Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study

Objectives Outcomes in hepatocellular carcinoma (HCC) are determined by both cancer characteristics and liver disease severity. This study aims to validate the use of inpatient electronic health records to determine liver disease severity from treatment and procedure codes.Design Retrospective obser...

Full description

Saved in:
Bibliographic Details
Main Authors: Anya Burton, Amy Downing, Eva Morris, Jessica Shearer, Robert J Driver, Vinay Balachandrakumar, Tim Cross, Ian A Rowe
Format: Article
Language:English
Published: BMJ Publishing Group 2019-07-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/9/7/e028571.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850236578049294336
author Anya Burton
Amy Downing
Eva Morris
Jessica Shearer
Robert J Driver
Vinay Balachandrakumar
Tim Cross
Ian A Rowe
author_facet Anya Burton
Amy Downing
Eva Morris
Jessica Shearer
Robert J Driver
Vinay Balachandrakumar
Tim Cross
Ian A Rowe
author_sort Anya Burton
collection DOAJ
description Objectives Outcomes in hepatocellular carcinoma (HCC) are determined by both cancer characteristics and liver disease severity. This study aims to validate the use of inpatient electronic health records to determine liver disease severity from treatment and procedure codes.Design Retrospective observational study.Setting Two National Health Service (NHS) cancer centres in England.Participants 339 patients with a new diagnosis of HCC between 2007 and 2016.Main outcome Using inpatient electronic health records, we have developed an optimised algorithm to identify cirrhosis and determine liver disease severity in a population with HCC. The diagnostic accuracy of the algorithm was optimised using clinical records from one NHS Trust and it was externally validated using anonymised data from another centre.Results The optimised algorithm has a positive predictive value (PPV) of 99% for identifying cirrhosis in the derivation cohort, with a sensitivity of 86% (95% CI 82% to 90%) and a specificity of 98% (95% CI 96% to 100%). The sensitivity for detecting advanced stage cirrhosis is 80% (95% CI 75% to 87%) and specificity is 98% (95% CI 96% to 100%), with a PPV of 89%.Conclusions Our optimised algorithm, based on inpatient electronic health records, reliably identifies and stages cirrhosis in patients with HCC. This highlights the potential of routine health data in population studies to stratify patients with HCC according to liver disease severity.
format Article
id doaj-art-1404be526837463d987dbeeb6bd2f561
institution OA Journals
issn 2044-6055
language English
publishDate 2019-07-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-1404be526837463d987dbeeb6bd2f5612025-08-20T02:01:57ZengBMJ Publishing GroupBMJ Open2044-60552019-07-019710.1136/bmjopen-2018-028571Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational studyAnya Burton0Amy Downing1Eva Morris2Jessica Shearer3Robert J Driver4Vinay Balachandrakumar5Tim Cross6Ian A Rowe7National Cancer Registration and Analysis Service, Bristol, UKLeeds Institute of Medical Research, University of Leeds, Leeds, UKApplied Health Research Unit, Big Data Institute, Nuffield Department of Population Health, University of Oxford, Oxford, UKDepartment of Hepatology, Leeds Teaching Hospitals NHS Trust, Leeds, UKDepartment of Hepatology, Leeds Teaching Hospitals NHS Trust, Leeds, UKRoyal Liverpool and Broadgreen University Hospitals NHS Trust, Liverpool, UKRoyal Liverpool University Hospital, UK8 University of Leeds, Leeds, UKObjectives Outcomes in hepatocellular carcinoma (HCC) are determined by both cancer characteristics and liver disease severity. This study aims to validate the use of inpatient electronic health records to determine liver disease severity from treatment and procedure codes.Design Retrospective observational study.Setting Two National Health Service (NHS) cancer centres in England.Participants 339 patients with a new diagnosis of HCC between 2007 and 2016.Main outcome Using inpatient electronic health records, we have developed an optimised algorithm to identify cirrhosis and determine liver disease severity in a population with HCC. The diagnostic accuracy of the algorithm was optimised using clinical records from one NHS Trust and it was externally validated using anonymised data from another centre.Results The optimised algorithm has a positive predictive value (PPV) of 99% for identifying cirrhosis in the derivation cohort, with a sensitivity of 86% (95% CI 82% to 90%) and a specificity of 98% (95% CI 96% to 100%). The sensitivity for detecting advanced stage cirrhosis is 80% (95% CI 75% to 87%) and specificity is 98% (95% CI 96% to 100%), with a PPV of 89%.Conclusions Our optimised algorithm, based on inpatient electronic health records, reliably identifies and stages cirrhosis in patients with HCC. This highlights the potential of routine health data in population studies to stratify patients with HCC according to liver disease severity.https://bmjopen.bmj.com/content/9/7/e028571.full
spellingShingle Anya Burton
Amy Downing
Eva Morris
Jessica Shearer
Robert J Driver
Vinay Balachandrakumar
Tim Cross
Ian A Rowe
Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
BMJ Open
title Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
title_full Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
title_fullStr Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
title_full_unstemmed Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
title_short Validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in England: an observational study
title_sort validation of an algorithm using inpatient electronic health records to determine the presence and severity of cirrhosis in patients with hepatocellular carcinoma in england an observational study
url https://bmjopen.bmj.com/content/9/7/e028571.full
work_keys_str_mv AT anyaburton validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT amydowning validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT evamorris validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT jessicashearer validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT robertjdriver validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT vinaybalachandrakumar validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT timcross validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy
AT ianarowe validationofanalgorithmusinginpatientelectronichealthrecordstodeterminethepresenceandseverityofcirrhosisinpatientswithhepatocellularcarcinomainenglandanobservationalstudy