arXiv subjects

Arthur Chatton

Publications and source records attributed to Arthur Chatton.

5 recordsLinked to original sources

arXiv2026

The positivity assumption in causal mediation analyses? Checked!

Causal mediation analyses are increasingly used in psychological sciences. Among the required assumptions, positivity is unfortunately seldom mentioned, likely due to the lack of tools for checking it. Mediational positivity is more complex than positivity in standard, non-mediated exposure effect analysis, because it requires positivity for both the exposure and the mediator, and because the specific form of the positivity assumption depends on the mediation estimand of interest. We propose an extension of the Positivity Regression Trees (PoRT) algorithm -- which was recently designed to check positivity in non-mediated settings without requiring assumptions about the modeling or the data-generating process -- to controlled, natural and interventional mediational effects. We illustrate its use through an application in mental health and have made it accessible through the port R package and a related notebook available at github.com/ArthurChatton/dePoRT-notebook. Finally, we discuss consequences and provide recommendations for when positivity violations are identified.

stat.ME↗

arXiv2024

What if we had built a prediction model with a survival super learner instead of a Cox model 10 years ago?

Objective: This study sought to compare the drop in predictive performance over time according to the modeling approach (regression versus machine learning) used to build a kidney transplant failure prediction model with a time-to-event outcome. Study Design and Setting: The Kidney Transplant Failure Score (KTFS) was used as a benchmark. We reused the data from which it was developed (DIVAT cohort, n=2,169) to build another prediction algorithm using a survival super learner combining (semi-)parametric and non-parametric methods. Performance in DIVAT was estimated for the two prediction models using internal validation. Then, the drop in predictive performance was evaluated in the same geographical population approximately ten years later (EKiTE cohort, n=2,329). Results: In DIVAT, the super learner achieved better discrimination than the KTFS, with a tAUROC of 0.83 (0.79-0.87) compared to 0.76 (0.70-0.82). While the discrimination remained stable for the KTFS, it was not the case for the super learner, with a drop to 0.80 (0.76-0.83). Regarding calibration, the survival SL overestimated graft survival at development, while the KTFS underestimated graft survival ten years later. Brier score values were similar regardless of the approach and the timing. Conclusion: The more flexible SL provided superior discrimination on the population used to fit it compared to a Cox model and similar discrimination when applied to a future dataset of the same population. Both methods are subject to calibration drift over time. However, weak calibration on the population used to develop the prediction model was correct only for the Cox model, and recalibration should be considered in the future to correct the calibration drift.

stat.ME↗

arXiv2024

Is checking for sequential positivity violations getting you down? Try sPoRT!

Background: Sequential positivity is often a necessary assumption for drawing causal inferences, such as through marginal structural modeling. Unfortunately, verification of this assumption can be challenging because it usually relies on multiple parametric propensity score models, unlikely all correctly specified. Therefore, we propose a new algorithm, called sequential Positivity Regression Tree (sPoRT), to overcome this issue and identify the subgroups found to be violating this assumption, allowing for insights about the nature of the violations and potential solutions. Methods: We present different versions of sPoRT based on either stratifying or pooling over time under static or dynamic treatment strategies. This methodological development was motivated by a real-life application of the impact of the timing of initiation of HIV treatment with and without smoothing over time, which we also use to demonstrate the method. Results: The illustration of sPoRT demonstrates its easy use and the interpretability of the results for applied epidemiologists. Furthermore, an R notebook showing how to use sPoRT in practice is available at github.com/ArthurChatton/sPoRT-notebook. Conclusions: The sPoRT algorithm provides interpretable subgroups violating the sequential positivity violation, allowing patterns and trends in the confounders to be easily identified. We finally provided practical implications and recommendations when positivity violations are identified.

stat.ME↗

arXiv2024

G-computation for increasing performances of clinical trials with individual randomization and binary response

In a clinical trial, the random allocation aims to balance prognostic factors between arms, preventing true confounders. However, residual differences due to chance may introduce near-confounders. Adjusting on prognostic factors is therefore recommended, especially because the related increase of the power. In this paper, we hypothesized that G-computation associated with machine learning could be a suitable method for randomized clinical trials even with small sample sizes. It allows for flexible estimation of the outcome model, even when the covariates' relationships with outcomes are complex. Through simulations, penalized regressions (Lasso, Elasticnet) and algorithm-based methods (neural network, support vector machine, super learner) were compared. Penalized regressions reduced variance but may introduce a slight increase in bias. The associated reductions in sample size ranged from 17\% to 54\%. In contrast, algorithm-based methods, while effective for larger and more complex data structures, underestimated the standard deviation, especially with small sample sizes. In conclusion, G-computation with penalized models, particularly Elasticnet with splines when appropriate, represents a relevant approach for increasing the power of RCTs and accounting for potential near-confounders.

stat.ME↗

arXiv2023

Personalised dynamic super learning: an application in predicting hemodiafiltration convection volumes

Obtaining continuously updated predictions is a major challenge for personalised medicine. Leveraging combinations of parametric regressions and machine learning approaches, the personalised online super learner (POSL) can achieve such dynamic and personalised predictions. We adapt POSL to predict a repeated continuous outcome dynamically and propose a new way to validate such personalised or dynamic prediction models. We illustrate its performance by predicting the convection volume of patients undergoing hemodiafiltration. POSL outperformed its candidate learners with respect to median absolute error, calibration-in-the-large, discrimination, and net benefit. We finally discuss the choices and challenges underlying the use of POSL.

stat.ME↗