Learning competing risks across multiple hospitals: one-shot distributed algorithms.

Zhang, D; Tong, J; Jing, N; Yang, Y; Luo, C; Lu, Y; Christakis, DA; Güthe, D; Hornig, M; Kelleher, KJ; Morse, KE; Rogerson, CM; Divers, J; Carroll, RJ; Forrest, CB; Chen, Y

Learning competing risks across multiple hospitals: one-shot distributed algorithms.

Zhang, D Tong, J Jing, N Yang, Y Luo, C Lu, Y Christakis, DA Güthe, D Hornig, M Kelleher, KJ Morse, KE Rogerson, CM Divers, J Carroll, RJ Forrest, CB Chen, Y

Permalink

Publisher:: OXFORD UNIV PRESS
Publication Type:: Journal Article
Citation:: J Am Med Inform Assoc, 2024, 31, (5), pp. 1102-1112
Issue Date:: 2024-04-19

Closed Access

	Filename	Description	Size
	ocae027.pdf	Published version	1.95 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, D
dc.contributor.author	Tong, J
dc.contributor.author	Jing, N
dc.contributor.author	Yang, Y
dc.contributor.author	Luo, C
dc.contributor.author	Lu, Y
dc.contributor.author	Christakis, DA
dc.contributor.author	Güthe, D
dc.contributor.author	Hornig, M
dc.contributor.author	Kelleher, KJ
dc.contributor.author	Morse, KE
dc.contributor.author	Rogerson, CM
dc.contributor.author	Divers, J
dc.contributor.author	Carroll, RJ
dc.contributor.author	Forrest, CB
dc.contributor.author	Chen, Y
dc.date.accessioned	2024-11-07T03:31:25Z
dc.date.available	2024-02-03
dc.date.available	2024-11-07T03:31:25Z
dc.date.issued	2024-04-19
dc.identifier.citation	J Am Med Inform Assoc, 2024, 31, (5), pp. 1102-1112
dc.identifier.issn	1067-5027
dc.identifier.issn	1527-974X
dc.identifier.uri	http://hdl.handle.net/10453/181797
dc.description.abstract	OBJECTIVES: To characterize the complex interplay between multiple clinical conditions in a time-to-event analysis framework using data from multiple hospitals, we developed two novel one-shot distributed algorithms for competing risk models (ODACoR). By applying our algorithms to the EHR data from eight national children's hospitals, we quantified the impacts of a wide range of risk factors on the risk of post-acute sequelae of SARS-COV-2 (PASC) among children and adolescents. MATERIALS AND METHODS: Our ODACoR algorithms are effectively executed due to their devised simplicity and communication efficiency. We evaluated our algorithms via extensive simulation studies as applications to quantification of the impacts of risk factors for PASC among children and adolescents using data from eight children's hospitals including the Children's Hospital of Philadelphia, Cincinnati Children's Hospital Medical Center, Children's Hospital of Colorado covering over 6.5 million pediatric patients. The accuracy of the estimation was assessed by comparing the results from our ODACoR algorithms with the estimators derived from the meta-analysis and the pooled data. RESULTS: The meta-analysis estimator showed a high relative bias (∼40%) when the clinical condition is relatively rare (∼0.5%), whereas ODACoR algorithms exhibited a substantially lower relative bias (∼0.2%). The estimated effects from our ODACoR algorithms were identical on par with the estimates from the pooled data, suggesting the high reliability of our federated learning algorithms. In contrast, the meta-analysis estimate failed to identify risk factors such as age, gender, chronic conditions history, and obesity, compared to the pooled data. DISCUSSION: Our proposed ODACoR algorithms are communication-efficient, highly accurate, and suitable to characterize the complex interplay between multiple clinical conditions. CONCLUSION: Our study demonstrates that our ODACoR algorithms are communication-efficient and can be widely applicable for analyzing multiple clinical conditions in a time-to-event analysis framework.
dc.format	Print
dc.language	eng
dc.publisher	OXFORD UNIV PRESS
dc.relation.ispartof	J Am Med Inform Assoc
dc.relation.isbasedon	10.1093/jamia/ocae027
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 11 Medical and Health Sciences
dc.subject.classification	Medical Informatics
dc.subject.classification	32 Biomedical and clinical sciences
dc.subject.classification	42 Health sciences
dc.subject.classification	46 Information and computing sciences
dc.subject.mesh	Adolescent
dc.subject.mesh	Child
dc.subject.mesh	Humans
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	Algorithms
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Hospitals
dc.subject.mesh	Risk Factors
dc.subject.mesh	Humans
dc.subject.mesh	Risk Factors
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	Algorithms
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Adolescent
dc.subject.mesh	Child
dc.subject.mesh	Hospitals
dc.subject.mesh	Adolescent
dc.subject.mesh	Child
dc.subject.mesh	Humans
dc.subject.mesh	Reproducibility of Results
dc.subject.mesh	Algorithms
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Hospitals
dc.subject.mesh	Risk Factors
dc.title	Learning competing risks across multiple hospitals: one-shot distributed algorithms.
dc.type	Journal Article
utslib.citation.volume	31
utslib.location.activity	England
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	11 Medical and Health Sciences
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Science
pubs.organisational-group	University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	closed_access	*
dc.date.updated	2024-11-07T03:31:23Z
pubs.issue	5
pubs.publication-status	Published
pubs.volume	31
utslib.citation.issue	5

Abstract:

OBJECTIVES: To characterize the complex interplay between multiple clinical conditions in a time-to-event analysis framework using data from multiple hospitals, we developed two novel one-shot distributed algorithms for competing risk models (ODACoR). By applying our algorithms to the EHR data from eight national children's hospitals, we quantified the impacts of a wide range of risk factors on the risk of post-acute sequelae of SARS-COV-2 (PASC) among children and adolescents. MATERIALS AND METHODS: Our ODACoR algorithms are effectively executed due to their devised simplicity and communication efficiency. We evaluated our algorithms via extensive simulation studies as applications to quantification of the impacts of risk factors for PASC among children and adolescents using data from eight children's hospitals including the Children's Hospital of Philadelphia, Cincinnati Children's Hospital Medical Center, Children's Hospital of Colorado covering over 6.5 million pediatric patients. The accuracy of the estimation was assessed by comparing the results from our ODACoR algorithms with the estimators derived from the meta-analysis and the pooled data. RESULTS: The meta-analysis estimator showed a high relative bias (∼40%) when the clinical condition is relatively rare (∼0.5%), whereas ODACoR algorithms exhibited a substantially lower relative bias (∼0.2%). The estimated effects from our ODACoR algorithms were identical on par with the estimates from the pooled data, suggesting the high reliability of our federated learning algorithms. In contrast, the meta-analysis estimate failed to identify risk factors such as age, gender, chronic conditions history, and obesity, compared to the pooled data. DISCUSSION: Our proposed ODACoR algorithms are communication-efficient, highly accurate, and suitable to characterize the complex interplay between multiple clinical conditions. CONCLUSION: Our study demonstrates that our ODACoR algorithms are communication-efficient and can be widely applicable for analyzing multiple clinical conditions in a time-to-event analysis framework.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/181797