Target Trial Emulation and Bias Through Missing Eligibility Data: An Application to a Study of Palivizumab for the Prevention of Hospitalization Due to Infant Respiratory Illness.

Target trial emulation (TTE) applies the principles of randomized controlled trials to the causal analysis of observational data sets. One challenge that is rarely considered in TTE is the sources of bias that may arise if the variables involved in the definition of eligibility for the trial are missing. We highlight patterns of bias that might arise when estimating the causal effect of a point exposure when restricting the target trial to individuals with complete eligibility data. Simulations consider realistic scenarios where the variables affecting eligibility modify the causal effect of the exposure and are missing at random or missing not at random. We discuss means to address these patterns of bias, namely: 1) controlling for the collider bias induced by the missing data on eligibility, and 2) imputing the missing values of the eligibility variables prior to selection into the target trial. Results are compared with the results when TTE is performed ignoring the impact of missing eligibility. A study of palivizumab, a monoclonal antibody recommended for the prevention of respiratory hospital admissions due to respiratory syncytial virus in high-risk infants, is used for illustration.

Access to palivizumab among children at high risk of respiratory syncytial virus complications in English hospitals.

AIMS: Palivizumab is a monoclonal antibody which can prevent infection with respiratory syncytial virus (RSV). Due to its high cost, it is recommended for high-risk infants only. We aimed to determine the proportion of infants eligible for palivizumab treatment in England who receive at least one dose. METHODS: We used the Hospital Treatment Insights database, which contains hospital admission records linked to hospital pharmacy dispensing data for 43 out of 153 hospitals in England. Infants born between 2010 and 2016 were considered eligible for palivizumab if their medical records indicated chronic lung disease (CLD), congenital heart disease (CHD) or severe immunodeficiency (SCID), and they met additional criteria based on gestational age at birth and age at start of the RSV season (beginning of October). We calculated the proportion of infants who received at least one dose of palivizumab in their first RSV season, and modelled the odds of treatment according to multiple child characteristics using logistic regression models. RESULTS: We identified 3712 eligible children, of whom 2479 (67%) had complete information on all risk factors. Palivizumab was prescribed to 832 of eligible children (34%). Being born at <30 weeks' gestation, aged <6 months at the start of RSV season, and having two or more of CLD, CHD or SCID were associated with higher odds of treatment. CONCLUSION: In England, palivizumab is not prescribed to the majority of children who are eligible to receive it. Doctors managing these infants may be unfamiliar with the eligibility criteria or constrained by other considerations, such as cost.

A general method for elicitation, imputation, and sensitivity analysis for incomplete repeated binary data.

We develop and demonstrate methods to perform sensitivity analyses to assess sensitivity to plausible departures from missing at random in incomplete repeated binary outcome data. We use multiple imputation in the not at random fully conditional specification framework, which includes one or more sensitivity parameters (SPs) for each incomplete variable. The use of an online elicitation questionnaire is demonstrated to obtain expert opinion on the SPs, and highest prior density regions are used alongside opinion pooling methods to display credible regions for SPs. We demonstrate that substantive conclusions can be far more sensitive to departures from the missing at random assumption (MAR) when control and intervention nonresponders depart from MAR differently, and show that the correlation of arm specific SPs in expert opinion is particularly important. We illustrate these methods on the iQuit in Practice smoking cessation trial, which compared the impact of a tailored text messaging system versus standard care on smoking cessation. We show that conclusions about the effect of intervention on smoking cessation outcomes at 8 week and 6 months are broadly insensitive to departures from MAR, with conclusions significantly affected only when the differences in behavior between the nonresponders in the two trial arms is larger than expert opinion judges to be realistic.

On the use of the not-at-random fully conditional specification (NARFCS) procedure in practice.

The not-at-random fully conditional specification (NARFCS) procedure provides a flexible means for the imputation of multivariable missing data under missing-not-at-random conditions. Recent work has outlined difficulties with eliciting the sensitivity parameters of the procedure from expert opinion due to their conditional nature. Failure to adequately account for this conditioning will generate imputations that are inconsistent with the assumptions of the user. In this paper, we clarify the importance of correct conditioning of NARFCS sensitivity parameters and develop procedures to calibrate these sensitivity parameters by relating them to more easily elicited quantities, in particular, the sensitivity parameters from simpler pattern mixture models. Additionally, we consider how to include the missingness indicators as part of the imputation models of NARFCS, recommending including all of them in each model as default practice. Algorithms are developed to perform the calibration procedure and demonstrated on data from the Avon Longitudinal Study of Parents and Children, as well as with simulation studies.

Simultaneous confidence sets for several effective doses.

Construction of simultaneous confidence sets for several effective doses currently relies on inverting the Scheffé type simultaneous confidence band, which is known to be conservative. We develop novel methodology to make the simultaneous coverage closer to its nominal level, for both two-sided and one-sided simultaneous confidence sets. Our approach is shown to be considerably less conservative than the current method, and is illustrated with an example on modeling the effect of smoking status and serum triglyceride level on the probability of the recurrence of a myocardial infarction.