Ongoing research projects
Addressing continuous missing outcome data in meta-analysis
A common and simple approach to deal with missing data is to restrict analysis to individuals for whom the outcome was obtained (complete case analysis). However, estimated treatment effects from complete case analyses are potentially biased if informative missing data are ignored. We develop methods for estimating meta-analytic summary treatment effects for continuous outcomes in the presence of missing data for some of the individuals within the trials. We build on a method previously developed for binary outcomes, which quantifies the degree of departure from a missing at random (MAR) assumption via the informative missingness odds ratio (IMOR). Our new model quantifies the degree of departure from MAR using either an informative missingness difference of means (IMDoM) or an informative missingness ratio of means (IMRoM), both of which relate the mean value of the missing outcome data to that of the observed data. We propose estimating the treatment effects, adjusted for informative missingness, and their standard errors by a Taylor series approximation and by a Monte Carlo method. We apply the methodology to examples of both pairwise and network meta-analysis with multi-arm trials.
To access material from a workshop in "Accounting for missing outcome data in meta-analysis" go to Workshops.
The work was presented in the 35th Annual Conference of the International Society for Clinical Biostatistics. You can find the slides of the presentation here.
The full paper is published at Statistics in Medicine (Mavridis D, White IR, Higgins JPT, Cipriani A, Salanti G. Allowing for uncertainty due to missing continuous outcome data in pairwise and network meta-analysis. Stat Med. 2014 [Early view])
Accounting for imperfect ‘Last Observation Carried Forward’ outcome imputation in a meta-analysis model
We propose a meta-analytic model that accounts for possible error in the effect sizes estimated in studies with LOCF imputed patients. Assuming a dichotomous outcome, we decompose the probability of a successful unobserved outcome taking into account the sensitivity and specificity of the LOCF imputation process for the missing participants. We fit the proposed model within a Bayesian framework, exploring different prior formulations for sensitivity and specificity. We illustrate our methods performing a meta-analysis of five studies comparing the efficacy of amisulpride versus conventional drugs (flupenthixol and haloperidol) on patients diagnosed with schizophrenia. Our meta-analytic models yield estimates similar to meta-analysis with LOCF-imputed patients. Allowing for uncertainty in the imputation process, precision is decreased depending on the priors used for sensitivity and specificity. Results on the significance of amisulpride versus conventional drugs differ between the standard LOCF approach and our model depending on prior beliefs on the imputation process. Our method can be regarded as a useful sensitivity analysis that can be used in the presence of concerns about the LOCF process.
A paper that describes our suggested methodology has been published by Statistics in Medicine (Dimitrakopoulou V., Efthimiou O. Leucht S., Salanti G. “Accounting for imperfect ‘Last Observation Carried Forward’ outcome imputation in a meta-analysis model increases uncertainty in the results”, Statistics in Medicine, 34, 742–752, doi: 10.1002/sim.6364)
Empirical evidence about reporting missing outcome data in systematic reviews in mental health.
This project aims to provide empirical evidence about the reporting of methodology to account and present missing outcome data and the acknowledgement of their impact in Cochrane systematic reviews in the mental health field. We review systematic reviews published in the Cochrane Database of Systematic Reviews after 1/1/2009 by the Cochrane Review Groups: Depression, Anxiety and Neurosis, Developmental, Psychosocial and Learning Problems and the Schizophrenia Review Group with respect to the reporting and handling missing outcome data.
The full paper is published at Research Synthesis Methods (Spineli LM, Pandis N, Salanti G. Allowing for uncertainty due to missing continuous outcome data in pairwise and network meta-analysis. Res Synth Meth. 2015 [Early view])
Publications from MissOPTIMA
- Mavridis D, White IR, Higgins JPT, Cipriani A, Salanti G. Allowing for uncertainty due to missing continuous outcome data in pairwise and network meta-analysis. Stat Med. 2014 [Early view]
- Spineli LM, Pandis N, Salanti G. Allowing for uncertainty due to missing continuous outcome data in pairwise and network meta-analysis. Res Synth Meth. 2015 [Early view]
- Dimitrakopoulou V, Eftimiou O, Leucht S, Salanti G. Reporting and handling missing outcome data in mental health: a systematic review of Cochrane systematic reviews and meta‐analyses. Stat Med. 2014 [Early view]
- Chaimani A. Accounting for baseline differences in meta-analysis. Evid Based Mental Health 2015;18:23-26.
- Chaimani A, Mavridis D, Salanti G. A hands-on practical tutorial on performing meta-analysis with Stata. Evid Based Mental Health 2014; 17(4): 76-86. The data and a Stata script that produces all results can be found here.
- Mavridis D, Chaimani A, Efthimiou O, Salanti G. Missing outcome data in meta-analysis. Evid Based Ment Health. 2014 Jul 9. pii: ebmental-2014-101899. doi: 10.1136/eb-2014-101899.
- Mavridis D, Chaimani A, Efthimiou O, Leucht S, Salanti G. Addressing missing outcome data in meta-analysis. Evid Based Ment Health. 2014 Aug;17(3):85-9.
- Samara MT, Spineli LM, Furukawa TA, Engel RA, Davis JM, Salanti G, Leucht S. "Imputation of response rates from means and standard deviations in schizophrenia" Schizophrenia research 151 (1), 209-214
- Spineli LM, Leucht S, Cipriani A, Higgins JP, Salanti G. “The Impact of Trial Characteristics on Premature Discontinuation of Antipsychotics in Schizophrenia.” Neuropsychopharmacology 2013 Sep;23(9):1010-6.
Presentations/Talks/Posters from MissOPTIMA
- 5th Hellenic Conference of the Forum of Public Health and Social Medicine, Thessaloniki “Missing data in clinical trials” by Orestis Efthimiou, slides here (in Greek)
- Hellenic Conference of the Forum of Public Health and Social Statistics, Athens “The Impact of Trial Characteristics on Premature Discontinuation of Antipsychotics in Schizophrenia.” by Loukia Spineli
- 23th Annual Conference of the International Society for Clinical Biostatistics, Ludwig-Maximilians-Universität, Munich, Germany “Evaluating the impact of imputations for missing participant outcome data in network meta-analysis.” by Loukia Spineli