Predictive Algorithm for Hepatic Steatosis Detection Using Elastography Data in the Veterans Affairs Electronic Health Records

Saroja Bangaru; Ram Sundaresh; Anna Lee; Nicole Prause; Frank Hao; Tien S Dong; Monica Tincopa; George Cholankeril; Nicole E Rich; Jenna Kawamoto; Debika Bhattacharya; Steven B Han; Arpan A Patel; Magda Shaheen; Jihane N Benhammou

doi:10.1007/s10620-023-08043-8

Predictive Algorithm for Hepatic Steatosis Detection Using Elastography Data in the Veterans Affairs Electronic Health Records

Dig Dis Sci. 2023 Dec;68(12):4474-4484. doi: 10.1007/s10620-023-08043-8. Epub 2023 Oct 21.

Authors

Saroja Bangaru^{1

2}, Ram Sundaresh³, Anna Lee³, Nicole Prause¹, Frank Hao⁴, Tien S Dong^{1

2}, Monica Tincopa⁵, George Cholankeril⁶, Nicole E Rich⁷, Jenna Kawamoto², Debika Bhattacharya^{8

9}, Steven B Han^{1

2}, Arpan A Patel^{1

2

10}, Magda Shaheen¹¹, Jihane N Benhammou^{12

13

14}

Affiliations

¹ Vatche and Tamar Manoukian Division of Digestive Diseases, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA, 90095, USA.
² Greater Los Angeles Veterans Affairs Healthcare System, Gastroenterology, Hepatology and Parenteral Nutrition, Los Angeles, CA, 90075, USA.
³ David Geffen School of Medicine, University of California, Los Angeles, CA, 90095, USA.
⁴ Department of Radiology, University of California, Los Angeles, Los Angeles, CA, 90095, USA.
⁵ Liver Center, University of California, San Diego, San Diego, CA, 92093, USA.
⁶ Section of Gastroenterology and Hepatology, Department of Medicine, Baylor College of Medicine, Houston, TX, 77030, USA.
⁷ UT Southwestern Medical Center, Division of Digestive and Liver Diseases and Harold C. Simmons Comprehensive Cancer Center, Dallas, TX, 75390, USA.
⁸ Division of Infectious Diseases, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA, 90095, USA.
⁹ Section of Infectious Diseases, Greater Los Angeles Veterans Affairs Healthcare System, Los Angeles, CA, 90075, USA.
¹⁰ VA Center for the Study of Healthcare Innovation, Implementation, and Policy (CSHIIP), North Hills, CA, 91343, USA.
¹¹ College of Medicine, Charles R Drew University, Los Angeles, CA, USA.
¹² Greater Los Angeles Veterans Affairs Healthcare System, Gastroenterology, Hepatology and Parenteral Nutrition, Los Angeles, CA, 90075, USA. jbenhammmou@mednet.ucla.edu.
¹³ Jonsson Comprehensive Cancer Center, University of California, Los Angeles, Los Angeles, CA, 90095, USA. jbenhammmou@mednet.ucla.edu.
¹⁴ Department of Medicine, University of California, Los Angeles, 11301 Wilshire Blvd, Building 113, Room 312, Los Angeles, CA, 90073, USA. jbenhammmou@mednet.ucla.edu.

Abstract

Background and aims: Nonalcoholic fatty liver disease (NAFLD) has reached pandemic proportions. Early detection can identify at-risk patients who can be linked to hepatology care. The vibration-controlled transient elastography (VCTE) controlled attenuation parameter (CAP) is biopsy validated to diagnose hepatic steatosis (HS). We aimed to develop a novel clinical predictive algorithm for HS using the CAP score at a Veterans' Affairs hospital.

Methods: We identified 403 patients in the Greater Los Angeles VA Healthcare System with valid VCTEs during 1/2018-6/2020. Patients with alcohol-associated liver disease, genotype 3 hepatitis C, any malignancies, or liver transplantation were excluded. Linear regression was used to identify predictors of NAFLD. To identify a CAP threshold for HS detection, receiver operating characteristic analysis was applied using liver biopsy, MRI, and ultrasound as the gold standards.

Results: The cohort was racially/ethnically diverse (26% Black/African American; 20% Hispanic). Significant positive predictors of elevated CAP score included diabetes, cholesterol, triglycerides, BMI, and self-identifying as Hispanic. Our predictions of CAP scores using this model strongly correlated (r = 0.61, p < 0.001) with actual CAP scores. The NAFLD model was validated in an independent Veteran cohort and yielded a sensitivity of 82% and specificity 83% (p < 0.001, 95% CI 0.46-0.81%). The estimated optimal CAP for our population cut-off was 273.5 dB/m, resulting in AUC = 75.5% (95% CI 70.7-80.3%).

Conclusion: Our HS predictive algorithm can identify at-risk Veterans for NAFLD to further risk stratify them by non-invasive tests and link them to sub-specialty care. Given the biased referral pattern for VCTEs, future work will need to address its applicability in non-specialty clinics. Proposed clinical algorithm to identify patients at-risk for NAFLD prior to fibrosis staging in Veteran.

Keywords: Elastography; Model; Nonalcoholic fatty liver disease; Prediction.

Publication types

Research Support, Non-U.S. Gov't
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Biopsy
Elasticity Imaging Techniques* / methods
Electronic Health Records
Humans
Liver / pathology
Liver Cirrhosis / diagnosis
Liver Diseases, Alcoholic* / complications
Non-alcoholic Fatty Liver Disease* / pathology
Prospective Studies
ROC Curve
Veterans*

Grants and funding

UL1 TR001881/TR/NCATS NIH HHS/United States