Predicting 7-day, 30-day and 60-day all-cause unplanned readmission: a case study of a Sydney hospital

Yashar Maali, Oscar Perez-Concha, Enrico Coiera, David Roffe, Richard O. Day, Blanca Gallego

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: The identification of patients at high risk of unplanned readmission is an important component of discharge planning strategies aimed at preventing unwanted returns to hospital. The aim of this study was to investigate the factors associated with unplanned readmission in a Sydney hospital. We developed and compared validated readmission risk scores using routinely collected hospital data to predict 7-day, 30-day and 60-day all-cause unplanned readmission. 

Methods: A combination of gradient boosted tree algorithms for variable selection and logistic regression models was used to build and validate readmission risk scores using medical records from 62,235 live discharges from a metropolitan hospital in Sydney, Australia. 

Results: The scores had good calibration and fair discriminative performance with c-statistic of 0.71 for 7-day and for 30-day readmission, and 0.74 for 60-day. Previous history of healthcare utilization, urgency of the index admission, old age, comorbidities related to cancer, psychosis, and drug-abuse, abnormal pathology results at discharge, and being unmarried and a public patient were found to be important predictors in all models. Unplanned readmissions beyond 7 days were more strongly associated with longer hospital stays and older patients with higher number of comorbidities and higher use of acute care in the past year. 

Conclusions: This study demonstrates similar predictors and performance to previous risk scores of 30-day unplanned readmission. Shorter-term readmissions may have different causal pathways than 30-day readmission, and may, therefore, require different screening tools and interventions. This study also re-iterates the need to include more informative data elements to ensure the appropriateness of these risk scores in clinical practice.

LanguageEnglish
Pages1-11
Number of pages11
JournalBMC Medical Informatics and Decision Making
Volume18
Issue number1
DOIs
Publication statusPublished - 2018

Fingerprint

Comorbidity
Logistic Models
Patient Discharge
Urban Hospitals
Psychotic Disorders
Calibration
Substance-Related Disorders
Medical Records
Length of Stay
Pathology
Delivery of Health Care
Neoplasms

Bibliographical note

Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

  • Hospital readmission
  • Readmission risk scores

Cite this

@article{9d5ca7b4d3a4476ea60d5de841d1943d,
title = "Predicting 7-day, 30-day and 60-day all-cause unplanned readmission: a case study of a Sydney hospital",
abstract = "Background: The identification of patients at high risk of unplanned readmission is an important component of discharge planning strategies aimed at preventing unwanted returns to hospital. The aim of this study was to investigate the factors associated with unplanned readmission in a Sydney hospital. We developed and compared validated readmission risk scores using routinely collected hospital data to predict 7-day, 30-day and 60-day all-cause unplanned readmission. Methods: A combination of gradient boosted tree algorithms for variable selection and logistic regression models was used to build and validate readmission risk scores using medical records from 62,235 live discharges from a metropolitan hospital in Sydney, Australia. Results: The scores had good calibration and fair discriminative performance with c-statistic of 0.71 for 7-day and for 30-day readmission, and 0.74 for 60-day. Previous history of healthcare utilization, urgency of the index admission, old age, comorbidities related to cancer, psychosis, and drug-abuse, abnormal pathology results at discharge, and being unmarried and a public patient were found to be important predictors in all models. Unplanned readmissions beyond 7 days were more strongly associated with longer hospital stays and older patients with higher number of comorbidities and higher use of acute care in the past year. Conclusions: This study demonstrates similar predictors and performance to previous risk scores of 30-day unplanned readmission. Shorter-term readmissions may have different causal pathways than 30-day readmission, and may, therefore, require different screening tools and interventions. This study also re-iterates the need to include more informative data elements to ensure the appropriateness of these risk scores in clinical practice.",
keywords = "Hospital readmission, Readmission risk scores",
author = "Yashar Maali and Oscar Perez-Concha and Enrico Coiera and David Roffe and Day, {Richard O.} and Blanca Gallego",
note = "Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2018",
doi = "10.1186/s12911-017-0580-8",
language = "English",
volume = "18",
pages = "1--11",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "Springer, Springer Nature",
number = "1",

}

Predicting 7-day, 30-day and 60-day all-cause unplanned readmission : a case study of a Sydney hospital. / Maali, Yashar; Perez-Concha, Oscar; Coiera, Enrico; Roffe, David; Day, Richard O.; Gallego, Blanca.

