Lightweight federated learning for STIs/HIV prediction
Article
Nguyen, Thi Phuoc Van, Yang, Wencheng, Tang, Zhaohui, Xia, Xiaoyu, Mullens, Amy B., Dean, Judith A. and Li, Yan. 2024. "Lightweight federated learning for STIs/HIV prediction." Scientific Reports. 14 (1). https://doi.org/10.1038/s41598-024-56115-0
Article Title | Lightweight federated learning for STIs/HIV prediction |
---|---|
ERA Journal ID | 201487 |
Article Category | Article |
Authors | Nguyen, Thi Phuoc Van, Yang, Wencheng, Tang, Zhaohui, Xia, Xiaoyu, Mullens, Amy B., Dean, Judith A. and Li, Yan |
Journal Title | Scientific Reports |
Journal Citation | 14 (1) |
Article Number | 6560 |
Number of Pages | 12 |
Year | 2024 |
Publisher | Nature Publishing Group |
ISSN | 2045-2322 |
Digital Object Identifier (DOI) | https://doi.org/10.1038/s41598-024-56115-0 |
Web Address (URL) | https://www.nature.com/articles/s41598-024-56115-0 |
Abstract | This paper presents a solution that prioritises high privacy protection and improves communication throughput for predicting the risk of sexually transmissible infections/human immunodeficiency virus (STIs/HIV). The approach utilised Federated Learning (FL) to construct a model from multiple clinics and key stakeholders. FL ensured that only models were shared between clinics, minimising the risk of personal information leakage. Additionally, an algorithm was explored on the FL manager side to construct a global model that aligns with the communication status of the system. Our proposed method introduced Random Forest Federated Learning for assessing the risk of STIs/HIV, incorporating a flexible aggregation process that can be adjusted to accommodate the capacious communication system. Experimental results demonstrated the significant potential of a solution for estimating STIs/HIV risk. In comparison with recent studies, our approach yielded superior results in terms of AUC (0.97) and accuracy ( |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 461103. Deep learning |
Byline Affiliations | School of Mathematics, Physics and Computing |
Centre for Health Research | |
Royal Melbourne Institute of Technology (RMIT) | |
School of Psychology and Wellbeing | |
Institute for Resilient Regions | |
University of Queensland |
Permalink -
https://research.usq.edu.au/item/z8555/lightweight-federated-learning-for-stis-hiv-prediction
Download files
58
total views16
total downloads15
views this month1
downloads this month