A Methodology to Generate Longitudinally Updated Acute‐On‐Chronic Liver Failure Prognostication Scores From Electronic Health Record Data

Abstract

Queries of electronic health record (EHR) data repositories allow for automated data collection. These techniques have not been used in hepatology due to the inability to capture hepatic encephalopathy (HE) grades, which are inputs for acute-on-chronic liver failure (ACLF) models. Here, we describe a methodology to use EHR data to calculate rolling ACLF scores. We examined 239 patient admissions with end-stage liver disease from July 2014 to June 2019. We mapped EHR flowsheet data to determine HE grades and calculated two longitudinally updated ACLF scores. We validated HE grades and ACLF diagnoses by chart review and calculated sensitivity, specificity, and Cohen's kappa. Of 239 patient admissions analyzed, 37% were women, 46% were non-Hispanic white, median age was 60 years, and the median Model for End-Stage Liver Disease-Na score at admission was 25. Of the 239, 7% were diagnosed with ACLF as defined by the North American Consortium for the Study of End-Stage Liver Disease (NACSELD) diagnostic criteria at admission, 27% during the hospitalization, and 9% at discharge. Forty percent were diagnosed with ACLF by the European Association for the Study of the Liver-Chronic Liver Failure Consortium (CLIF-C) diagnostic criteria at admission, 51% during the hospitalization, and 34% at discharge. From the chart review of 51 admissions, we found sensitivities and specificities for any HE (grades 1-4) were 92%-97% and 76%-95%, respectively; for severe HE (grades 3-4), sensitivities and specificities were 100% and 78%-98%, respectively. Cohen's kappa between flowsheet and chart review of HE grades ranged from 0.55 to 0.72. Sensitivities and specificities for NACSELD-ACLF diagnoses were 75%-100% and 96%-100%, respectively; for CLIF-C-ACLF diagnoses, these were 91%-100% and 96-100%, respectively. We generated approximately 28 unique ACLF scores per patient per admission day. Conclusion: We developed an informaticsbased methodology to calculate longitudinally updated ACLF scores. This opens new analytic potentials, such as big data methods, to develop electronic phenotypes for patients with ACLF. (Hepatology Communications 2021;0:1-12). E lectronic health records (EHRs) capture and generate vast amounts of granular clinical data through routine operations. (1) Structured Query Language (SQL) queries of associated clinical data repositories (CDRs) allow for automated generation of comprehensive laboratory, flowsheet, medical device, and medication administration reports for a cohort of patients. (2-4) Integration of these separate

Predicting post–liver transplant outcomes in patients with acute-on-chronic liver failure using Expert-Augmented Machine Learning

“…Consistent with prior informatics approaches for detecting ACLF admissions, we excluded all patients who underwent transplant within 48 hours of admission as they were likely admitted electively. (15) We included patients who had evidence of ACLF prior to the time of LT through a previously published informatics-driven approach. (15) Briefly, this involves identifying any patient who meets ACLF diagnostic criteria based on the NACSELD or EF-CLIF definitions prior to LT. We did not use the APASL ACLF diagnostic criteria due to bacterial infection being the most common precipitant of ACLF in patients with cirrhosis in the United States.…”

“…Our group had previously demonstrated an informatics approach to extract EHR data that yielded a median of 454 features per admission to more accurately represent ACLF patients' clinical courses. (15) Machine Learning (ML) is well-suited for analyzing such data, but can be misleading when taken out of context of biological or clinical mechanisms. (16,17) Expert-Augmented Machine Learning (EAML) is an emerging technique that overcomes this limitation of ML by extracting rules from decision-tree ML models for human expert feedback.…”

“Beyond MELD” – Emerging strategies and technologies for improving mortality prediction, organ allocation and outcomes in liver transplantation

“…72 In clinical hepatology, the integration of longitudinal EHR elements, such as structured flowsheet entries, medication administration, procedure orders, vital signs, and laboratory values, has enabled dynamic calculations of the North American Consortium for the Study of End-Stage Liver Disease-ACLF and Chronic Liver Failure Consortium-ACLF prognostication scores in hospitalised patients with ACLF. 73 Despite the potential for longitudinal EHR data to improve outcome prediction, the lack of standards, lack of semantic interoperability, and disparate EHR systems/implementations have historically limited large multi-institution collaborations. 74 Early regional-based EHR consortiums, such as HealthLNK based in the Chicago area, have demonstrated the value of multicentre EHR data in predicting factors associated with mortality in patients with cirrhosis.…”

Predicting Post-Liver Transplant Outcomes in Patients with Acute-on-Chronic Liver Failure using Expert-Augmented Machine Learning

“…Our group had previously demonstrated an informatics approach to extract EHR data that yielded a median of 454 features per admission to more accurately represent ACLF patients’ clinical courses. (15) Machine Learning (ML) is well-suited for analyzing such data, but can be misleading when taken out of context of biological or clinical mechanisms. (16,17)…”