Imagen de Portada

FedECA: federated external control arms for causal inference with time-to-event data in distributed settings

Guardado en:
Publicado en:Nature Communications vol. 16, no. 1 (2025), p. 7496-7518
Autor principal: Ogier du Terrail, Jean
Otros Autores: Klopfenstein, Quentin, Li, Honghao, Mayer, Imke, Loiseau, Nicolas, Hallal, Mohammad, Debouver, Michael, Camalon, Thibault, Fouqueray, Thibault, Arellano Castro, Jorge, Yanes, Zahia, Dahan, Laëtitia, Taïeb, Julien, Laurent-Puig, Pierre, Bachet, Jean-Baptiste, Zhao, Shulin, Nicolle, Remy, Cros, Jérôme, Gonzalez, Daniel, Carreras-Torres, Robert, Garcia Velasco, Adelaida, Abdilleh, Kawther, Doss, Sudheer, Balazard, Félix, Andreux, Mathieu
Publicado:
Nature Publishing Group
Materias:
Food & Drug Administration > FDA
Clinical trials
Patients
Machine learning
Data processing
Regression analysis
Probability learning
Effectiveness
Pharmaceutical industry
Pancreatic cancer
Oncology
Information sharing
Privacy
Metastases
Chemotherapy
Federated learning
Drug development
Statistical methods
Social
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:External control arms can inform early clinical development of experimental drugs and provide efficacy evidence for regulatory approval. However, accessing sufficient real-world or historical clinical trials data is challenging. 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 method that leverages federated learning to enable inverse probability of treatment weighting for time-to-event outcomes on separate cohorts without needing to pool data. To showcase its potential, we apply it in different settings of increasing complexity, culminating with a real-world use-case in which our method is used to compare the treatment effect of two approved chemotherapy regimens using data from three separate cohorts of patients with metastatic pancreatic cancer. By sharing our code, we hope it will foster the creation of federated research networks and thus accelerate drug development.External Control Arm methods for clinical trials were developed to compare the efficacy of a treatment to a control group that is built with data from external sources. Here, the authors present FedECA, a privacy-enhancing method for analyzing treatment effects across institutions, streamlining multi-centric trial design and thereby accelerating drug development while minimizing patient data exposure.
ISSN:2041-1723
DOI:10.1038/s41467-025-62525-z
Fuente:Health & Medical Collection