Distributed learning for heterogeneous clinical data with application to integrating COVID-19 data across 230 sites

Tong, Jiayi; Luo, Chongliang; Islam, Md. Nazmul; Sheils, Natalie E.; Buresh, John; Edmondson, Mackenzie; Merkel, Peter A.; Lautenbach, Ebbing; Duan, Rui; Chen, Yong

doi:10.1038/s41746-022-00615-8

Cited by 13 publications

(3 citation statements)

References 46 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 20) OMOP CDM can be a solution for standardizing the feature extraction process while assuring feature quality. 21) ATLAS can improve code production, and a pre-established OMOP CDM network, such as FeederNet, can solve the problem of network connection, which is another major problem of FL. 20) …”

Section: Patient-level Predictionmentioning

confidence: 99%

Establishment of an International Evidence Sharing Network Through Common Data Model for Cardiovascular Research

et al. 2022

View full text Add to dashboard Cite

Author's summary A distributed research network refers to a research network wherein multiple institutions unite for joint research based on common data model wherein the structure and meaning of the data are standardized. Researchers can only send the analysis code to multiple institutions and get the summarized analysis results. Thus, researchers cannot see any of the individual patient data at any time, and no individual patient data can be leaked from the institutions. The Observational Health Data Sciences and Informatics research network standardized 928 million unique records or 12% of the world’s population from 41 countries.

show abstract

Section: Patient-level Predictionmentioning

confidence: 99%

Establishment of an International Evidence Sharing Network Through Common Data Model for Cardiovascular Research

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Further work in semi- and weakly-supervised deep learning methods is necessary. [143,144] Moreover, given the privacy constraints associated with EHRs and other health data sources, leveraging interoperable and multimodal data calls for advancements in federated learning methods that can accommodate distributed data sources stored locally across institutions [145]…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review

Yang

Varghese²,

Stephenson

et al. 2022

Preprint

View full text Add to dashboard Cite

ObjectiveAccurate and rapid methods for phenotyping are a prerequisite to realizing the potential of electronic health records (EHRs) data for clinical and translational research. This study reviews the literature on machine learning (ML) approaches for phenotyping with respect to the phenotypes considered, the data sources and methods used, and the contributions within the wider context of EHR-based research.Materials and MethodsWe searched for relevant articles in PubMed and Web of Science published between January 1, 2018 and April 14, 2022. After screening, we collected data on 52 variables across 106 selected articles.ResultsML-based methods were developed for 156 unique phenotypes, primarily using EHR data from a single institution or health system. 72 of 106 articles leveraged unstructured data in clinical notes. In terms of methodology, supervised learning is the most prevalent ML paradigm (n = 64, 60.4%), with half of the articles employing deep learning. Semi-supervised and weakly-supervised approaches were applied to reduce the burden of obtaining gold-standard labeled data (n = 21, 19.8%), while unsupervised learning was used for phenotype discovery (n = 20, 18.9%). Federated learning has been applied to develop algorithms across multiple institutions while preserving data privacy (n = 2, 1.9%).DiscussionWhile the use of ML for phenotyping is growing, most articles applied traditional supervised ML to characterize the presence of common, chronic conditions.ConclusionContinued research in ML-based methods is warranted, with particular attention to the development of advanced methods for complex phenotypes and standards for reporting and evaluating phenotyping algorithms.

show abstract

“…Fortunately, multiple rs-fMRI datasets from different sites provide the possibility for enhancing the quality of learned BNs. However, multi-site data are often subject to inter-site heterogeneity and data-sharing policies [Li et al, 2020, Tong et al, 2022. How to learn more helpful heterogeneous information from multi-site data with considering data-sharing policies is still one of the research hotspots of BN learning.…”

Section: Introductionmentioning

confidence: 99%

Learning Personalized Brain Functional Connectivity of MDD Patients from Multiple Sites via Federated Bayesian Networks

Liu¹,

X²,

Qi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Identifying functional connectivity biomarkers of major depressive disorder (MDD) patients is essential to advance understanding of the disorder mechanisms and early intervention. However, due to the small sample size and the high dimension of available neuroimaging data, the performance of existing methods is often limited. Multi-site data could enhance the statistical power and sample size, while they are often subject to inter-site heterogeneity and data-sharing policies. In this paper, we propose a federated joint estimator, NOTEARS-PFL, for simultaneous learning of multiple Bayesian networks (BNs) with continuous optimization, to identify diseaseinduced alterations in MDD patients. We incorporate information shared between sites and site-specific information into the proposed federated learning framework to learn personalized BN structures by introducing the group fused lasso penalty. We develop the alternating direction method of multipliers, where in the local update step, the neuroimaging data is processed at each local site. Then the learned network structures are transmitted to the center for the global update. In particular, we derive a closed-form expression for the local update step and use the iterative proximal projection method to deal with the group fused lasso penalty in the global update step. We evaluate the performance of the proposed method on both synthetic and real-world multi-site rs-fMRI datasets. The results suggest that the proposed NOTEARS-PFL yields superior effectiveness and accuracy than the comparable methods.

show abstract

Distributed learning for heterogeneous clinical data with application to integrating COVID-19 data across 230 sites

Cited by 13 publications

References 46 publications

Establishment of an International Evidence Sharing Network Through Common Data Model for Cardiovascular Research

Establishment of an International Evidence Sharing Network Through Common Data Model for Cardiovascular Research

Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review

Learning Personalized Brain Functional Connectivity of MDD Patients from Multiple Sites via Federated Bayesian Networks

Contact Info

Product

Resources

About