Melbourne School of Population and Global Health - Research Publications
Permanent URI for this collection
Search Results
1 - 4 of 4
-
ItemA comparison of methods to estimate the survivor average causal effect in the presence of missing data: a simulation study (vol 19, 223, 2019)(BMC, 2020-02-27)In the original publication of this article [1], the incorrect causal diagram was submitted as Fig. 1.
-
ItemA comparison of methods to estimate the survivor average causal effect in the presence of missing data: a simulation study(BMC, 2019-12-03)BACKGROUND: Attrition due to death and non-attendance are common sources of bias in studies of age-related diseases. A simulation study is presented to compare two methods for estimating the survivor average causal effect (SACE) of a binary exposure (sex-specific dietary iron intake) on a binary outcome (age-related macular degeneration, AMD) in this setting. METHODS: A dataset of 10,000 participants was simulated 1200 times under each scenario with outcome data missing dependent on measured and unmeasured covariates and survival. Scenarios differed by the magnitude and direction of effect of an unmeasured confounder on both survival and the outcome, and whether participants who died following a protective exposure would also die if they had not received the exposure (validity of the monotonicity assumption). The performance of a marginal structural model (MSM, weighting for exposure, survival and missing data) was compared to a sensitivity approach for estimating the SACE. As an illustrative example, the SACE of iron intake on AMD was estimated using data from 39,918 participants of the Melbourne Collaborative Cohort Study. RESULTS: The MSM approach tended to underestimate the true magnitude of effect when the unmeasured confounder had opposing directions of effect on survival and the outcome. Overestimation was observed when the unmeasured confounder had the same direction of effect on survival and the outcome. Violation of the monotonicity assumption did not increase bias. The estimates were similar between the MSM approach and the sensitivity approach assessed at the sensitivity parameter of 1 (assuming no survival bias). In the illustrative example, high iron intake was found to be protective of AMD (adjusted OR 0.57, 95% CI 0.40-0.82) using complete case analysis via traditional logistic regression. The adjusted SACE odds ratio did not differ substantially from the complete case estimate, ranging from 0.54 to 0.58 for each of the SACE methods. CONCLUSIONS: On average, MSMs with weighting for exposure, missing data and survival produced biased estimates of the SACE in the presence of an unmeasured survival-outcome confounder. The direction and magnitude of effect of unmeasured survival-outcome confounders should be considered when assessing exposure-outcome associations in the presence of attrition due to death.
-
ItemCan genetic associations change with age? CFH and age-related macular degeneration(OXFORD UNIV PRESS, 2012-12-01)Genetic variation in the gene encoding complement factor H (CFH) on chromosome 1q31 has repeatedly been associated with an increased risk of age-related macular degeneration (AMD); however, previous studies have had inadequate numbers of participants across a sufficiently wide age range to determine whether the association varies by age. We conducted a genetic case-control study using data from 2294 cases and 2294 controls selected from the Melbourne Collaborative Cohort Study, matched on age, sex and region of origin. Four consistently replicated CFH single-nucleotide polymorphisms (SNPs) were genotyped: rs1061170 (Y402H), rs2274700, rs393955 and rs800292; their relationship with AMD prevalence was determined across the age range 48-86. A difference in genotype frequencies was seen across age groups, where the low-risk homozygote prevalence rose with each increasing age group. Associations with early AMD were strongly modified by age for three of the four SNPs (interaction P-value: 0.01-0.00003). An inverse association between the high-risk homozygote for each SNP and early AMD was observed in the younger age groups [odds ratios (OR) range 0.37-0.48 for age <55], reversing to a positive association with increasing age (OR 1.87-2.8 for age >75). The direction of associations for this gene change was from inverse to risk with increasing age. These findings have important implications for predictive models for AMD and potentially other age-related diseases which extrapolate risks from older cohorts, as they assume homogeneity of association by age, which might not exist.
-
ItemNo Preview Available20/20-Alcohol and Age-related Macular Degeneration: The Melbourne Collaborative Cohort Study(OXFORD UNIV PRESS INC, 2012-08-15)Little evidence exists regarding associations between age-related macular degeneration (AMD) and moderate alcohol consumption, patterns of consumption, or different types of alcoholic beverage. The authors examined associations between AMD prevalence and alcohol intake using 20,963 participants from the Melbourne Collaborative Cohort Study aged 40-69 years at baseline (1990-1994). Participants' alcohol consumption was determined from a structured interview at baseline. At follow-up from 2003 to 2007, digital macula photographs of both eyes were taken and evaluated for early and late AMD signs. Drinking more than 20 g of alcohol per day was associated with an approximate 20% increase in the odds of early AMD (odds ratio = 1.21, 95% confidence interval: 1.06, 1.38; P = 0.004) when compared with those who reported no alcohol intake at baseline, having adjusted for sex, age, smoking, country of birth, education, physical activity, and energy from food. This positive association was apparent for wine, beer, and spirits. The estimates were similar for both sexes. The odds ratio for those drinking more than 20 g of alcohol per day for late AMD was 1.44 (95% confidence interval: 0.85, 2.45; P = 0.17). These results show a modest association between alcohol consumption and increased AMD risk.