Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records

03/22/2019
by   Li Huang, et al.
0

Electronic medical records (EMRs) supports the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events. But insofar most algorithms have been centralized, taking little account of the decentralized, non-identically independently distributed (non-IID), and privacy-sensitive characteristics of EMRs that can complicate data collection, sharing and learning. To address this challenge, we introduced a community-based federated machine learning (CBFL) algorithm and evaluated it on non-IID ICU EMRs. Our algorithm clustered the distributed data into clinically meaningful communities that captured similar diagnoses and geological locations, and learnt one model for each community. Throughout the learning process, the data was kept local on hospitals, while locally-computed results were aggregated on a server. Evaluation results show that CBFL outperformed the baseline FL algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area Under the Precision-Recall Curve (PR AUC), and communication cost between hospitals and the server. Furthermore, communities' performance difference could be explained by how dissimilar one community was to others.

READ FULL TEXT
research
07/17/2023

Privacy-preserving patient clustering for personalized federated learning

Federated Learning (FL) is a machine learning framework that enables mul...
research
08/01/2023

Data Collaboration Analysis applied to Compound Datasets and the Introduction of Projection data to Non-IID settings

Given the time and expense associated with bringing a drug to market, nu...
research
07/11/2022

FD-GATDR: A Federated-Decentralized-Learning Graph Attention Network for Doctor Recommendation Using EHR

In the past decade, with the development of big data technology, an incr...
research
02/18/2022

An Integrated Optimization and Machine Learning Models to Predict the Admission Status of Emergency Patients

This work proposes a framework for optimizing machine learning algorithm...
research
06/09/2020

A Machine Learning Early Warning System: Multicenter Validation in Brazilian Hospitals

Early recognition of clinical deterioration is one of the main steps for...
research
12/25/2019

Federated machine learning with Anonymous Random Hybridization (FeARH) on medical records

Sometimes electrical medical records are restricted and difficult to cen...
research
04/11/2017

Federated Tensor Factorization for Computational Phenotyping

Tensor factorization models offer an effective approach to convert massi...

Please sign up or login with your details

Forgot password? Click here to reset