Summary of Federated Learning Model For Predicting Major Postoperative Complications, by Yonggi Park et al.
Federated learning model for predicting major postoperative complications
by Yonggi Park, Yuanfang Ren, Benjamin Shickel, Ziyuan Guan, Ayush Patela, Yingbo Ma, Zhenhong Hu, Tyler J. Loftus, Parisa Rashidi, Tezcan Ozrazgat-Baslanti, Azra Bihorac
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
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 This paper presents a study on developing artificial intelligence (AI) models to predict the risk of postoperative complications using Electronic Health Records (EHRs). The authors collected data from two hospitals, UFH Gainesville and Jacksonville, and trained three types of AI models: federated learning, local learning, and central learning. The results show that federated learning models achieved comparable performance to central learning models and outperformed local learning models in predicting postoperative complications. The study demonstrates the potential of federated learning in training robust AI models from large-scale data across multiple institutions while protecting patient privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how artificial intelligence can be used to predict whether patients will develop serious complications after surgery. Researchers collected medical records from two hospitals and tested different ways of teaching computers to make predictions. They found that a special method called federated learning worked well, even when they only had data from one or the other hospital. This means that doctors could use AI to help predict which patients are at risk without having to share their patient data with anyone else. |
Keywords
* Artificial intelligence * Federated learning
