Systematic review and simulation study of ignoring clustered data in surgical trials.

BACKGROUND: Multiple surgical procedures in a single patient are relatively common and lead to dependent (clustered) data. This dependency needs to be accounted for in study design and data analysis. A systematic review was performed to assess how clustered data were handled in inguinal hernia trials. The impact of ignoring clustered data was estimated using simulations. METHODS: PubMed, Embase and the Cochrane Library were reviewed systematically for RCTs published between 2004 and 2013, including patients undergoing unilateral or bilateral inguinal hernia repair. Study characteristics determining the appropriateness of handling clustered data were extracted. Using simulations, various statistical methods accounting for clustered data were compared with an analysis ignoring clustering by assuming 100 hernias, with a varying percentage of patients having bilateral hernias. RESULTS: Of the 50 eligible trials including patients with bilateral hernias, 20 (40 per cent) did not provide information on how they dealt with clustered data and 18 (36 per cent) avoided clustering by assessing the outcome by patient and not by hernia. None of the remaining 12 trials (24 per cent) considered clustering in the design or analysis. In the simulations, ignoring clustering led to an increased type I error rate of up to 12 per cent and to a loss in power of up to 15 per cent, depending on whether the patient or the hernia was the randomization unit. CONCLUSION: Clustering was rarely considered in inguinal hernia trials. The simulations underline the importance of considering clustering as part of the statistical analysis to avoid false-positive and false-negative results, and hence inappropriate study conclusions.

Risk of malignancies in patients with diabetes treated with human insulin or insulin analogues: a cohort study.

AIMS/HYPOTHESIS: The aim of this cohort study was to investigate the risk of malignant neoplasms and mortality in patients with diabetes treated either with human insulin or with one of three insulin analogues. METHODS: Data were provided by the largest German statutory health insurance fund (time-frame: January 1998 to June 2005 inclusive), on patients without known malignant disease who had received first-time therapy for diabetes mellitus exclusively with human insulin, aspart, lispro or glargine. The primary outcome was the diagnosis of a malignant neoplasm. Data were analysed by multiple Cox regression models adjusting for potential confounders. RESULTS: A total of 127,031 patients were included, with a mean follow-up time of 1.63 (median 1.41, maximum 4.41) years. A positive association between cancer incidence and insulin dose was found for all insulin types. Because patients receiving combined therapy with insulin analogues and human insulin were excluded, the mean daily dose was much lower for glargine than for human insulin, and a slightly lower cancer incidence in the glargine group was found. After adjusting for dose, a dose-dependent increase in cancer risk was found for treatment with glargine compared with human insulin (p < 0.0001): the adjusted HR was 1.09 (95% CI 1.00 to 1.19) for a daily dose of 10 IU, 1.19 (95% CI 1.10 to 1.30) for a daily dose of 30 IU, and 1.31 (95% CI 1.20 to 1.42) for a daily dose of 50 IU. No increased risk was found for aspart (p = 0.30) or lispro (p = 0.96) compared with human insulin. CONCLUSIONS/INTERPRETATION: Considering the overall relationship between insulin dose and cancer, and the lower dose with glargine, the cancer incidence with glargine was higher than expected compared with human insulin. Our results based on observational data support safety concerns surrounding the mitogenic properties of glargine in diabetic patients. Prospective long-term studies are needed to further evaluate the safety of insulin analogues, especially glargine.