Real-time prediction of mortality, readmission, and length of stay using electronic health record data

Xiongcai Cai, Oscar Perez-Concha, Enrico Coiera, Fernando Martin-Sanchez, Richard Day, David Roffe, Blanca Gallego

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective To develop a predictive model for real-time predictions of length of stay, mortality, and readmission for hospitalized patients using electronic health records (EHRs). Materials and Methods A Bayesian Network model was built to estimate the probability of a hospitalized patient being "at home," in the hospital, or dead for each of the next 7 days. The network utilizes patient-specific administrative and laboratory data and is updated each time a new pathology test result becomes available. Electronic health records from 32 634 patients admitted to a Sydney metropolitan hospital via the emergency department from July 2008 through December 2011 were used. The model was tested on 2011 data and trained on the data of earlier years. Results The model achieved an average daily accuracy of 80% and area under the receiving operating characteristic curve (AUROC) of 0.82. The model's predictive ability was highest within 24 hours from prediction (AUROC=0.83) and decreased slightly with time. Death was the most predictable outcome with a daily average accuracy of 93% and AUROC of 0.84. Discussion We developed the first non-disease-specific model that simultaneously predicts remaining days of hospitalization, death, and readmission as part of the same outcome. By providing a future daily probability for each outcome class, we enable the visualization of future patient trajectories. Among these, it is possible to identify trajectories indicating expected discharge, expected continuing hospitalization, expected death, and possible readmission. Conclusions Bayesian Networks can model EHRs to provide real-time forecasts for patient outcomes, which provide richer information than traditional independent point predictions of length of stay, death, or readmission, and can thus better support decision making.

LanguageEnglish
Pages553-561
Number of pages9
JournalJournal of the American Medical Informatics Association
Volume23
Issue number3
DOIs
Publication statusPublished - 2016

Fingerprint

Electronic Health Records
Length of Stay
Mortality
Hospitalization
Patient Readmission
Aptitude
Bayes Theorem
Urban Hospitals
Hospital Emergency Service
Decision Making
Pathology

Cite this

@article{9244bea386d24b4aa8cb15beaf07d322,
title = "Real-time prediction of mortality, readmission, and length of stay using electronic health record data",
abstract = "Objective To develop a predictive model for real-time predictions of length of stay, mortality, and readmission for hospitalized patients using electronic health records (EHRs). Materials and Methods A Bayesian Network model was built to estimate the probability of a hospitalized patient being {"}at home,{"} in the hospital, or dead for each of the next 7 days. The network utilizes patient-specific administrative and laboratory data and is updated each time a new pathology test result becomes available. Electronic health records from 32 634 patients admitted to a Sydney metropolitan hospital via the emergency department from July 2008 through December 2011 were used. The model was tested on 2011 data and trained on the data of earlier years. Results The model achieved an average daily accuracy of 80{\%} and area under the receiving operating characteristic curve (AUROC) of 0.82. The model's predictive ability was highest within 24 hours from prediction (AUROC=0.83) and decreased slightly with time. Death was the most predictable outcome with a daily average accuracy of 93{\%} and AUROC of 0.84. Discussion We developed the first non-disease-specific model that simultaneously predicts remaining days of hospitalization, death, and readmission as part of the same outcome. By providing a future daily probability for each outcome class, we enable the visualization of future patient trajectories. Among these, it is possible to identify trajectories indicating expected discharge, expected continuing hospitalization, expected death, and possible readmission. Conclusions Bayesian Networks can model EHRs to provide real-time forecasts for patient outcomes, which provide richer information than traditional independent point predictions of length of stay, death, or readmission, and can thus better support decision making.",
author = "Xiongcai Cai and Oscar Perez-Concha and Enrico Coiera and Fernando Martin-Sanchez and Richard Day and David Roffe and Blanca Gallego",
year = "2016",
doi = "10.1093/jamia/ocv110",
language = "English",
volume = "23",
pages = "553--561",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "3",

}

Real-time prediction of mortality, readmission, and length of stay using electronic health record data. / Cai, Xiongcai; Perez-Concha, Oscar; Coiera, Enrico; Martin-Sanchez, Fernando; Day, Richard; Roffe, David; Gallego, Blanca.

