BayesMeCOS
"Bayesian Methods for Clinical and Observational Studies" is the winning project of the University of Florence Young Independent Researcher call, funded by NextGenerationEU.
It all started in 2022 when Alejandra Avalos-Pacheco, Matteo Pedone, and I were at the DiSIA @Unifi. Despite being involved in different projects with different collaborators, we were all directly and indirectly facing the issue of how the traditional development of new drugs and biomarkers following the “one drug, one target disease” strategy is costly and inefficient. Hence, we thought it would have been helpful to research together to create Bayesian Methods for Clinical and Observational Studies that study heterogeneous populations, target several diseases, and test various treatments from the pre-clinical and clinical stages. We then proposed the project intending to help speed up the drug development process while increasing the power of results and biomarker discovery using adaptive randomization. Since then, our research group has grown, first welcoming Norma Alejandra Vergara Lope Gracia to the team, and then Giulio Grossi and Cristian Chiuchiolo.
Currently, we are working on novel and ethical Bayesian adaptive designs that:
integrate data coming from non-concurrent trials;
change the randomization ratios using covariate-dependent models;
provide a way to analyze the study in the presence of intercurrent events, i.e., events that take place after the randomization and may bias the study results in a causal framework;
help evaluate the potential variations in global genomic architecture associated with bacterial genomic information.
research products
Mattei A., Ding P., Ballerini V., Mealli F. (2024) Assessing causal effects in the presence of treatment switching through principal stratification. Bayesian Analysis, forthcoming
Avalos-Pacheco A., Ballerini V., Pedone M., Müller P. (2023) Contributed discussion: "Causal Inference Under Mis-Specification: Adjustment Based on the Propensity Score (with Discussion)", Bayesian Analysis, 18(2), 680-682.
Ballerini V., Bornkamp B., Mattei A., Mealli F., Wang C., Zhang Y. (2023) Evaluating causal effects on time-to-event outcomes in an RCT in Oncology with treatment discontinuation due to adverse events. arXiv:2310.06653v1
Braito L., Ballerini V., Bocci C., Rocco E. (2024) “Integrating traditional and innovative data sources”, report. Available here
Pedone M., Argiento R., Stingo F. C. (2023) Personalized treatment selection model for survival outcomes. Book of Abstract and Short Papers, 14th Scientific Meeting of the Classification and Data Analysis Group. Salerno, September 11-13, 2023 edited by Carla Rampichini, Michele La Rocca, Pietro Coretto, Giuseppe Giordano, Maria Lucia Parrella. Available here