A new paper evaluates federated learning for survival analysis in healthcare, specifically on breast cancer data across multiple institutions. The study compared three survival models (Cox Proportional Hazards, DeepSurv, and Random Survival Forest) using federated optimization strategies like FedAvg, FedProx, and FedAdam. Results indicate that federated learning approaches or even surpasses centralized performance while preserving patient privacy. The Random Survival Forest model demonstrated the best balance of accuracy and robustness, with performance influenced by client data diversity. AI
IMPACT Federated learning offers a privacy-preserving approach for developing robust survival models in healthcare, potentially accelerating clinical decision-making.
RANK_REASON The cluster contains a research paper detailing a multi-model evaluation of federated learning for survival analysis in healthcare.
- breast cancer
- Cox proportional hazards model
- DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network
- FedAdam
- FedAvg
- Federated Survival Analysis
- FedProx
- health care
- Miguel Fernandez-De-Retana
- random survival forest
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
