One of the primary objectives of CAN-AIM is to develop and validate new methods that will enhance the analyses of prospective studies of drug safety and effectiveness.
In 2011-2014, the methodology experts among our team members, together with our trainees and collaborators, have continued active research on the development, validation and applications of novel statistical and epidemiological methods directly relevant to CAN-AIM objectives.
Specifically, our recent research activities focused mostly on two major methodological challenges, essential for the validity, accuracy and/or efficiency of the analyses of prospective, observational, longitudinal post-marketing studies of real-life safety and effectiveness of medications: (i) improvement of the accuracy of drug exposure modeling; and (ii) controlling for biases due to different sources of confounding.
In addition, we have initiated research, with our trainees, on more specialized, and relatively less studied, methodological issues frequently encountered in real-life studies of adverse or intended effects of drugs, related to (iii) reducing residual confounding, due to mis-modeling the confounder effects; (iv) exposure measurement errors; and (v) accounting for measurement problems or uncertainty regarding the outcomes.
- Flexible modeling of time-varying drug use:
- Extending the weighted cumulative exposure (WCE) method to marginal structural models:
- Xiao Y, Abrahamowicz M, Moodie EEM, Weber R, Young J. Flexible marginal structural models for estimating the cumulative effect of a time-dependent treatment on the hazard: reassessing the cardiovascular risks of didanosine treatment in the Swiss HIV cohort study. Journal of the American Statistical Association. 2014 Jun;109(506):455-464.
- Improving efficiency of instrumental variables (IV) corrections for unmeasured confounding:
- Abrahamowicz M, Beauchamp M-E, Ionescu-Ittu R, Delaney JCA, Pilote L. Reducing the variance of the prescribing preference-based instrumental variable estimates of the treatment effect. American Journal of Epidemiology. 2011 Aug 15;174(4):494-502.
- Ionescu-Ittu R, Abrahamowicz M, Pilote L. Treatment effect estimates varied depending on the definition of the provider prescribing preference-based instrumental variables. Journal of Clinical Epidemiology. 2012 Feb; 65(2):155-162.
- Validating multi-stage approaches to test for treatment effect modifications and for subgroup-specific treatment effects:
- Extending the weighted cumulative exposure (WCE) method to active pharmaco-vigillance:
- Novel “Missing cause’ approach (alternative to IV’s) to control for unmeasured confounding: