to multiple factors, cluster randomized trials (CRTs) are widely used to assess the delivery of health services and public health interventions. In this type of trial, it is no longer individuals who are randomized, but groups of individuals such as families, doctors, and village communities who receive the intervention. These interventions may differ during implementation as a result of various factors related to the complexity of the intervention design, context, participants, and stakeholders involved. These factors should be considered at the time of assessment and before replication in other contexts. Implementation fidelity assessment, a key tool in process evaluation, examines study processes to assess the extent to which the intervention was carried out as originally intended. The fidelity of implementation is an essential part of the scale-up process. This thesis aimed to examine the fidelity of implementation of public health interventions in the context of cluster randomized trials, to determine whether the interventions implemented under a controlled model should consider this type of evaluation to strengthen their results and facilitate their replication on a large scale. This thesis has two parts: a systematic review and a single case study with three units of analysis using a mixed triangulated approach. The first article assessed the implementation fidelity of public health interventions in the context of cluster randomized trials. The systematic review highlighted the finding that public health interventions implemented under this model did not systematically consider this type of evaluation, that the way of doing it was very heterogeneous, and that the evaluation was not adequately documented. The second and third articles were the research findings of the evaluation of an intervention, using a case study as the research method, that was conducted to first examine the plausibility of the intervention theory and to better understand the design and context of the intervention being evaluated, and second, to evaluate implementation fidelity and its acceptability among the participants with the aim of making improvements (if necessary) before large-scale replication. The evaluation of the case study highlighted several key findings. First, the results of the evaluation reflected that the underlying theory and model of the public health intervention were well designed to achieve the desired results. The evaluation provided key points and actions to consider during intervention development to serve hard-to-reach communities and improve health outcomes. Further, it was shown that the results demonstrated a high degree of implementation fidelity. The clarity of the theory of the intervention, the motivation and commitment of the stakeholders as well as the periodic meetings of supervisors with the field team largely explained the high level of fidelity obtained. Contextual factors such as geographical distance to the intervention, access to a mobile phone, level of education, and gender norms contributed to the heterogeneity of the participation of the intervention target group. Finally, this evaluation underlined the finding that the mobile platform coupled with community mobilization, both key components of the intervention, were well received by the participants and may be an effective means of improving health knowledge and changing health-related behaviors. This thesis contributes to the development of methodological knowledge concerning the evaluation of the fidelity of implementation of public health interventions by identifying gaps in this field, and by suggesting a tool that facilitates advancing this evaluation practice. This thesis also contributes to the strengthening of research in implementation sciences, and empirically provides key elements essential to assess the fidelity of the implementation of this type of intervention using CRT studies and evaluation of this fidelity, which is the subject of this doctoral research.