1 Leeds Institute of Medical Research, University of Leeds, Leeds, UK.
2 Department of Hepatology, Leeds Teaching Hospitals NHS Trust, Leeds, UK.
3 Leeds Institute for Data Analytics, University of Leeds, Leeds, UK.
4 Royal Liverpool and Broadgreen University Hospitals NHS Trust, Liverpool, UK.
5 National Cancer Registration and Analysis Service, Bristol, UK.
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.
Retrospective observational study.
Two National Health Service (NHS) cancer centres in England.
339 patients with a new diagnosis of HCC between 2007 and 2016.
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.
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%.
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.