Summary of Privacy-preserving Federated Prediction Of Pain Intensity Change Based on Multi-center Survey Data, by Supratim Das et al.
Privacy-preserving federated prediction of pain intensity change based on multi-center survey data
by Supratim Das, Mahdie Rafie, Paula Kammer, Søren T. Skou, Dorte T. Grønne, Ewa M. Roos, André Hajek, Hans-Helmut König, Md Shihab Ullaha, Niklas Probul, Jan Baumbacha, Linda Baumbach
First submitted to arxiv on: 12 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 In this study, researchers aimed to develop privacy-preserving federated machine learning techniques for building prognostic models using patient-reported survey data. They used centralized, local, and federated learning methods on two healthcare datasets from Denmark (GLA:D) and 27 countries (SHARE). The goal was to predict health outcomes without compromising patient privacy by allowing data to remain within the legally safe harbors of medical centers. The team compared linear regression, random forest regression, and random forest classification models trained locally versus centrally or federatedly. Results showed that federated learning outperformed local approaches in GLA:D data, with statistical significance. In SHARE, both federated and centralized models performed better than local ones. Overall, the study demonstrates the potential of federated learning to train accurate prognostic models while respecting patient privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study is about using computer algorithms to help predict health outcomes from patient surveys without sharing personal data. Researchers developed a way to combine survey answers from different places into one model without keeping all the data in one place. They compared three ways of training these models: doing it locally, centrally, or by combining data from multiple centers while keeping it private. The results show that combining data this way can be just as accurate as having all the data in one place, and it respects patients’ privacy. |
Keywords
» Artificial intelligence » Classification » Federated learning » Linear regression » Machine learning » Random forest » Regression
