DFML: Dynamic Federated Meta-Learning for Rare Disease Prediction

被引:10
作者
Chen, Bingyang [1 ]
Chen, Tao [1 ]
Zeng, Xingjie [1 ]
Zhang, Weishan [1 ]
Lu, Qinghua [2 ]
Hou, Zhaoxiang [1 ]
Zhou, Jiehan [3 ]
Helal, Sumi [4 ]
机构
[1] China Univ Petr, Sch Comp Sci & Technol, Qingdao 266580, Peoples R China
[2] CSIRO, Sydney, NSW 2601, Australia
[3] Oulu Univ, Oulu 90570, Finland
[4] Univ Florida, Gainesville, FL 32611 USA
基金
中国国家自然科学基金;
关键词
Diseases; Predictive models; Data models; Servers; Hospitals; Task analysis; Federated learning; Inaccuracy-focused meta-learning; dynamic weight-based fusion strategy; federated meta-learning; rare disease prediction; digital health; MODEL; SYSTEM;
D O I
10.1109/TCBB.2023.3239848
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. Hospitals are usually reluctant to share patient information for data fusion due to the sensitivity of medical data. These challenges make it difficult for traditional AI models to extract rare disease features for disease prediction. In this paper, we propose a Dynamic Federated Meta-Learning (DFML) approach to improve rare disease prediction. We design an Inaccuracy-Focused Meta-Learning (IFML) approach that dynamically adjusts the attention to different tasks according to the accuracy of base learners. Additionally, a dynamic weight-based fusion strategy is proposed to further improve federated learning, which dynamically selects clients based on the accuracy of each local model. Experiments on two public datasets show that our approach outperforms the original federated meta-learning algorithm in accuracy and speed with as few as five shots. The average prediction accuracy of the proposed model is improved by 13.28% compared with each hospital's local model.
引用
收藏
页码:880 / 889
页数:10
相关论文
共 37 条
[31]   Dynamic-Fusion-Based Federated Learning for COVID-19 Detection [J].
Zhang, Weishan ;
Zhou, Tao ;
Lu, Qinghua ;
Wang, Xiao ;
Zhu, Chunsheng ;
Sun, Haoyun ;
Wang, Zhipeng ;
Lo, Sin Kit ;
Wang, Fei-Yue .
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (21) :15884-15891
[32]   MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records [J].
Zhang, Xi Sheryl ;
Tang, Fengyi ;
Dodge, Hiroko H. ;
Zhou, Jiayu ;
Wang, Fei .
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, :2487-2495
[33]  
Zheng WB, 2020, PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P4654
[34]   2D Federated Learning for Personalized Human Activity Recognition in Cyber-Physical-Social Systems [J].
Zhou, Xiaokang ;
Liang, Wei ;
Ma, Jianhua ;
Yan, Zheng ;
Wang, Kevin I-Kai .
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2022, 9 (06) :3934-3944
[35]   Two-Layer Federated Learning With Heterogeneous Model Aggregation for 6G Supported Internet of Vehicles [J].
Zhou, Xiaokang ;
Liang, Wei ;
She, Jinhua ;
Yan, Zheng ;
Wang, Kevin .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2021, 70 (06) :5308-5317
[36]   CNN-RNN Based Intelligent Recommendation for Online Medical Pre-Diagnosis Support [J].
Zhou, Xiaokang ;
Li, Yue ;
Liang, Wei .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2021, 18 (03) :912-921
[37]   Multi-Modality Behavioral Influence Analysis for Personalized Recommendations in Health Social Media Environment [J].
Zhou, Xiaokang ;
Liang, Wei ;
Wang, Kevin I-Kai ;
Shimizu, Shohei .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2019, 6 (05) :888-897