A multivariate model for the meta-analysis of study level survival data at multiple times

Diet-derived circulating antioxidants, periodontitis and dental caries: A Mendelian randomization study

BACKGROUND AND OBJECTIVE

Given the potential association between oxidative stress, periodontitis and dental caries, whether dietary supplementation with antioxidants is beneficial for periodontitis and dental caries has been widely reported, but remains controversial. This study aims to clarify these relationships through two-sample Mendelian randomization (MR) analysis.

METHODS

Circulating antioxidants (copper, selenium, zinc, ascorbate, β-carotene, lycopene, retinol and vitamin E) were derived from absolute circulating antioxidants and circulating antioxidant metabolites. Summary data of periodontitis and dental caries were obtained from two separate databases, respectively. We performed inverse-variance weighted (IVW) analysis separately in different databases, followed by meta-analysis. The robustness of results was examined by sensitivity analyses, including three complementary MR methods, heterogeneity and pleiotropy tests, and PhenoScanner query.

RESULTS

IVW analysis showed that elevated levels of absolute circulating retinol reduced the risk of periodontitis (GLIDE: OR = 0.41, 95% CI = 0.18-0.95, p = .038, power = 100%; FinnGen: OR = 0.15, 95% CI = 0.04-0.54, p = .004, power = 100%). The pooled OR for periodontitis risk per unit increase of retinol is 0.30 (95% CI = 0.15-0.61, p = .001, I2 = 40.3%, power = 100%). No significant associations were noted for genetically predicted circulating antioxidants and dental caries risk. The sensitivity analyses yielded similar estimates.

CONCLUSION

This study demonstrates that a negative causality between circulating retinol and periodontitis risk, and null linkage between circulating antioxidants and dental caries risk, suggesting potential strategies for the prevention and control of periodontitis.

Challenges of modelling approaches for network meta-analysis of time-to-event outcomes in the presence of non-proportional hazards to aid decision making: Application to a melanoma network

BACKGROUND

Synthesis of clinical effectiveness from multiple trials is a well-established component of decision-making. Time-to-event outcomes are often synthesised using the Cox proportional hazards model assuming a constant hazard ratio over time. However, with an increasing proportion of trials reporting treatment effects where hazard ratios vary over time and with differing lengths of follow-up across trials, alternative synthesis methods are needed.

OBJECTIVES

To compare and contrast five modelling approaches for synthesis of time-to-event outcomes and provide guidance on key considerations for choosing between the modelling approaches.

METHODS

The Cox proportional hazards model and five other methods of estimating treatment effects from time-to-event outcomes, which relax the proportional hazards assumption, were applied to a network of melanoma trials reporting overall survival: restricted mean survival time, generalised gamma, piecewise exponential, fractional polynomial and Royston-Parmar models.

RESULTS

All models fitted the melanoma network acceptably well. However, there were important differences in extrapolations of the survival curve and interpretability of the modelling constraints demonstrating the potential for different conclusions from different modelling approaches.

CONCLUSION

The restricted mean survival time, generalised gamma, piecewise exponential, fractional polynomial and Royston-Parmar models can accommodate non-proportional hazards and differing lengths of trial follow-up within a network meta-analysis of time-to-event outcomes. We recommend that model choice is informed using available and relevant prior knowledge, model transparency, graphically comparing survival curves alongside observed data to aid consideration of the reliability of the survival estimates, and consideration of how the treatment effect estimates can be incorporated within a decision model.

Classifying information-sharing methods

BACKGROUND

Sparse relative effectiveness evidence is a frequent problem in Health Technology Assessment (HTA). Where evidence directly pertaining to the decision problem is sparse, it may be feasible to expand the evidence-base to include studies that relate to the decision problem only indirectly: for instance, when there is no evidence on a comparator, evidence on other treatments of the same molecular class could be used; similarly, a decision on children may borrow-strength from evidence on adults. Usually, in HTA, such indirect evidence is either included by ignoring any differences ('lumping') or not included at all ('splitting'). However, a range of more sophisticated methods exists, primarily in the biostatistics literature. The objective of this study is to identify and classify the breadth of the available information-sharing methods.

METHODS

Forwards and backwards citation-mining techniques were used on a set of seminal papers on the topic of information-sharing. Papers were included if they specified (network) meta-analytic methods for combining information from distinct populations, interventions, outcomes or study-designs.

RESULTS

Overall, 89 papers were included. A plethora of evidence synthesis methods have been used for information-sharing. Most papers (n=79) described methods that shared information on relative treatment effects. Amongst these, there was a strong emphasis on methods for information-sharing across multiple outcomes (n=42) and treatments (n=25), with fewer papers focusing on study-designs (n=23) or populations (n=8). We categorise and discuss the methods under four 'core' relationships of information-sharing: functional, exchangeability-based, prior-based and multivariate relationships, and explain the assumptions made within each of these core approaches.

CONCLUSIONS

This study highlights the range of information-sharing methods available. These methods often impose more moderate assumptions than lumping or splitting. Hence, the degree of information-sharing that they impose could potentially be considered more appropriate. Our identification of four 'core' methods of information-sharing allows for an improved understanding of the assumptions underpinning the different methods. Further research is required to understand how the methods differ in terms of the strength of sharing they impose and the implications of this for health care decisions.

Meta-analyzing count events over varying durations using the piecewise Poisson model: The case for poststroke seizures

Meta-analyzing count data can be challenging when follow-up time varies across studies. Simply pooling aggregate data over time-periods would result in biased estimates, which may erroneously inform clinical decision-making. In this study, we exploit the convolution property of the Poisson distribution to develop a likelihood for observed cumulative counts over varying follow-up periods, where different Poisson distributions are used to represent the data generating processes for the latent counts in pre-defined successive intervals of follow-up. We illustrate this approach using an example of poststroke seizures, a case in which risk may change over time, and mimic its survival duration with time-varying hazard. Data were extracted from observational studies (1997-2016) reporting poststroke seizures over a maximum of 10 years of follow-up. Three clinically meaningful follow-up time intervals were considered: 0 to 7 days, 8 to 365 days, and 1 to 10 years poststroke. External validation was performed using claims data. Results suggest the incidence rate of seizures was 0.0452 (95% confidence interval: 0.0429, 0.0475), 0.0001 (0, 0.016), and 0.0647 (0.0441, 0.0941) for the three time intervals, respectively, indicating that the risk of seizures changes over time poststroke. We found that the model performed well against the incidence rate of seizures among actual retrospective cohort from claims data. The piecewise Poisson model presents a flexible way to meta-analyze count data over time and mimic survival curves. The results of the piecewise Poisson model are readily interpretable and may spur meaningful clinical action. The method may also be applied to other diseases. HIGHLIGHTS: It is challenging to perform a meta-analysis when follow-up time varies across studies. Ideally, outcomes over different time-periods should be pooled with individual patient-level data (IPD). A new model was developed to meta-analyze count data over time using aggregate-level data from previous published studies. The piecewise Poisson model could be a useful tool to estimate time-vary hazards given available data, and mimic survival curves over time which would be readily interpretable.