Search

Background: In stark contrast to network-centric view for complex disease, regression-based methods are preferred in disease prediction, especially for epidemiologists and clinical professionals. It remains a controversy whether the network-based methods have advantageous performance than regression-based methods, and to what extent do they outperform.Methods: Simulations under different scenarios (the input variables are independent or in network relationship) as well as an application were conducted to assess the prediction performance of four typical methods including Bayesian network, neural network, logistic regression and regression splines.Results: The simulation results reveal that Bayesian network showed a better performance when the variables were in a network relationship or in a chain structure. For the special wheel network structure, logistic regression had a considerable performance compared to others. Further application on GWAS of leprosy show Bayesian network still outperforms other methods.Conclusion: Although regression-based methods are still popular and widely used, network-based approaches should be paid more attention, since they capture the complex relationship between variables. [ABSTRACT FROM AUTHOR]

Background: In observational studies, matched case-control designs are routinely conducted to improve study precision. How to select covariates for match or adjustment, however, is still a great challenge for estimating causal effect between the exposure E and outcome D.Methods: From the perspective of causal diagrams, 9 scenarios of causal relationships among exposure (E), outcome (D) and their related covariates (C) were investigated. Further various simulation strategies were performed to explore whether match or adjustment should be adopted. The "do calculus" and "back-door criterion" were used to calculate the true causal effect (β) of E on D on the log-odds ratio scale. 1:1 matching method was used to create matched case-control data, and the conditional or unconditional logistic regression was utilized to get the estimators ([Formula: see text]) of causal effect. The bias ([Formula: see text]) and standard error ([Formula: see text]) were used to evaluate their performances.Results: When C is exactly a confounder for E and D, matching on it did not illustrate distinct improvement in the precision; the benefit of match was to greatly reduce the bias for β though failed to completely remove the bias; further adjustment for C in matched case-control designs is still essential. When C is associated with E or D, but not a confounder, including an independent cause of D, a cause of E but has no direct causal effect on D, a collider of E and D, an effect of exposure E, a mediator of causal path from E to D, arbitrary match or adjustment of this kind of plausible confounders C will create unexpected bias. When C is not a confounder but an effect of D, match or adjustment is unnecessary. Specifically, when C is an instrumental variable, match or adjustment could not reduce the bias due to existence of unobserved confounders U.Conclusions: Arbitrary match or adjustment of the plausible confounder C is very dangerous before figuring out the possible causal relationships among E, D and their related covariates. [ABSTRACT FROM AUTHOR]

Background: Confounders can produce spurious associations between exposure and outcome in observational studies. For majority of epidemiologists, adjusting for confounders using logistic regression model is their habitual method, though it has some problems in accuracy and precision. It is, therefore, important to highlight the problems of logistic regression and search the alternative method.Methods: Four causal diagram models were defined to summarize confounding equivalence. Both theoretical proofs and simulation studies were performed to verify whether conditioning on different confounding equivalence sets had the same bias-reducing potential and then to select the optimum adjusting strategy, in which logistic regression model and inverse probability weighting based marginal structural model (IPW-based-MSM) were compared. The "do-calculus" was used to calculate the true causal effect of exposure on outcome, then the bias and standard error were used to evaluate the performances of different strategies.Results: Adjusting for different sets of confounding equivalence, as judged by identical Markov boundaries, produced different bias-reducing potential in the logistic regression model. For the sets satisfied G-admissibility, adjusting for the set including all the confounders reduced the equivalent bias to the one containing the parent nodes of the outcome, while the bias after adjusting for the parent nodes of exposure was not equivalent to them. In addition, all causal effect estimations through logistic regression were biased, although the estimation after adjusting for the parent nodes of exposure was nearest to the true causal effect. However, conditioning on different confounding equivalence sets had the same bias-reducing potential under IPW-based-MSM. Compared with logistic regression, the IPW-based-MSM could obtain unbiased causal effect estimation when the adjusted confounders satisfied G-admissibility and the optimal strategy was to adjust for the parent nodes of outcome, which obtained the highest precision.Conclusions: All adjustment strategies through logistic regression were biased for causal effect estimation, while IPW-based-MSM could always obtain unbiased estimation when the adjusted set satisfied G-admissibility. Thus, IPW-based-MSM was recommended to adjust for confounders set. [ABSTRACT FROM AUTHOR]

Background: In observational studies, matched case-control designs are routinely conducted to improve study precision. How to select covariates for match or adjustment, however, is still a great challenge for estimating causal effect between the exposure E and outcome D., Methods: From the perspective of causal diagrams, 9 scenarios of causal relationships among exposure (E), outcome (D) and their related covariates (C) were investigated. Further various simulation strategies were performed to explore whether match or adjustment should be adopted. The "do calculus" and "back-door criterion" were used to calculate the true causal effect (β) of E on D on the log-odds ratio scale. 1:1 matching method was used to create matched case-control data, and the conditional or unconditional logistic regression was utilized to get the estimators ([Formula: see text]) of causal effect. The bias ([Formula: see text]) and standard error ([Formula: see text]) were used to evaluate their performances., Results: When C is exactly a confounder for E and D, matching on it did not illustrate distinct improvement in the precision; the benefit of match was to greatly reduce the bias for β though failed to completely remove the bias; further adjustment for C in matched case-control designs is still essential. When C is associated with E or D, but not a confounder, including an independent cause of D, a cause of E but has no direct causal effect on D, a collider of E and D, an effect of exposure E, a mediator of causal path from E to D, arbitrary match or adjustment of this kind of plausible confounders C will create unexpected bias. When C is not a confounder but an effect of D, match or adjustment is unnecessary. Specifically, when C is an instrumental variable, match or adjustment could not reduce the bias due to existence of unobserved confounders U., Conclusions: Arbitrary match or adjustment of the plausible confounder C is very dangerous before figuring out the possible causal relationships among E, D and their related covariates.

Background: In stark contrast to network-centric view for complex disease, regression-based methods are preferred in disease prediction, especially for epidemiologists and clinical professionals. It remains a controversy whether the network-based methods have advantageous performance than regression-based methods, and to what extent do they outperform., Methods: Simulations under different scenarios (the input variables are independent or in network relationship) as well as an application were conducted to assess the prediction performance of four typical methods including Bayesian network, neural network, logistic regression and regression splines., Results: The simulation results reveal that Bayesian network showed a better performance when the variables were in a network relationship or in a chain structure. For the special wheel network structure, logistic regression had a considerable performance compared to others. Further application on GWAS of leprosy show Bayesian network still outperforms other methods., Conclusion: Although regression-based methods are still popular and widely used, network-based approaches should be paid more attention, since they capture the complex relationship between variables.