Summary of Humekafl: Automated Detection Of Neonatal Asphyxia Using Federated Learning, by Pamely Zantou et al.
HumekaFL: Automated Detection of Neonatal Asphyxia Using Federated Learning
by Pamely Zantou, Blessed Guda, Bereket Retta, Gladys Inabeza, Carlee Joe-Wong, Assane Gueye
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Audio and Speech Processing (eess.AS)
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 addresses the challenge of detecting Birth Apshyxia, a severe condition causing insufficient oxygen supply to newborns during delivery, in African healthcare settings where delays in diagnosis can be detrimental. The authors highlight that centralized machine learning methods are effective but require sensitive health data and may not prioritize privacy and security. To overcome this, they propose a federated learning-based software architecture that prioritizes privacy and security by design. Their developed mobile application embeds the federated pipeline for early detection of Birth Apshyxia, which outperformed centralized SVM pipelines and Neural Networks-based methods in existing literature. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding a way to detect a serious condition that happens when newborn babies don’t get enough oxygen during birth. This is a big problem in Africa where many babies die before they are five years old. The usual method for detecting this condition is not very good because doctors can make mistakes or take too long to diagnose it, which means the baby might not get the help they need on time. Some computer programs that try to solve this problem require sensitive information and don’t keep it private, so hospitals in Africa are hesitant to use them. The authors suggest a new way of using computers to detect this condition that prioritizes keeping the information private and secure. They created an app that uses this method and found that it worked better than other methods. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
