Last‐Observation‐Carried‐Forward Imputation Method in Clinical Efficacy Trials: Review of 352 Antidepressant Studies

Abstract

The percentage of clinical antidepressant trials using the LOCF method and the percentage of study subjects' data imputed by using LOCF increased many-fold during 1965-2004. Published reports of trials provided little information to allow readers to assess possible bias introduced by use of the LOCF method.

Randomized, Placebo-Controlled Trials of Antidepressants for Acute Major Depression: Thirty-Year Meta-Analytic Review

“…The present findings are congruent with reviews discussed above indicating that antidepressant drug-vs-placebo differences in published reports of controlled trials are generally moderate (Baldessarini, 2005;Gartlehner et al, 2008;Kirsch et al, 2008;Tsapakis et al, 2008;Bridge et al, 2009;Wooley et al, 2009;Masi et al, 2010;Pigott et al, 2010;Khin et al, 2011). This conclusion was reached in the previous literature despite typical reliance on initial improvement on scale ratings rather than less readily achieved clinical remission, and despite growing evidence of publication bias toward underreporting of studies without significant drugplacebo differences (Ioannidis, 2008;Turner et al, 2008).…”

“…The superiority of most clinically employed antidepressants over placebos in controlled trials has been modest in adult patients diagnosed with major depression, even lower in juvenile depressed patients, and probably has declined in recent years (Walsh et al, 2002;Baldessarini, 2005;Cipriani et al, 2007;Papakostas et al, 2007;Gartlehner et al, 2008;Kirsch et al, 2008;Tsapakis et al, 2008;Bridge et al, 2009;Wooley et al, 2009;Masi et al, 2010;Pigott et al, 2010;Khin et al, 2011). Evident decline in superiority of drugs over placebos has occurred despite evidence of selective reporting of positive findings of potential commercial interest from therapeutic trials (Ioannidis, 2008;Turner et al, 2008).…”

“…Possible differentiation of efficacy among antidepressants was a lively question soon after introduction of the SRIs and SNRIs (Healy, 1997;Baldessarini, 2005Baldessarini, , 2012. However, the popularity of most modern antidepressants owes far more to their perceived safety, relative ease of use, and broad clinical utility rather than to well-demonstrated superior efficacy in major depressive disorder compared with older agents (Baldessarini, 2005(Baldessarini, , 2012Cipriani et al, 2007;Papakostas et al, 2007;Wooley et al, 2009;Pigott et al, 2010;Khin et al, 2011).…”

High frequency repetitive transcranial magnetic stimulation treatment for major depression: Dissociated effects on psychopathology and neurocognition

“…Participant attrition was handled using the last-observationcarried-forward (LOCF) approach (Woolley, Cardoni, & Goethe, 2009). To investigate the effects of HF-rTMS on psychopathology, decision-making and impulse control we employed repeated measures analysis of variance (ANOVA) with time (i.e., pre-rTMS, post-rTMS) as the independent within-subjects variable, and the difference in pre-post scores on the depression/anxiety scales and the neurocognitive tasks as the dependent variable.…”

Designing Quality Health Services Research: Why Comparative Effectiveness Studies Are Needed and Why Pharmacists Should Be Involved

“…However, another group of authors nicely describe the hazards of using the last-observation-carried-forward imputation methods in clinical trials. 26 Ideally, multiple methods should be employed for missing data to determine if the results are robust and can withstand many manipulations including modeling. 16,24 For instance, general estimating equations and linear mixed models do not require an equal number of observations and provide valid inferences if data are missing at random.…”