Implementation of pattern-mixture models in randomized clinical trials.

Modern analysis of incomplete longitudinal outcomes involves formulating assumptions about the missingness mechanisms and then using a statistical method that produces valid inferences under this assumption. In this manuscript, we define missingness strategies for analyzing randomized clinical trials (RCTs) based on plausible clinical scenarios. Penalties for dropout are also introduced in an attempt to balance benefits against risks. Some missingness mechanisms are assumed to be non-future dependent, which is a subclass of missing not at random. Non-future dependent stipulates that missingness depends on the past and the present information but not on the future. Missingness strategies are implemented in the pattern-mixture modeling framework using multiple imputation (MI), and it is shown how to estimate the marginal treatment effect. Next, we outline how MI can be used to investigate the impact of dropout strategies in subgroups of interest. Finally, we provide the reader with some points to consider when implementing pattern-mixture modeling-MI analyses in confirmatory RCTs. The data set that motivated our investigation comes from a placebo-controlled RCT design to assess the effect on pain of a new compound. Copyright © 2016 John Wiley & Sons, Ltd.

Recent Developments in the Prevention and Treatment of Missing Data.

Recent research has fostered new guidance on preventing and treating missing data, most notably the landmark expert panel report from the National Research Council (NRC) that was commissioned by FDA. One of the findings from that panel was the need for better software tools to conduct missing data sensitivity analyses and frameworks for drawing inference from them. In response to the NRC recommendations, a Scientific Working Group was formed under the Auspices of the Drug Information Association (DIASWG). The present paper is from work of the DIASWG. Specifically, the NRC panel's 18 recommendations are distilled into 3 pillars for dealing with missing data: (1) providing clearly stated objectives and causal estimands; (2) preventing as much missing data as possible; and (3) combining a sensible primary analysis with sensitivity analyses to assess robustness of inferences to missing data assumptions. Sample data sets are used to illustrate how sensitivity analyses can be used to assess robustness of inferences to missing data assumptions. The suite of software tools used to conduct the sensitivity analyses are freely available for public use at www.missingdata.org.uk.

Analysis of an incomplete binary outcome derived from frequently recorded longitudinal continuous data: application to daily pain evaluation.

Randomized clinical trials increasingly collect daily data, frequently using electronic diaries. Such data are usually summarized into an 'intermediate' continuous outcome (such as the mean of the daily values in a period before a scheduled clinic visit). These are in turn often summarized further into a binary outcome, for example, indicating whether the intermediate continuous outcome has improved by a prespecified amount from randomization. This article compares and contrasts statistical approaches for analyzing such binary outcomes when the underlying study is subject to dropout so that some of the underlying diary data are missing. Such analysis involves rigorous rules for the derivation of outcomes, a thorough data exploration for the selection of covariates, and an elucidation of the missingness mechanism. The investigated statistical methods for treatment-effect analysis are based on direct modeling and on multiple imputation and are applied either to the binary outcome or the intermediate continuous outcome or to the daily diary data. These are compared on the basis of criteria for inferences at prespecified times during the follow-up. We show that multiple-imputation methods are particularly well adapted to our context and that missing data imputation on the daily diary data, rather than the derived outcomes, makes best use of the available information. The data set, which motivated our investigation, comes from a placebo-controlled clinical trial to assess the effect on pain of a new compound.

Evaluation of iopentol (Imagopaque 350) in CT enhancement. A multi-centre monitoring trial assessing adverse events and diagnostic information--results from 1,823 patients in France.

OBJECTIVES: To evaluate the safety and efficacy of iopentol 350 mg I/ml (Imagopaque/Ivépaque, Nycomed Imaging AS, Oslo, Norway), a monomeric non-ionic contrast medium for computed tomography, in a large population. To identify predictive factors for patient safety. MATERIALS AND METHODS: One thousand eight hundred and twenty-three (1,823) patients from 48 centres in France were included during a 5-month period. Safety was evaluated by registering adverse events (AEs) reported by the patients, and data were analysed using a multiple factor model. RESULTS: Only 2.6% of the patients experienced AEs other than discomfort. There were no serious AEs. Overall, AEs were more frequent in patients under 50 years of age, in women, and in patients who received contrast medium as a single bolus. Contrast enhancement was considered adequate or better in 98.9% of the patients. A large variation in discomfort (local warmth/chill or pain) frequency was seen between centres, ranging from 0% to 81%. This result implies that factors other than the CM influence the incidence of discomfort. CONCLUSIONS: This first study in a large population shows that iopentol 350 mg I/ml is well tolerated and provides CT images of excellent, good or adequate quality in the vast majority of patients. Age, sex and injection procedure were shown to be independent predictors in the AE survey.

Intracoronary stent implantation without ultrasound guidance and with replacement of conventional anticoagulation by antiplatelet therapy. 30-day clinical outcome of the French Multicenter Registry.

