A Federated Network for Translational Cancer Research Using Clinical Data and Biospecimens | [52] | 2015 | Learning Systems | This report describes a fully functional federated data and biospecimen sharing network for cross-institutional cancer research collaboration |
Privacy-preserving GWAS analysis on federated genomic datasets | [27] | 2015 | Framework | On federated genomic datasets, this research proposes a privacy-preserving GWAS methodology |
Privacy-Preserving Integration of Medical Data | [78] | 2017 | Protocol | This work presents a safe and privacy-preserving method for searching and integrating health care data from diverse sources |
LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data | [50] | 2018 | Learning Systems | LoAdaBoost, a methodology for increasing the efficiency of federated machine learning, was suggested in this research, and the algorithm was evaluated using data from intensive care units in hospitals |
Federated learning of predictive models from federated electronic health records | [13] | 2018 | Framework | A novel FL framework is presented that can train predictive models through peer-to-peer cooperation instead of exchanging raw EHR data |
FADL: Federated-Autonomous Deep Learning for Distributed Electronic Health Record | [70] | 2018 | Learning Systems | By presenting a novel approach called Federated-Autonomous Deep Learning, this study illustrates the efficacy of FL by using ICU data from 58 different hospitals to predict patient mortality can be trained quickly without transferring health data out of their silos under FL environment (FADL) |
Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records | [49] | 2019 | FL inBiomedical | The community-based federated machine learning (CBFL) technique is described in this research, and it is tested on non-IID ICU EMRs |
FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare | [20] | 2019 | FL in Healthcare IoT | To address data privacy concerns, this paper proposes a federated transfer learning system for wearable healthcare |
Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation | [20] | 2019 | Learning Systems | This paper presents a synchronous learning strategy for FL clients |
Federated deep learning for detecting COVID-19 lung abnormalities in CT: A privacy-preserving multinational validation study | [32] | 2019 | Diagnosis | With external validation on patients from a global cohort, this report reveals the efficiency of an FL system for identifying COVID-19 associated CT anomalies |
Federated Learning for Healthcare Informatics | [119] | 2019 | Survey | This survey study provides an overview of federated learning systems, focusing on biomedical applications |
Federated electronic health records research technology to support clinical trial protocol optimization: Evidence from EHR4CR and the InSite platform | [25] | 2019 | FL in EHR data | This paper determines if inclusion/exclusion (I/E) criteria of clinical trial protocols can be represented as structured queries along with those executed using a secure federated research platform (InSite) on hospital electronic health records (EHR) |
Predicting Adverse Drug Reactions on Distributed Health Data using Federated Learning | [24] | 2019 | Framework | To increase the global model’s predictive power, this research proposes two unique approaches to local model aggregation |
Privacy-preserving Federated Brain Tumour Segmentation | [68] | 2019 | FL in Biomedical | Adopting the BraTS dataset for brain tumor segmentation, this research investigates the possibility of using differential-privacy approaches to secure patient data in a federated learning context |
Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results | [69] | 2020 | Medical Image Analysis | This work proposes a privacy-preserving multi-site fMRI classification that ensures that private information cannot be retrieved from model gradients or weights |
Stochastic Channel-Based Federated Learning With Neural Network Pruning for Medical Data Privacy Preservation: Model Development and Experimental Validation | [99] | 2020 | Learning Systems | For the study of distributed medical data, this research proposes a privacy-preserving approach called stochastic channel-based federated learning (SCBFL) |
Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data | [100] | 2020 | Medicine | This research shows that utilizing data from ten universities, the models achieve 99 percent model quality and discuss the impact of data distribution across participating institutions |
FedHome: Cloud-Edge based Personalized Federated Learning for In-Home Health Monitoring | [115] | 2020 | FL in Healthcare IoT | FedHome, a cloud-edge-based federated learning architecture for in-home health monitoring, is proposed in this research |
