FedECA: A Federated External Control Arm Method for Causal Inference with Time-To-Event Data in Distributed Settings - Centre de recherche des Cordeliers
Pré-Publication, Document De Travail Année : 2024

FedECA: A Federated External Control Arm Method for Causal Inference with Time-To-Event Data in Distributed Settings

Honghao Li
Imke Mayer
  • Fonction : Auteur
  • PersonId : 1122333
Thibault Fouqueray
  • Fonction : Auteur
  • PersonId : 1105614
Jorge Arellano Castro
  • Fonction : Auteur
Zahia Yanes
  • Fonction : Auteur
Shulin Zhao
Félix Balazard

Résumé

External control arms (ECA) can inform the early clinical development of experimental drugs and provide efficacy evidence for regulatory approval. However, the main challenge in implementing ECA lies in accessing real-world or historical clinical trials data. Indeed, regulations protecting patients' rights by strictly controlling data processing make pooling data from multiple sources in a central server often difficult. To address these limitations, we develop a new method, 'FedECA' that leverages federated learning (FL) to enable inverse probability of treatment weighting (IPTW) for time-to-event outcomes on separate cohorts without needing to pool data. To showcase the potential of FedECA, we apply it in different settings of increasing complexity culminating with a real-world use-case in which FedECA provides evidence for a differential effect between two drugs that would have otherwise gone unnoticed. By sharing our code, we hope FedECA will foster the creation of federated research networks and thus accelerate drug development.
Fichier principal
Vignette du fichier
main.pdf (1.89 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04727636 , version 1 (09-10-2024)
hal-04727636 , version 2 (18-10-2024)

Identifiants

Citer

Jean Ogier Du Terrail, Quentin Klopfenstein, Honghao Li, Imke Mayer, Nicolas Loiseau, et al.. FedECA: A Federated External Control Arm Method for Causal Inference with Time-To-Event Data in Distributed Settings. 2024. ⟨hal-04727636v2⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More