Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30)

John Billings, Ian Blunt, Adam Steventon, Theo Georghiou, Geraint Lewis, Martin Bardsley

Research output: Contribution to journalArticle

Abstract

Objectives: To develop an algorithm for identifying inpatients at high risk of re-admission to a National Health Service (NHS) hospital in England within 30 days of discharge using information that can either be obtained from hospital information systems or from the patient and their notes. Design: Multivariate statistical analysis of routinely collected hospital episode statistics (HES) data using logistic regression to build the predictive model. The model's performance was calculated using bootstrapping. Setting: HES data covering all NHS hospital admissions in England. Participants: The NHS patients were admitted to hospital between April 2008 and March 2009 (10% sample of all admissions, n=576 868). Main outcome measures: Area under the receiver operating characteristic curve for the algorithm, together with its positive predictive value and sensitivity for a range of risk score thresholds. Results: The algorithm produces a ' risk score' ranging (0-1) for each admitted patient, and the percentage of patients with a re-admission within 30 days and the mean re-admission costs of all patients are provided for 20 risk bands. At a risk score threshold of 0.5, the positive predictive value (ie, percentage of inpatients identified as high risk who were subsequently re-admitted within 30 days) was 59.2% (95% CI 58.0% to 60.5%); representing 5.4% (95% CI 5.2% to 5.6%) of all inpatients who would be re-admitted within 30 days (sensitivity). The area under the receiver operating characteristic curve was 0.70 (95% CI 0.69 to 0.70). Conclusions: We have developed a method of identifying inpatients at high risk of unplanned readmission to NHS hospitals within 30 days of discharge. Though the models had a low sensitivity, we show how to identify subgroups of patients that contain a high proportion of patients who will be readmitted within 30 days. Additional work is necessary to validate the model in practice.

Original languageEnglish (US)
Article numbere001667
JournalBMJ Open
Volume2
Issue number4
DOIs
StatePublished - 2012

Fingerprint

Inpatients
National Health Programs
ROC Curve
England
Hospital Information Systems
Multivariate Analysis
Logistic Models
Outcome Assessment (Health Care)
Costs and Cost Analysis

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30). / Billings, John; Blunt, Ian; Steventon, Adam; Georghiou, Theo; Lewis, Geraint; Bardsley, Martin.

In: BMJ Open, Vol. 2, No. 4, e001667, 2012.

Research output: Contribution to journalArticle

Billings, John ; Blunt, Ian ; Steventon, Adam ; Georghiou, Theo ; Lewis, Geraint ; Bardsley, Martin. / Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30). In: BMJ Open. 2012 ; Vol. 2, No. 4.
@article{0da4acf5a9304d5696c1047e0a368e14,
title = "Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30)",
abstract = "Objectives: To develop an algorithm for identifying inpatients at high risk of re-admission to a National Health Service (NHS) hospital in England within 30 days of discharge using information that can either be obtained from hospital information systems or from the patient and their notes. Design: Multivariate statistical analysis of routinely collected hospital episode statistics (HES) data using logistic regression to build the predictive model. The model's performance was calculated using bootstrapping. Setting: HES data covering all NHS hospital admissions in England. Participants: The NHS patients were admitted to hospital between April 2008 and March 2009 (10{\%} sample of all admissions, n=576 868). Main outcome measures: Area under the receiver operating characteristic curve for the algorithm, together with its positive predictive value and sensitivity for a range of risk score thresholds. Results: The algorithm produces a ' risk score' ranging (0-1) for each admitted patient, and the percentage of patients with a re-admission within 30 days and the mean re-admission costs of all patients are provided for 20 risk bands. At a risk score threshold of 0.5, the positive predictive value (ie, percentage of inpatients identified as high risk who were subsequently re-admitted within 30 days) was 59.2{\%} (95{\%} CI 58.0{\%} to 60.5{\%}); representing 5.4{\%} (95{\%} CI 5.2{\%} to 5.6{\%}) of all inpatients who would be re-admitted within 30 days (sensitivity). The area under the receiver operating characteristic curve was 0.70 (95{\%} CI 0.69 to 0.70). Conclusions: We have developed a method of identifying inpatients at high risk of unplanned readmission to NHS hospitals within 30 days of discharge. Though the models had a low sensitivity, we show how to identify subgroups of patients that contain a high proportion of patients who will be readmitted within 30 days. Additional work is necessary to validate the model in practice.",
author = "John Billings and Ian Blunt and Adam Steventon and Theo Georghiou and Geraint Lewis and Martin Bardsley",
year = "2012",
doi = "10.1136/bmjopen-2012-001667",
language = "English (US)",
volume = "2",
journal = "BMJ Open",
issn = "2044-6055",
publisher = "BMJ Publishing Group",
number = "4",