In: BMC Medical Informatics and Decision Making, Vol. 18, No. 1, 2018, p. 1-11.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Predicting 7-day, 30-day and 60-day all-cause unplanned readmission

T2 - BMC Medical Informatics and Decision Making

AU - Maali, Yashar

AU - Perez-Concha, Oscar

AU - Coiera, Enrico

AU - Roffe, David

AU - Day, Richard O.

AU - Gallego, Blanca

N1 - Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2018

Y1 - 2018

N2 - Background: The identification of patients at high risk of unplanned readmission is an important component of discharge planning strategies aimed at preventing unwanted returns to hospital. The aim of this study was to investigate the factors associated with unplanned readmission in a Sydney hospital. We developed and compared validated readmission risk scores using routinely collected hospital data to predict 7-day, 30-day and 60-day all-cause unplanned readmission. Methods: A combination of gradient boosted tree algorithms for variable selection and logistic regression models was used to build and validate readmission risk scores using medical records from 62,235 live discharges from a metropolitan hospital in Sydney, Australia. Results: The scores had good calibration and fair discriminative performance with c-statistic of 0.71 for 7-day and for 30-day readmission, and 0.74 for 60-day. Previous history of healthcare utilization, urgency of the index admission, old age, comorbidities related to cancer, psychosis, and drug-abuse, abnormal pathology results at discharge, and being unmarried and a public patient were found to be important predictors in all models. Unplanned readmissions beyond 7 days were more strongly associated with longer hospital stays and older patients with higher number of comorbidities and higher use of acute care in the past year. Conclusions: This study demonstrates similar predictors and performance to previous risk scores of 30-day unplanned readmission. Shorter-term readmissions may have different causal pathways than 30-day readmission, and may, therefore, require different screening tools and interventions. This study also re-iterates the need to include more informative data elements to ensure the appropriateness of these risk scores in clinical practice.

AB - Background: The identification of patients at high risk of unplanned readmission is an important component of discharge planning strategies aimed at preventing unwanted returns to hospital. The aim of this study was to investigate the factors associated with unplanned readmission in a Sydney hospital. We developed and compared validated readmission risk scores using routinely collected hospital data to predict 7-day, 30-day and 60-day all-cause unplanned readmission. Methods: A combination of gradient boosted tree algorithms for variable selection and logistic regression models was used to build and validate readmission risk scores using medical records from 62,235 live discharges from a metropolitan hospital in Sydney, Australia. Results: The scores had good calibration and fair discriminative performance with c-statistic of 0.71 for 7-day and for 30-day readmission, and 0.74 for 60-day. Previous history of healthcare utilization, urgency of the index admission, old age, comorbidities related to cancer, psychosis, and drug-abuse, abnormal pathology results at discharge, and being unmarried and a public patient were found to be important predictors in all models. Unplanned readmissions beyond 7 days were more strongly associated with longer hospital stays and older patients with higher number of comorbidities and higher use of acute care in the past year. Conclusions: This study demonstrates similar predictors and performance to previous risk scores of 30-day unplanned readmission. Shorter-term readmissions may have different causal pathways than 30-day readmission, and may, therefore, require different screening tools and interventions. This study also re-iterates the need to include more informative data elements to ensure the appropriateness of these risk scores in clinical practice.

KW - Hospital readmission

KW - Readmission risk scores

UR - http://www.scopus.com/inward/record.url?scp=85042583701&partnerID=8YFLogxK

U2 - 10.1186/s12911-017-0580-8

DO - 10.1186/s12911-017-0580-8

M3 - Article

VL - 18

SP - 1

EP - 11

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

SN - 1472-6947

IS - 1

ER -