TY - JOUR
T1 - Predictive Algorithm for Hepatic Steatosis Detection Using Elastography Data in the Veterans Affairs Electronic Health Records
AU - Bangaru, Saroja
AU - Sundaresh, Ram
AU - Lee, Anna
AU - Prause, Nicole
AU - Hao, Frank
AU - Dong, Tien S.
AU - Tincopa, Monica
AU - Cholankeril, George
AU - Rich, Nicole E.
AU - Kawamoto, Jenna
AU - Bhattacharya, Debika
AU - Han, Steven B.
AU - Patel, Arpan A.
AU - Shaheen, Magda
AU - Benhammou, Jihane N.
N1 - Publisher Copyright:
© 2023, This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.
PY - 2023/12
Y1 - 2023/12
N2 - 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. Graphical Abstract: Proposed clinical algorithm to identify patients at-risk for NAFLD prior to fibrosis staging in Veteran.[Figure not available: see fulltext.]
AB - 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. Graphical Abstract: Proposed clinical algorithm to identify patients at-risk for NAFLD prior to fibrosis staging in Veteran.[Figure not available: see fulltext.]
KW - Elastography
KW - Model
KW - Nonalcoholic fatty liver disease
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=85174564755&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174564755&partnerID=8YFLogxK
U2 - 10.1007/s10620-023-08043-8
DO - 10.1007/s10620-023-08043-8
M3 - Article
C2 - 37864738
AN - SCOPUS:85174564755
SN - 0163-2116
VL - 68
SP - 4474
EP - 4484
JO - Digestive Diseases and Sciences
JF - Digestive Diseases and Sciences
IS - 12
ER -