Validity of an Automated Algorithm to Identify Cirrhosis Using Electronic Health Records in Patients with Primary Biliary Cholangitis

• Main Authors: Lu M, Bowlus CL, Lindor K, Rodriguez-Watson CV, Romanelli RJ, Haller IV, Anderson H, VanWormer JJ, Boscarino JA, Schmidt MA, Daida YG, Sahota A, Vincent J, Li J, Trudeau S, Rupp LB, Gordon SC
• Format: Article
• Language: English
• Published: Dove Medical Press 2020-11-01
• Series: Clinical Epidemiology
• Subjects: primary biliary cirrhosis; cholangitis; race/ gender/ ethnicity; decompensated cirrhosis; ursodeoxycholic acid/ udca’
• Online Access: https://www.dovepress.com/validity-of-an-automated-algorithm-to-identify-cirrhosis-using-electro-peer-reviewed-article-CLEP

Mei Lu,1 Christopher L Bowlus,2 Keith Lindor,3 Carla V Rodriguez-Watson,4 Robert J Romanelli,5 Irina V Haller,6 Heather Anderson,7 Jeffrey J VanWormer,8 Joseph A Boscarino,9 Mark A Schmidt,10 Yihe G Daida,11 Amandeep Sahota,12 Jennifer Vincent,13 Jia Li,1 Sheri Trudeau,1 Loralee B Rupp,14 Stuart C Gordon15 On Behalf of the FOLD Investigators1Department of Public Health Sciences, Henry Ford Health System, Detroit, MI, USA; 2University of California Davis School of Medicine, Sacramento, CA, USA; 3College of Health Solutions, Arizona State University, Phoenix, AZ, USA; 4Center for Health Research Kaiser Permanente Mid-Atlantic Research Institute, Rockville, MD; Reagan-Udall Foundation for the FDA, Washington, DC, USA; 5Palo Alto Medical Foundation Research Institute, Palo Alto, CA, USA; 6Essentia Institute of Rural Health, Essentia Health, Duluth, MN, USA; 7Skaggs School of Pharmacy and Pharmaceutical Sciences, University of Colorado Anschutz Medical Campus, Aurora, CO, USA; 8Marshfield Clinic Research Foundation, Marshfield, WI, USA; 9Department of Population Health Sciences, Geisinger Clinic, Danville, PA, USA; 10Center for Health Research, Kaiser Permanente Northwest, Portland, OR, USA; 11Center for Integrated Health Care Research, Kaiser Permanente Hawai’i, Honolulu, HI, USA; 12Department of Research and Evaluation, Kaiser Permanente Southern California, Los Angeles, CA, USA; 13Baylor, Scott & White Research Institute, Temple, TX, USA; 14Center for Health Policy and Health Services Research, Henry Ford Health System, Detroit, MI, USA; 15Division of Gastroenterology and Hepatology, Henry Ford Health System; and Wayne State University School of Medicine, Detroit, MI, USACorrespondence: Mei LuDepartment of Public Health Sciences, Henry Ford Health System, 3E One Ford Place, Detroit, MI 48202, USATel [phone]Fax [phone]Email [e-mail]: Biopsy remains the gold standard for determining fibrosis stage in patients with primary biliary cholangitis (PBC), but it is unavailable for most patients. We used data from the 11 US health systems in the FibrOtic Liver Disease Consortium to explore a combination of biochemical markers and electronic health record (EHR)-based diagnosis/procedure codes (DPCs) to identify the presence of cirrhosis in PBC patients.Methods: Histological fibrosis staging data were obtained from liver biopsies. Variables considered for the model included demographics (age, gender, race, ethnicity), total bilirubin, alkaline phosphatase, albumin, aspartate aminotransferase (AST) to platelet ratio index (APRI), Fibrosis 4 (FIB4) index, AST to alanine aminotransferase (ALT) ratio, and > 100 DPCs associated with cirrhosis/decompensated cirrhosis, categorized into ten clusters. Using least absolute shrinkage and selection operator regression (LASSO), we derived and validated cutoffs for identifying cirrhosis.Results: Among 4328 PBC patients, 1350 (32%) had biopsy data; 121 (9%) were staged F4 (cirrhosis). DPC clusters (including codes related to cirrhosis and hepatocellular carcinoma diagnoses/procedures), Hispanic ethnicity, ALP, AST/ALT ratio, and total bilirubin were retained in the final model (AUROC=0.86 and 0.83 on learning and testing data, respectively); this model with two cutoffs divided patients into three categories (no cirrhosis, indeterminate, and cirrhosis) with specificities of 81.8% (for no cirrhosis) and 80.3% (for cirrhosis). A model excluding DPCs retained ALP, AST/ALT ratio, total bilirubin, Hispanic ethnicity, and gender (AUROC=0.81 and 0.78 on learning and testing data, respectively).Conclusion: An algorithm using laboratory results and DPCs can categorize a majority of PBC patients as cirrhotic or noncirrhotic with high accuracy (with a small remaining group of patients’ cirrhosis status indeterminate). In the absence of biopsy data, this EHR-based model can be used to identify cirrhosis in cohorts of PBC patients for research and/or clinical follow-up.Keywords: primary biliary cirrhosis, cholangitis, race/gender/ethnicity, gender, ethnicity, decompensated cirrhosis, ursodeoxycholic acid, UCDA