• Corpus ID: 53858584

FADL: Federated-Autonomous Deep Learning for Distributed Electronic Health Record

@article{Liu2018FADLFD,
  title={FADL: Federated-Autonomous Deep Learning for Distributed Electronic Health Record},
  author={Dianbo Liu and Timothy Miller and Raheel Sayeed and Kenneth D. Mandl},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.11400}
}
Electronic health record (EHR) data is collected by individual institutions and often stored across locations in silos. Getting access to these data is difficult and slow due to security, privacy, regulatory, and operational issues. We show, using ICU data from 58 different hospitals, that machine learning models to predict patient mortality can be trained efficiently without moving health data out of their silos using a distributed machine learning strategy. We propose a new method, called… 

Figures and Tables from this paper

Federated Learning for Healthcare: Systematic Review and Architecture Proposal

A systematic literature review on current research about federated learning in the context of EHR data for healthcare applications and discusses a general architecture for FL applied to healthcare data based on the main insights obtained from the literature review.

LoAdaBoost: Loss-Based AdaBoost Federated Machine Learning on medical Data

This work showed that LoAdaBoost federated learning outperformed baseline method and increased communication efficiency at negligible additional cost, and proposed an adaptive boosting method that increases the efficiency of federated machine learning.

Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions

This survey paper highlights the current and future of FL technology in medical applications where data sharing is a significant burden and outlines the general FL’s statistical problems, device challenges, security, privacy concerns, and its potential in the medical domain.

Federated Learning Systems for Healthcare: Perspective and Recent Progress

The primary objective of the chapter is to highlight the adaptability and working of the FL techniques in the healthcare system especially in drug development, clinical diagnosis, digital health monitoring, and various disease predictions and detection system.

Towards the Practical Utility of Federated Learning in the Medical Domain

This work proposes empirical benchmarks of FL methods considering both performance and monetary cost with three real-world datasets: electronic health records, skin cancer images, and electrocardiogram datasets, and proposes Federated learning with Proximal regularization eXcept local Normalization ( FedPxN ), which outperforms all other FL algorithms while consuming only slightly more power than the most power efficient method.

Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges

This paper aims to lay out existing research and list the possibilities of federated learning for healthcare industries and what challenges, methods, and applications a practitioner should be aware of in the topic of Federated learning.

Cloud-Based Federated Learning Implementation Across Medical Centers

This paper explores several federated learning implementations by applying them in both a simulated environment and an actual implementation using electronic health record data from two academic medical centers on a Microsoft Azure Cloud Databricks platform.

Two-stage Federated Phenotyping and Patient Representation Learning

A two-stage federated natural language processing method is developed that enables utilization of clinical notes from different hospitals or clinics without moving the data, and its performance using obesity and comorbities phenotyping as medical task is demonstrated.

A Review of Privacy Preserving Federated Learning for Private IoT Analytics

This work reviews research around an alternative approach to machine learning known as federated learning which seeks to train machine learning models in a distributed fashion on devices in the user's domain, rather than by a centralised entity.

Privacy-preserving Decentralized Learning Framework for Healthcare System

A Blockchain-based Federated Learning architecture with two layers of participation is presented, which improves the global model accuracy and guarantees participant’s privacy and Blockchain's challenges are systematized.

References

SHOWING 1-10 OF 21 REFERENCES

Federated Optimization: Distributed Machine Learning for On-Device Intelligence

We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number

Federated Learning: Strategies for Improving Communication Efficiency

Two ways to reduce the uplink communication costs are proposed: structured updates, where the user directly learns an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, which learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling.

Communication-Efficient Learning of Deep Networks from Decentralized Data

This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.

Internet of Things and Big Data Technologies for Next Generation Healthcare

This comprehensive book focuses on better big-data security for healthcare organizations and offers an in-depth analysis of medical body area networks with the 5th generation of IoT communication technology along with its nanotechnology.

Translating Artificial Intelligence Into Clinical Care.

Findings from a study evaluating the use of deep learning for detection of diabetic retinopathy and macular edema are presented, giving the authors confidence that this algorithm could be of clinical utility.

The eICU Collaborative Research Database, a freely available multi-center database for critical care research

The e ICU Collaborative Research Database is described, a multi-center intensive care unit (ICU) database with high granularity data for over 200,000 admissions to ICUs monitored by eICU Programs across the United States.

Centralized and Distributed Anonymization for High-Dimensional Healthcare Data

The privacy concerns of sharing patient information between the Hong Kong Red Cross Blood Transfusion Service and the public hospitals are studied and a new privacy model called LKC-privacy is proposed to overcome the challenges and two anonymization algorithms are presented to achieve LKC -privacy in both the centralized and the distributed scenarios.

Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review

Electronic health records are an increasingly common data source for clinical risk prediction, presenting both unique analytic opportunities and challenges, and there is room for improvement in designing studies using EHR data.

The Internet of Things for Health Care: A Comprehensive Survey

An intelligent collaborative security model to minimize security risk is proposed; how different innovations such as big data, ambient intelligence, and wearables can be leveraged in a health care context is discussed; and various IoT and eHealth policies and regulations are addressed to determine how they can facilitate economies and societies in terms of sustainable development.

Ten things we have to do to achieve precision medicine

The core concept of this initiative is that by harnessing measurements of multiple modalities—not just clinical and genomic evaluations, but environmental exposures, daily activities, and many others, the authors can develop a much more comprehensive view of the patient's state and its trajectory over time.