BACKGROUND: Stenting reduces both acute complications of coronary angioplasty and restenosis rates but increases subacute thrombosis rates and hemorrhagic complications when used with coumadin anticoagulation. METHODS AND RESULTS: To simplify postcoronary stenting treatment and to reduce these drawbacks, we evaluated the 1-month outcome of a prospective registry of 2900 patients in whom successful coronary artery stenting was performed without coumadin anticoagulation. Patients received 100 mg/d aspirin and 250 mg/d ticlopidine for 1 month. Low-molecular-weight heparin (LMWH) treatment was progressively reduced in four consecutive stages, from 1-month treatment to none. Event-free outcome at 1 month was achieved in 2816 patients (97.1%). Major stent-related cardiac events were subacute closure in 51 patients (1.8%), including death in 12 (0.5%), acute myocardial infarction in 17 (0.6%), and coronary artery bypass graft surgery in 9 (0.3%). Stent thrombosis was more frequent with balloon size of < 3.0 mm (< or = 2.5 mm, 10%; 3.0 mm, 2.3%; > or = 3.5 mm, 1.0%; P < .001), bail-out situations (6.67% versus 1.38%, P < .001), and patients with unstable angina or acute myocardial infarction (2.2% versus 1.12%, P = .02). Bleeding complications that required transfusion, surgical repair, or both occurred in 55 patients (1.9%). Bleeding complications were related to female gender (4.0% versus 1.51%, P < .001), duration of LMWH treatment (3.83% in phase II/III versus 0.69% in phase IV/V, P < .001), sheath size (6F, 0.52%; 7F, 1.04%; > or = 8F, 4.23%; P < .001), bail-out situations (4.76% versus 1.67%, P < .01), and saphenous graft stenting (4.38% versus 1.75%, P = .04). CONCLUSIONS: These results suggest that poststenting treatment by ticlopidine/aspirin is an effective alternative to coumadin anticoagulation, achieving low rates of subacute closure and bleeding complications. LMWH treatment does not improve subacute reocclusion rates but increases bleeding complications. Furthermore, as bleeding complications were independently related to sheath size, we suggest that stenting with 6F guiding catheters may prevent local complications. Furthermore, the ticlopidine/aspirin combination allows a low-cost stenting strategy without ultrasound assessment of stent deployment and permits short inhospital stay.

Evaluation of the clinical safety of gadodiamide injection, a new nonionic MRI contrast medium for the central nervous system: a European perspective.

Gadodiamide injection is a new nonionic paramagnetic, extracellular contrast medium. Its safety at a dose of 0.1 mmol/kg body weight was evaluated in a large European multicentre trial on adults referred for contrast-enhanced MRI of the central nervous system. Safety analysis was performed on 2102 patients, in whom adverse events during and up to 24 h after injection were recorded. Adverse events related or possibly related to gadodiamide injection were observed in 102 patients. Injection-associated reactions classified as discomfort (sensation of heat or coldness, pain or pressure at the injection site) occurred in 37 patients (1.8%) and other adverse events (e.g. headache, nausea) were observed in 65 patients (3.1%). No serious adverse event was reported. Efficacy analysis, performed on 2273 patients, and based on comparison of T1- and T2-weighted images before and T1-weighted images after injection showed that more diagnostic information was obtained after gadodiamide injection in 1424 (62.6%) patients: management of 386 (17.0%) patients was affected by the new information given and that a new diagnosis was made in 755 (33.3%) patients. Gadodiamide injection was shown to be safe and well tolerated. It represents a nonionic alternative to the current products for MRI of the central nervous system.

Contrast material injection for hepatic helical computed tomography. Comparative study of five protocols.

RATIONALE AND OBJECTIVES: The authors develop and compare contrast material injection protocols suitable for hepatic helical computed tomography. METHODS: One hundred twenty-one patients who underwent contrast-enhanced computed tomography (CT) of the liver with spiral CT imaging were evaluated for enhancement of the liver parenchyma and for post-enhancement attenuation of the aorta and portal vein with iohexol. Patients were assigned randomly to five protocols with different flow rates, volume of contrast material, and scan delays. RESULTS: Mean parenchymal contrast enhancement was statistically significantly higher with protocol 5 (biphasic injection of 100 mL of iohexol 300 (g/100 mL) at a flow rate of 1.5 mL/second followed by 25 mL at 2 mL/second; total iodine load = 37.5 g, with a scan delay of 70 seconds). The highest aortic enhancement and the second highest portal vein enhancement were obtained with this protocol. CONCLUSION: The authors suggest an easily tolerated injection protocol able to ensure high parenchymal liver enhancement and satisfactory aortic and portal vein enhancement. This protocol includes a long scan delay (70 seconds), biphasic low flow injection rate, and a relatively low iodine load.

[Clinical evaluation of the tolerability of gadodiamide, a new nonionic contrast agent in MRI of the central nervous system]. / Evaluation clinique de la tolérance du gadodiamide, nouvel agent de contraste non-ionique pour l'IRM du système nerveux central.

Gadodiamide injection (Gd-DTPA-BMA) is a new non-ionic paramagnetic contrast agent for which the safety at the dose 0.1 mmol/kg was evaluated during a European multicentre study on a large population of adult patients who had an MR examination of the central nervous system with contrast medium. The safety analysis was performed on 2,102 patients by recording the adverse events observed during injection and up to 24 hours after the injection. Adverse events due or probably due to gadodiamide injection were observed in 102 patients (4.4%) with injection-site associated discomfort (heat, coldness, pain at the injection site) in 37 patients (1.8%) and adverse events other than discomfort (headache, nausea, vomiting) in 35 patients (3.1%). No adverse events of severe intensity or death were reported during the trial. Gadodiamide injection was shown to be safe and well tolerated and represents a non-ionic alternative to the current products in the field of MR imaging of the central nervous system.