Long-term effects of autologous bone marrow stem cell treatment in acute myocardial infarction: factors that may influence outcomes

Abstract

Aims: To investigate whether there are important sources of heterogeneity between the findings of different clinical trials which administer autologous stem cell treatment for acute myocardial infarction (AMI) and to evaluate what factors may influence the long-term effects of this treatment.

Methods and results: MEDLINE (1950-January 2011), EMBASE (1974-January 2011), CENTRAL (The Cochrane Library 2011, Issue 1), CINAHL (1982-January 2011), and ongoing trials registers were searched for randomised trials of bone marrow stem cells as treatment for AMI. Hand-searching was used to screen recent, relevant conference proceedings (2005-2010/11). Meta-analyses were conducted using random-effects models and heterogeneity between subgroups was assessed using chi-squared tests. Planned analyses included length of follow-up, timing of cell infusion and dose, patient selection, small trial size effect, methodological quality, loss of follow-up and date of publication. Thirty-three trials with a total of 1,765 participants were included. There was no evidence of bias due to publication or time-lag, methodological quality of included studies, participant drop-out, duration of follow-up or date of the first disclosure of results. However, in long-term follow-ups the treatment seemed more effective when administered at doses greater than 10(8) cells and to patients with more severe heart dysfunction.

Conclusions: Evaluation of heterogeneity between trials has not identified significant sources of bias in this study. However, clinical differences between trials are likely to exist which should be considered when undertaking future trials.

Figure 1. Assessment of risk of bias due to publication and study size on LVEF.

(A) Funnel plot and (B) Egger’s test. No significant risk of publication bias or small study effects was observed.

Figure 2. Forest plot of Weighted Mean Difference [WMD, with 95% CI (confidence interval)] in left ventricular ejection fraction (LVEF) in short-term follow-up.

(A) Twenty-two randomised trials reporting only short-term follow-up and (B) the remaining 14 trials that reported long-term outcome data as well as short-term data. BMSC treatment significantly improved LVEF in trials with short-term follow-up (3.56%, 95% CI 1.74 to 5.37, p<0.0001) as well as in trials with short- and long-term follow-up (2.71%, 95% CI 1.35 to 4.06, p<0.0001).

Figure 3. Forest plot of Weighted Mean Difference [WMD, with 95% CI (confidence interval)] in left ventricular ejection fraction (LVEF) in short-term follow-up sub-grouped by the year of the first results’ disclosure.

(A) Including early studies reporting data in 2004 (3.26%, 95% CI 2.12 to 4.40, p<0.00001).and (B) excluding studies with early reporting in 2004 (2.80%, 95% CI 1.83 to 3.77, p<0.00001). BMSC treatment significantly improved LVEF in both meta-analyses. WMD had overlapping CI and were not significantly different.