Several strategies are available to address this issue. One approach is to group all sorted mediators as a single mediator of interest and decompose the total effect into effects through or without this grouped mediator 17, 18. Another approach is to make a strong cross-world assumption to measure the bounds upper and lower PSE through sensitivity analysis, while the point estimate of PSE is not yet possible to obtain 19. Lin and VanderWeele proposed an interventional approach to estimate analogues of path-specific effects without confounding assumptions not measured with an approach based on regression and a corresponding SAS code 20. However, several limitations of this method are noted. The first is that the result must follow an ordinary linear regression model and that it cannot be fitted to non-linear or generalized linear models. Furthermore, unlike the analysis of the overall effect, the analytical solutions for estimating all PSEs vary substantially in different models, even if the result follows the linear model. Therefore, the software based on has only a few templates