Summary of Developing Federated Time-to-event Scores Using Heterogeneous Real-world Survival Data, by Siqi Li et al.
Developing Federated Time-to-Event Scores Using Heterogeneous Real-World Survival Data
by Siqi Li, Yuqing Shang, Ziwen Wang, Qiming Wu, Chuan Hong, Yilin Ning, Di Miao, Marcus Eng Hock Ong, Bibhas Chakraborty, Nan Liu
First submitted to arxiv on: 8 Mar 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel framework for building federated scoring systems for multi-site survival outcomes, ensuring both privacy and communication efficiency in collaborations with multiple data owners. The framework is applied to emergency department datasets from Singapore and the US, where local scores are developed independently at each site. The proposed federated scoring system outperforms all local models, achieving higher integrated area under the receiver operating characteristic curve (iAUC) values and narrower confidence intervals (CIs) across most time points. This study demonstrates the effectiveness of the framework in enhancing prediction accuracy and efficiency for healthcare research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to make predictions about when certain events will happen, like when someone might get sick or die. This is important for doctors to make good decisions. Right now, we have ways to predict these things, but they only work if all the data comes from one place. What if we want to use data from many different places? That’s a problem! The paper solves this problem by creating a new way to combine data from lots of places without sharing any personal information. They tested it with real data and showed that it works better than just using data from one place. This is important for making good predictions in healthcare. |
