Mon programme de recherche se place à l'intersection de l'inférence causale et de la modélisation prédictive, avec un intérêt particulier pour l'utilisation d'approches d'apprentissage automatique ensemblistes. Au travers de mes différents projets de recherche, j'ai entre autres développé un algorithme de prédiction dynamique personnalisée en dialyse et un algorithme de vérification de la présupposition causale de positivité. Plus largement, je m'intéresse aux analyses de survie, à la médiation, à la transportabilité et au transfert de connaissances interdisciplinaires. 

J'ai actuellement deux financements pour des doctorants, un en causalité et un en prédiction. N'hésitez pas à me contacter si intéréssé.

Publications méthodologiques :

• Chatton A, Schomaker M, Luque-Fernandez M-A, Platt RW, and Schnitzer ME. Is the sequential positivity assumption getting you down? Try sPort! (2025) Accepted in Epidemiology
• Chatton A, Bally M, Lévesque R, Malenica, I, Platt RW, and Schnitzer ME. Personalised dynamic super learning: an application in predicting convection volumes in hemodiafiltration. (2024) Journal of the Royal Statistical Society, Series C 
• Chatton A and Rohrer JM. The causal cookbook: recipes for propensity score, g-computation and doubly robust standardisation (2024). Advances in Methods and Practices in Psychological Science, 7(1) 
• Danelian G, Le Borgne F, Léger M, Foucher Y, and Chatton A. Identification of in-sample positivity violations using regression trees: the PoRT algorithm (2023). Journal of Causal Inference, 11(1):20220032 
• Chatton A, Le Borgne F, Leyrat C, and Foucher Y. G-computation and doubly robust standardisation for continuous-time data: a comparison with inverse probability weighting (2022). Statistical Methods in Medical Research, 31(4):706-718 
• Léger M, Chatton A, Le Borgne F, Pirracchio R, Lasocki S, and Foucher Y. Causal inference in case of near-violation of positivity: comparison of methods (2022). Biometrical Journal, 64(8):1389-1403 
• Chatton A, Le Borgne F, Leyrat C, Gillaizeau F, Rousseau C, Barbin L, et al. G-computation, propensity score-based methods, and targeted maximum likelihood estimator for causal inference with different covariates sets: a comparative simulation study (2020). Scientific Reports, 10(1):9219. 

Publications appliquées :

• Haber NA, Wieten SE, Rohrer JM, ..., Chatton A et al. Causal and Associational Linking Language From Observational Research and Health Evaluation Literature in Practice: A systematic language evaluation (2022). American Journal of Epidemiology, 191(12):2084-2097 
• Féray C, Taupin J-L, Sebagh M, ..., Chatton A, et al. Donor HLA Class 1 Evolutionary Divergence Is a Major Predictor of Liver Allograft Rejection (2021). Annals of Internal Medicine, 174(10):1385-1394 
• Lejeune F, Chatton A, Laplaud D-A, Le Page E, Wiertlewski S, Edan G, et al. SMILE: a predictive model for Scoring the severity of relapses in MultIple scLErosis (2021). Journal of Neurology, 268(2):669–679. 

Prépublications :

• Chatton A, Assob Feugo K, Pilote E, Cardinal H, Platt RW, and Schnitzer ME. Is the Kidney Transplant Failure Score still accurate? A geographical-temporal evaluation. Submitted
• De Keizer J, Lenain R, Porcher R, Zohar S, Chatton A, and Foucher Y. G-computation for increasing performances of clinical trials with individual randomization and binary response. Submitted
• Chatton A, Pilote E, Assob Feugo K, Cardinal H, Platt RW, and Schnitzer ME. Ten years later, what if we used a super learner instead of a Cox model to build a prognostic score? Submitted
• Brodeur A, Valenta D, Marcoci A, ... , Chatton A, et al. Comparison of human, AI-assisted, and quasi-automated approaches to assessing research reproducibility in quantitative social science. Under review
• Pollock N, Chang J, Onishi E, Chatton A, and Labrecque M. Effectiveness and complications of vasectomy with fascial interposition without mucosal cautery (double open-ended vasectomy): a retrospective cohort study. Submitted
• Chatton A, Lefebvre, G, Gervais J, Schnitzer ME, and Talbot D. The positivity assumption in causal mediation analyses? Checked! In writing