FedECA: Federated External Control Arms for Causal Inference with Time-To-Event Data in Distributed Settings
arXiv:2311.16984
Abstract
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.
code available at: https://github.com/owkin/fedeca, fix bug in SMD (v3), rw exp added, fix YODA exp (v4), fix affiliations, more precise ack., fix rw exp by excluding bias data, text polished (v6), updating abs (v7), typo(v8), extra discussion on hyper-param tuning, regularization and global bootstrap(v9), address editorial comments, fix idibgi p-value, update ethics and data availability (v10)
References in corpus (10)
- Applied Federated Learning: Improving Google Keyboard Query Suggestions
- Federated Learning Enables Big Data for Rare Cancer Boundary Detection
- FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
- NeuMiss networks: differentiable programming for supervised learning with missing values
- Federated Survival Forests
- Collaborative causal inference on distributed data
- Federated Adaptive Causal Estimation (FACE) of Target Treatment Effects
- Randomized Quantization is All You Need for Differential Privacy in Federated Learning
- Multiply Robust Federated Estimation of Targeted Average Treatment Effects
- SecureFedYJ: a safe feature Gaussianization protocol for Federated Learning