TY - JOUR
T1 - Adapted time-varying covariates Cox model for predicting future cirrhosis development performs well in a large hepatitis C cohort
AU - Beste, Lauren A.
AU - Zhang, Xuefei
AU - Su, Grace L.
AU - Van, Tony
AU - Ioannou, George N.
AU - Oselio, Brandon
AU - Tincopa, Monica
AU - Liu, Boang
AU - Singal, Amit G.
AU - Zhu, Ji
AU - Waljee, Akbar K.
N1 - Funding Information:
The funders had no role in design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication. Drs. Waljee, Beste, Ioannou, Su are funded by IIR 16-024 from the United States (U.S.) Department of Veterans Affairs Health Services R&D (HSRD) Service. Drs. Waljee and Zhu are supported by the Michigan Integrated Center for Health Analytics and Medical Prediction (MiCHAMP) in the Institute for Healthcare Policy and Innovation at the University of Michigan Medical School.
Funding Information:
This material is the result of work supported by resources from the VA Ann Arbor Health Care System (Ann Arbor, Michigan) and VA Puget Sound Health Care System (Seattle, Washington). The views expressed in this article are those of the authors and do not necessarily represent the views of the Department of Veterans Affairs or the United States Government.
Funding Information:
Lauren A. Beste, MD, MSc: None. Xuefei Zhang, MS: None. Grace Su, MD: Is an equity owner of Applied Morphomics and Prenovo. Dr. Su has a patent with the University of Michigan regarding image analysis of liver disease. Dr. Su has received funding from the NIH, VA and DoD. No conflicts with this manuscript. Tony Van, MS: None. George N. Ioannou, MD, MS: None. Monica Tincopa, MD, MSc: None. Boang Liu, PhD: None. Amit Singal, MD: Has received research funding from Gilead and Abbvie. Ji Zhu, PhD: None. Akbar K. Waljee, MD, MSc: None.
Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12
Y1 - 2021/12
N2 - Background: Patients with hepatitis C virus (HCV) frequently remain at risk for cirrhosis after sustained virologic response (SVR). Existing cirrhosis predictive models for HCV do not account for dynamic antiviral treatment status and are limited by fixed laboratory covariates and short follow up time. Advanced fibrosis assessment modalities, such as transient elastography, remain inaccessible in many settings. Improved cirrhosis predictive models are needed. Methods: We developed a laboratory-based model to predict progression of liver disease after SVR. This prediction model used a time-varying covariates Cox model adapted to utilize longitudinal laboratory data and to account for antiretroviral treatment. Individuals were included if they had a history of detectable HCV RNA and at least 2 AST-to-platelet ratio index (APRI) scores available in the national Veterans Health Administration from 2000 to 2015, Observation time extended through January 2019. We excluded individuals with preexisting cirrhosis. Covariates included baseline patient characteristics and 16 time-varying laboratory predictors. SVR, defined as permanently undetectable HCV RNA after antiviral treatment, was modeled as a step function of time. Cirrhosis development was defined as two consecutive APRI scores > 2. We predicted cirrhosis development at 1-, 3-, and 5-years follow-up. Results: In a national sample of HCV patients (n = 182,772) with a mean follow-up of 6.32 years, 42% (n = 76,854) achieved SVR before 2016 and 16.2% (n = 29,566) subsequently developed cirrhosis. The model demonstrated good discrimination for predicting cirrhosis across all combinations of laboratory data windows and cirrhosis prediction intervals. AUROCs ranged from 0.781 to 0.815, with moderate sensitivity 0.703–0.749 and specificity 0.723–0.767. Conclusion: A novel adaptation of time-varying covariates Cox modeling technique using longitudinal laboratory values and dynamic antiviral treatment status accurately predicts cirrhosis development at 1-, 3-, and 5-years among patients with HCV, with and without SVR. It improves upon earlier cirrhosis predictive models and has many potential population-based applications, especially in settings without transient elastography available.
AB - Background: Patients with hepatitis C virus (HCV) frequently remain at risk for cirrhosis after sustained virologic response (SVR). Existing cirrhosis predictive models for HCV do not account for dynamic antiviral treatment status and are limited by fixed laboratory covariates and short follow up time. Advanced fibrosis assessment modalities, such as transient elastography, remain inaccessible in many settings. Improved cirrhosis predictive models are needed. Methods: We developed a laboratory-based model to predict progression of liver disease after SVR. This prediction model used a time-varying covariates Cox model adapted to utilize longitudinal laboratory data and to account for antiretroviral treatment. Individuals were included if they had a history of detectable HCV RNA and at least 2 AST-to-platelet ratio index (APRI) scores available in the national Veterans Health Administration from 2000 to 2015, Observation time extended through January 2019. We excluded individuals with preexisting cirrhosis. Covariates included baseline patient characteristics and 16 time-varying laboratory predictors. SVR, defined as permanently undetectable HCV RNA after antiviral treatment, was modeled as a step function of time. Cirrhosis development was defined as two consecutive APRI scores > 2. We predicted cirrhosis development at 1-, 3-, and 5-years follow-up. Results: In a national sample of HCV patients (n = 182,772) with a mean follow-up of 6.32 years, 42% (n = 76,854) achieved SVR before 2016 and 16.2% (n = 29,566) subsequently developed cirrhosis. The model demonstrated good discrimination for predicting cirrhosis across all combinations of laboratory data windows and cirrhosis prediction intervals. AUROCs ranged from 0.781 to 0.815, with moderate sensitivity 0.703–0.749 and specificity 0.723–0.767. Conclusion: A novel adaptation of time-varying covariates Cox modeling technique using longitudinal laboratory values and dynamic antiviral treatment status accurately predicts cirrhosis development at 1-, 3-, and 5-years among patients with HCV, with and without SVR. It improves upon earlier cirrhosis predictive models and has many potential population-based applications, especially in settings without transient elastography available.
KW - Hepatitis C virus
KW - Prediction
KW - Survival model
KW - Sustained virologic response
KW - Veterans
UR - http://www.scopus.com/inward/record.url?scp=85121104468&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121104468&partnerID=8YFLogxK
U2 - 10.1186/s12911-021-01711-7
DO - 10.1186/s12911-021-01711-7
M3 - Article
C2 - 34903225
AN - SCOPUS:85121104468
SN - 1472-6947
VL - 21
JO - BMC Medical Informatics and Decision Making
JF - BMC Medical Informatics and Decision Making
IS - 1
M1 - 347
ER -