Dynamic prediction of risk of liver-related outcomes in chronic hepatitis C using routinely collected data

Accurate prediction of HCC risk after SVR in patients with hepatitis C cirrhosis based on longitudinal data

BACKGROUND

Most existing predictive models of hepatocellular carcinoma (HCC) risk after sustained virologic response (SVR) are built on data collected at baseline and therefore have limited accuracy. The current study aimed to construct an accurate predictive model incorporating longitudinal data using a novel modeling strategy. The predictive performance of the longitudinal model was also compared with a baseline model.

METHODS

A total of 400 patients with HCV-related cirrhosis who achieved SVR with direct-acting antivirals (DAA) were enrolled in the study. Patients were randomly divided into a training set (70%) and a validation set (30%). Informative features were extracted from the longitudinal variables and then put into the random survival forest (RSF) to develop the longitudinal model. A baseline model including the same variables was built for comparison.

RESULTS

During a median follow-up time of approximately 5 years, 25 patients (8.9%) in the training set and 11 patients (9.2%) in the validation set developed HCC. The areas under the receiver-operating characteristics curves (AUROC) for the longitudinal model were 0.9507 (0.8838-0.9997), 0.8767 (0.6972,0.9918), and 0.8307 (0.6941,0.9993) for 1-, 2- and 3-year risk prediction, respectively. The brier scores of the longitudinal model were also relatively low for the 1-, 2- and 3-year risk prediction (0.0283, 0.0561, and 0.0501, respectively). In contrast, the baseline model only achieved mediocre AUROCs of around 0.6 (0.6113, 0.6213, and 0.6480, respectively).

CONCLUSIONS

Our longitudinal model yielded accurate predictions of HCC risk in patients with HCV-relate cirrhosis, outperforming the baseline model. Our model can provide patients with valuable prognosis information and guide the intensity of surveillance in clinical practice.

Development and Validation of a Model for Prediction of End-Stage Liver Disease in People With HIV

BACKGROUND

End-stage liver disease (ESLD) is a leading cause of non-AIDS-related death among people with HIV (PWH). Factors that increase the progression of liver disease include comorbidities and HIV-specific factors, but we currently lack a tool to apply this evidence into clinical practice.

METHODS

We developed and validated a risk prediction model for ESLD among PWH who received care in 12 cohorts of the North American AIDS Cohort Collaboration on Research and Design between 2000 and 2016 and had fibrosis-4 index > 1.45. The first occurrence of ascites, variceal bleed, spontaneous bacterial peritonitis, or hepatic encephalopathy was verified by standardized medical record review. The Bayesian model averaging was used to select predictors among biomarkers and diagnoses and the Harrell C statistic to assess model discrimination.

RESULTS

Among 13,787 PWH in the training set, 82% were men and 54% were Black with a mean age of 48 years. Three hundred ninety ESLD events occurred over a mean 5.4 years. Among the ESLD cases, 52% had hepatitis C virus, 15% hepatitis B virus, and 31% alcohol use disorder. Twelve factors together predicted ESLD risk moderately well (C statistic 0.79, 95% confidence interval: 0.76 to 0.81): age, sex, race/ethnicity, chronic hepatitis B or C, and routinely collected laboratory values reflecting hepatic impairment (serum albumin, aspartate aminotransferase, total bilirubin, and platelets) and lipid metabolism (triglycerides, high-density lipoprotein, and total cholesterol). Our model performed well in the test set (C statistic 0.81, 95% confidence interval: 0.76 to 0.86).

CONCLUSION

This model of readily accessible clinical parameters predicted ESLD in a large diverse population of PWH.

Harnessing repeated measurements of predictor variables for clinical risk prediction: a review of existing methods

BACKGROUND

Clinical prediction models (CPMs) predict the risk of health outcomes for individual patients. The majority of existing CPMs only harness cross-sectional patient information. Incorporating repeated measurements, such as those stored in electronic health records, into CPMs may provide an opportunity to enhance their performance. However, the number and complexity of methodological approaches available could make it difficult for researchers to explore this opportunity. Our objective was to review the literature and summarise existing approaches for harnessing repeated measurements of predictor variables in CPMs, primarily to make this field more accessible for applied researchers.

METHODS

MEDLINE, Embase and Web of Science were searched for articles reporting the development of a multivariable CPM for individual-level prediction of future binary or time-to-event outcomes and modelling repeated measurements of at least one predictor. Information was extracted on the following: the methodology used, its specific aim, reported advantages and limitations, and software available to apply the method.

RESULTS

The search revealed 217 relevant articles. Seven methodological frameworks were identified: time-dependent covariate modelling, generalised estimating equations, landmark analysis, two-stage modelling, joint-modelling, trajectory classification and machine learning. Each of these frameworks satisfies at least one of three aims: to better represent the predictor-outcome relationship over time, to infer a covariate value at a pre-specified time and to account for the effect of covariate change.

