Federated Learning for the Internet-of-Medical-Things: A Survey

被引:12
作者
Prasad, Vivek Kumar [1 ]
Bhattacharya, Pronaya [1 ]
Maru, Darshil [1 ]
Tanwar, Sudeep [1 ]
Verma, Ashwin [1 ]
Singh, Arunendra [2 ]
Tiwari, Amod Kumar [3 ]
Sharma, Ravi [4 ]
Alkhayyat, Ahmed [5 ,6 ]
Turcanu, Florin-Emilian [7 ]
Raboaca, Maria Simona [8 ,9 ,10 ]
机构
[1] Nirma Univ, Inst Technol, Dept Comp Sci & Engn, Ahmadabad 382481, Gujarat, India
[2] Pranveer Singh Inst Technol, Dept Informat Technol, Kanpur 209305, Uttar Pradesh, India
[3] Rajikiya Engn Coll, Dept Comp Sci & Engn, Sonbhadra 231206, Uttar Pradesh, India
[4] Univ Petr & Energy Studies, Ctr Interdisciplinary Res & Innovat, Dehra Dun 248001, Uttarakhand, India
[5] Islamic Univ, Coll Tech Engn, Najaf 54001, Iraq
[6] Al Turath Univ Coll, Dept Med Instruments Engn Tech, Baghdad 10021, Iraq
[7] Tech Univ Gheorghe Asachi, Fac Civil Engn & Bldg Serv, Dept Bldg Serv, Iasi 700050, Romania
[8] Natl Res & Dev Inst Cryogen & Isotop Technol ICSI, Ramicu Valcea 240050, Romania
[9] Univ Politehn Bucuresti, Doctoral Sch, Bucharest 060042, Romania
[10] Stefan Cel Mare Univ, Fac Elect Engn & Comp Sci, Suceava 720229, Romania
关键词
federated Learning; healthcare; cloud computing; security; privacy; blockchain; machine learning; HEALTH-CARE-SYSTEMS; PRIVACY PRESERVATION; BLOCKCHAIN; NETWORKS; MACHINE; AI; COMMUNICATION; OPTIMIZATION; INTELLIGENCE; MANAGEMENT;
D O I
10.3390/math11010151
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Recently, in healthcare organizations, real-time data have been collected from connected or implantable sensors, layered protocol stacks, lightweight communication frameworks, and end devices, named the Internet-of-Medical-Things (IoMT) ecosystems. IoMT is vital in driving healthcare analytics (HA) toward extracting meaningful data-driven insights. Recently, concerns have been raised over data sharing over IoMT, and stored electronic health records (EHRs) forms due to privacy regulations. Thus, with less data, the analytics model is deemed inaccurate. Thus, a transformative shift has started in HA from centralized learning paradigms towards distributed or edge-learning paradigms. In distributed learning, federated learning (FL) allows for training on local data without explicit data-sharing requirements. However, FL suffers from a high degree of statistical heterogeneity of learning models, level of data partitions, and fragmentation, which jeopardizes its accuracy during the learning and updating process. Recent surveys of FL in healthcare have yet to discuss the challenges of massive distributed datasets, sparsification, and scalability concerns. Because of this gap, the survey highlights the potential integration of FL in IoMT, the FL aggregation policies, reference architecture, and the use of distributed learning models to support FL in IoMT ecosystems. A case study of a trusted cross-cluster-based FL, named Cross-FL, is presented, highlighting the gradient aggregation policy over remotely connected and networked hospitals. Performance analysis is conducted regarding system latency, model accuracy, and the trust of consensus mechanism. The distributed FL outperforms the centralized FL approaches by a potential margin, which makes it viable for real-IoMT prototypes. As potential outcomes, the proposed survey addresses key solutions and the potential of FL in IoMT to support distributed networked healthcare organizations.
引用
收藏
页数:47
相关论文
共 176 条
  • [81] Kumar Y, 2021, Federated Learning Syst Towards Next-Gener AI, P141
  • [82] Federated-Learning Based Privacy Preservation and Fraud-Enabled Blockchain IoMT System for Healthcare
    Lakhan, Abdullah
    Mohammed, Mazin Abed
    Nedoma, Jan
    Martinek, Radek
    Tiwari, Prayag
    Vidyarthi, Ankit
    Alkhayyat, Ahmed
    Wang, Weiyu
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2023, 27 (02) : 664 - 672
  • [83] Li J., 2015, Switchable and Responsive Surfaces and Materials for Biomedical Applications, P259, DOI DOI 10.1016/B978-0-85709-713-2.00011-0
  • [84] A Prediction-Based Charging Policy and Interference Mitigation Approach in the Wireless Powered Internet of Things
    Li, Lixin
    Xu, Yang
    Zhang, Zihe
    Yin, Jiaying
    Chen, Wei
    Han, Zhu
    [J]. IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (02) : 439 - 451
  • [85] Li Q., 2021, ARXIV
  • [86] Privacy-Preserving Federated Brain Tumour Segmentation
    Li, Wenqi
    Milletari, Fausto
    Xu, Daguang
    Rieke, Nicola
    Hancox, Jonny
    Zhu, Wentao
    Baust, Maximilian
    Cheng, Yan
    Ourselin, Sebastien
    Cardoso, M. Jorge
    Feng, Andrew
    [J]. MACHINE LEARNING IN MEDICAL IMAGING (MLMI 2019), 2019, 11861 : 133 - 141
  • [87] Li X, 2021, ARXIV
  • [88] Liu B, 2020, ARXIV
  • [89] Liu D, 2019, ARXIV
  • [90] Liu DB, 2019, SIGBIOMED WORKSHOP ON BIOMEDICAL NATURAL LANGUAGE PROCESSING (BIONLP 2019), P283, DOI 10.18653/v1/W19-5030