The future of digital health with federated learning | [93] | 2020 | Survey | This survey report looks at how FL could help with the future of digital health, as well as the obstacles |
Federated Learning on Clinical Benchmark Data: Performance Assessment | [63] | 2020 | Benchmark | The research uses three benchmark datasets, including a clinical benchmark dataset, to assess the reliability and performance of FL |
FedMed: A Federated Learning Framework for Language Modeling | [116] | 2020 | Framework | To address model aggregation and communication costs in the FL environment, this study provides a unique Federated Mediation (FedMed) framework with adaptive aggregation, mediation incentive scheme, and topK method |
Federated Learning for Breast Density Classification: A Real-World Implementation | [94] | 2020 | Medical Image Analysis | This article demonstrates the efficacy of FL by training a model for breast density categorization based on Breast Imaging, Reporting, and Data systems utilizing data from seven clinical institutions across the world (BI-RADS) |
Federated Transfer Learning for EEG Signal Classification | [56] | 2020 | Learning Systems | This work proposes a unique privacy-preserving DL architecture called federated transfer learning that uses the FL in EEG classification (FTL) |
COVID-19 detection using federated machine learning | [96] | 2021 | Diagnosis | To determine which parameters impact model prediction accuracy and loss, this study employed a descriptive dataset and chest x-ray (CXR) images from COVID-19 patients in an FL context |
Implementing Vertical Federated Learning Using Autoencoders: Practical Application, Generalizability, and Utility Study | [16] | 2021 | Learning Systems | Without revealing the raw data, this research shows that FL on vertically partitioned data may perform equivalent to centralized models |
Federated Learning Meets Human Emotions: A Decentralized Framework for Human–Computer Interaction for IoT Applications | [23] | 2021 | FL in Biomedical | This article combines facial expression and voice inputs to construct an emotion monitoring ** analysis system using FL |
FeARH: Federated machine learning with anonymous random hybridization on electronic medical records | [28] | 2021 | Learning Systems | This research study suggests a novel FL method to deal with untrustworthy conditions |
Federated Learning for Thyroid Ultrasound Image Analysis to Protect Personal Information: Validation Study in a Real Health Care Environment | [64] | 2021 | Diagnosis | The purpose of this research is to see if FL’s performance is equivalent to that of traditional deep learning |
Learning From Others Without Sacrificing Privacy: Simulation Comparing Centralized and Federated Machine Learning on Mobile Health Data | [71] | 2021 | FL in Healthcare IoT | The research explores FL use cases in a mHealth environment and uses an mHealth data set to simulate federated learning |
Cloud-Based Federated Learning Implementation Across Medical Centers | [92] | 2021 | FL in EHR data | This research mimics an FL environment in order to investigate multiple federated learning implementations and apply FL algorithms to data from two academic medical facilities’ electronic health records |
Federated learning improves site performance in multicenter deep learning without data sharing | [97] | 2021 | FL in EHR data | This study demonstrates how to provide multi-institutional training in an FL environment without centralization |
A Resource-Constrained and Privacy-Preserving Edge-Computing-Enabled Clinical Decision System: A Federated Reinforcement Learning Approach | [121] | 2021 | FL in EHR data | This article combines mobile-edge computing (MEC) with software-defined networking to make use of the processing and storage capabilities available among edge nodes (ENs) (i.e., MEC servers) in the FL environment |
Variation-Aware Federated Learning with Multi-Source Decentralized Medical Image Data | [122] | 2021 | Learning Systems | Variation-aware federated learning (VAFL) is a methodology proposed in this research for minimising client variations by transforming all clients’ images into a shared image space |
Federated Learning in a Medical Context: A Systematic Literature Review | [87] | 2021 | Survey | This survey article examines federated learning and its relevance to sensitive healthcare data |
Federated Learning for Smart Healthcare: A Survey | [80] | 2021 | Survey | The application of FL in smart healthcare and IoT devices are reviewed and surveyed in this survey report |