CONCLUSIONS

The applicability of identified methods depends on the motivation for including longitudinal information and the method's compatibility with the clinical context and available patient data, for both model development and risk estimation in practice.

The Road to Hepatitis C Virus Cure: Practical Considerations from a Health System's Perspective

Hepatitis C virus infection remains a significant global health problem. Many individuals are unaware of their infection or disease stage. Innovations in care that promote rapid and easy identification of at-risk populations for screening, comprehensive diagnostic screening, and triage to curative direct-acting antiviral medications will accelerate efforts to eradicate hepatitis C.

Machine learning models to predict disease progression among veterans with hepatitis C virus

Background

Machine learning (ML) algorithms provide effective ways to build prediction models using longitudinal information given their capacity to incorporate numerous predictor variables without compromising the accuracy of the risk prediction. Clinical risk prediction models in chronic hepatitis C virus (CHC) can be challenging due to non-linear nature of disease progression. We developed and compared two ML algorithms to predict cirrhosis development in a large CHC-infected cohort using longitudinal data.

Methods and findings

We used national Veterans Health Administration (VHA) data to identify CHC patients in care between 2000–2016. The primary outcome was cirrhosis development ascertained by two consecutive aspartate aminotransferase (AST)-to-platelet ratio indexes (APRIs) > 2 after time zero given the infrequency of liver biopsy in clinical practice and that APRI is a validated non-invasive biomarker of fibrosis in CHC. We excluded those with initial APRI > 2 or pre-existing diagnosis of cirrhosis, hepatocellular carcinoma or hepatic decompensation. Enrollment was defined as the date of the first APRI. Time zero was defined as 2 years after enrollment. Cross-sectional (CS) models used predictors at or closest before time zero as a comparison. Longitudinal models used CS predictors plus longitudinal summary variables (maximum, minimum, maximum of slope, minimum of slope and total variation) between enrollment and time zero. Covariates included demographics, labs, and body mass index. Model performance was evaluated using concordance and area under the receiver operating curve (AuROC). A total of 72,683 individuals with CHC were analyzed with the cohort having a mean age of 52.8, 96.8% male and 53% white. There are 11,616 individuals (16%) who met the primary outcome over a mean follow-up of 7 years. We found superior predictive performance for the longitudinal Cox model compared to the CS Cox model (concordance 0.764 vs 0.746), and for the longitudinal boosted-survival-tree model compared to the linear Cox model (concordance 0.774 vs 0.764). The accuracy of the longitudinal models at 1,3,5 years after time zero also showed superior performance compared to the CS model, based on AuROC.

Conclusions

Boosted-survival-tree based models using longitudinal information are statistically superior to cross-sectional or linear models for predicting development of cirrhosis in CHC, though all four models were highly accurate. Similar statistical methods could be applied to predict outcomes in other non-linear chronic disease states.

Assessing risk of fibrosis progression and liver-related clinical outcomes among patients with both early stage and advanced chronic hepatitis C

OBJECTIVE

Assessing risk of adverse outcomes among patients with chronic liver disease has been challenging due to non-linear disease progression. We previously developed accurate prediction models for fibrosis progression and clinical outcomes among patients with advanced chronic hepatitis C (CHC). The primary aim of this study was to validate fibrosis progression and clinical outcomes models among a heterogeneous patient cohort.

DESIGN

Adults with CHC with ≥3 years follow-up and without hepatic decompensation, hepatocellular carcinoma (HCC), liver transplant (LT), HBV or HIV co-infection at presentation were analyzed (N = 1007). Outcomes included: 1) fibrosis progression 2) hepatic decompensation 3) HCC and 4) LT-free survival. Predictors included longitudinal clinical and laboratory data. Machine learning methods were used to predict outcomes in 1 and 3 years.

RESULTS

The external cohort had a median age of 49.4 years (IQR 44.3-54.3); 61% were male, 80% white, and 79% had genotype 1. At presentation, 73% were treatment naïve and 31% had cirrhosis. Fibrosis progression occurred in 34% over a median of 4.9 years (IQR 3.2-7.6). Clinical outcomes occurred in 22% over a median of 4.4 years (IQR 3.2-7.6). Model performance for fibrosis progression was limited due to small sample size. The area under the receiver operating characteristic curve (AUROC) for 1 and 3-year risk of clinical outcomes was 0.78 (95% CI 0.73-0.83) and 0.76 (95% CI 0.69-0.81).

CONCLUSION

Accurate assessments for risk of clinical outcomes can be obtained using routinely collected data across a heterogeneous cohort of patients with CHC. These methods can be applied to predict risk of progression in other chronic liver diseases.