}

TY - JOUR

T1 - Development of a predictive model to identify inpatients at risk of re-admission within 30 days of discharge (PARR-30)

AU - Billings, John

AU - Blunt, Ian

AU - Steventon, Adam

AU - Georghiou, Theo

AU - Lewis, Geraint

AU - Bardsley, Martin

PY - 2012

Y1 - 2012

N2 - Objectives: To develop an algorithm for identifying inpatients at high risk of re-admission to a National Health Service (NHS) hospital in England within 30 days of discharge using information that can either be obtained from hospital information systems or from the patient and their notes. Design: Multivariate statistical analysis of routinely collected hospital episode statistics (HES) data using logistic regression to build the predictive model. The model's performance was calculated using bootstrapping. Setting: HES data covering all NHS hospital admissions in England. Participants: The NHS patients were admitted to hospital between April 2008 and March 2009 (10% sample of all admissions, n=576 868). Main outcome measures: Area under the receiver operating characteristic curve for the algorithm, together with its positive predictive value and sensitivity for a range of risk score thresholds. Results: The algorithm produces a ' risk score' ranging (0-1) for each admitted patient, and the percentage of patients with a re-admission within 30 days and the mean re-admission costs of all patients are provided for 20 risk bands. At a risk score threshold of 0.5, the positive predictive value (ie, percentage of inpatients identified as high risk who were subsequently re-admitted within 30 days) was 59.2% (95% CI 58.0% to 60.5%); representing 5.4% (95% CI 5.2% to 5.6%) of all inpatients who would be re-admitted within 30 days (sensitivity). The area under the receiver operating characteristic curve was 0.70 (95% CI 0.69 to 0.70). Conclusions: We have developed a method of identifying inpatients at high risk of unplanned readmission to NHS hospitals within 30 days of discharge. Though the models had a low sensitivity, we show how to identify subgroups of patients that contain a high proportion of patients who will be readmitted within 30 days. Additional work is necessary to validate the model in practice.

AB - Objectives: To develop an algorithm for identifying inpatients at high risk of re-admission to a National Health Service (NHS) hospital in England within 30 days of discharge using information that can either be obtained from hospital information systems or from the patient and their notes. Design: Multivariate statistical analysis of routinely collected hospital episode statistics (HES) data using logistic regression to build the predictive model. The model's performance was calculated using bootstrapping. Setting: HES data covering all NHS hospital admissions in England. Participants: The NHS patients were admitted to hospital between April 2008 and March 2009 (10% sample of all admissions, n=576 868). Main outcome measures: Area under the receiver operating characteristic curve for the algorithm, together with its positive predictive value and sensitivity for a range of risk score thresholds. Results: The algorithm produces a ' risk score' ranging (0-1) for each admitted patient, and the percentage of patients with a re-admission within 30 days and the mean re-admission costs of all patients are provided for 20 risk bands. At a risk score threshold of 0.5, the positive predictive value (ie, percentage of inpatients identified as high risk who were subsequently re-admitted within 30 days) was 59.2% (95% CI 58.0% to 60.5%); representing 5.4% (95% CI 5.2% to 5.6%) of all inpatients who would be re-admitted within 30 days (sensitivity). The area under the receiver operating characteristic curve was 0.70 (95% CI 0.69 to 0.70). Conclusions: We have developed a method of identifying inpatients at high risk of unplanned readmission to NHS hospitals within 30 days of discharge. Though the models had a low sensitivity, we show how to identify subgroups of patients that contain a high proportion of patients who will be readmitted within 30 days. Additional work is necessary to validate the model in practice.

UR - http://www.scopus.com/inward/record.url?scp=84865126986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865126986&partnerID=8YFLogxK

U2 - 10.1136/bmjopen-2012-001667

DO - 10.1136/bmjopen-2012-001667

M3 - Article

C2 - 22885591

AN - SCOPUS:84865126986

VL - 2

JO - BMJ Open

JF - BMJ Open

SN - 2044-6055

IS - 4

M1 - e001667

ER -