In: Journal of the American Medical Informatics Association, Vol. 23, No. 3, 2016, p. 553-561.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Real-time prediction of mortality, readmission, and length of stay using electronic health record data

AU - Cai, Xiongcai

AU - Perez-Concha, Oscar

AU - Coiera, Enrico

AU - Martin-Sanchez, Fernando

AU - Day, Richard

AU - Roffe, David

AU - Gallego, Blanca

PY - 2016

Y1 - 2016

N2 - Objective To develop a predictive model for real-time predictions of length of stay, mortality, and readmission for hospitalized patients using electronic health records (EHRs). Materials and Methods A Bayesian Network model was built to estimate the probability of a hospitalized patient being "at home," in the hospital, or dead for each of the next 7 days. The network utilizes patient-specific administrative and laboratory data and is updated each time a new pathology test result becomes available. Electronic health records from 32 634 patients admitted to a Sydney metropolitan hospital via the emergency department from July 2008 through December 2011 were used. The model was tested on 2011 data and trained on the data of earlier years. Results The model achieved an average daily accuracy of 80% and area under the receiving operating characteristic curve (AUROC) of 0.82. The model's predictive ability was highest within 24 hours from prediction (AUROC=0.83) and decreased slightly with time. Death was the most predictable outcome with a daily average accuracy of 93% and AUROC of 0.84. Discussion We developed the first non-disease-specific model that simultaneously predicts remaining days of hospitalization, death, and readmission as part of the same outcome. By providing a future daily probability for each outcome class, we enable the visualization of future patient trajectories. Among these, it is possible to identify trajectories indicating expected discharge, expected continuing hospitalization, expected death, and possible readmission. Conclusions Bayesian Networks can model EHRs to provide real-time forecasts for patient outcomes, which provide richer information than traditional independent point predictions of length of stay, death, or readmission, and can thus better support decision making.

AB - Objective To develop a predictive model for real-time predictions of length of stay, mortality, and readmission for hospitalized patients using electronic health records (EHRs). Materials and Methods A Bayesian Network model was built to estimate the probability of a hospitalized patient being "at home," in the hospital, or dead for each of the next 7 days. The network utilizes patient-specific administrative and laboratory data and is updated each time a new pathology test result becomes available. Electronic health records from 32 634 patients admitted to a Sydney metropolitan hospital via the emergency department from July 2008 through December 2011 were used. The model was tested on 2011 data and trained on the data of earlier years. Results The model achieved an average daily accuracy of 80% and area under the receiving operating characteristic curve (AUROC) of 0.82. The model's predictive ability was highest within 24 hours from prediction (AUROC=0.83) and decreased slightly with time. Death was the most predictable outcome with a daily average accuracy of 93% and AUROC of 0.84. Discussion We developed the first non-disease-specific model that simultaneously predicts remaining days of hospitalization, death, and readmission as part of the same outcome. By providing a future daily probability for each outcome class, we enable the visualization of future patient trajectories. Among these, it is possible to identify trajectories indicating expected discharge, expected continuing hospitalization, expected death, and possible readmission. Conclusions Bayesian Networks can model EHRs to provide real-time forecasts for patient outcomes, which provide richer information than traditional independent point predictions of length of stay, death, or readmission, and can thus better support decision making.

UR - http://www.scopus.com/inward/record.url?scp=84979055388&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/nhmrc/568612

U2 - 10.1093/jamia/ocv110

DO - 10.1093/jamia/ocv110

M3 - Article

VL - 23

SP - 553

EP - 561

JO - Journal of the American Medical Informatics Association : JAMIA

T2 - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 3

ER -