Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

Abstract

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (p<0.001) and integrated discrimination improvement (p=0.04). The HALT-C model had a c-statistic of 0.60 (95%CI 0.50-0.70) in the validation cohort and was outperformed by the machine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC.

Racial, Social, and Clinical Determinants of Hepatocellular Carcinoma Surveillance

“…Providers must accurately identify high-risk patients and order surveillance testing, the healthcare system must schedule the tests, and patients must adhere with surveillance recommendations 22–25 . Furthermore, the surveillance process must be repeated every 6 months to be effective.…”

A genomic and clinical prognostic index for hepatitis C-related early-stage cirrhosis that predicts clinical deterioration

“…Several clinical prognostic indicators have been proposed to discriminate late-stage cirrhosis from early-stage cirrhosis 28 or to discriminate progressive cirrhosis from less advanced or no fibrosis with hazard ratios smaller than 2.0. 29–31 However, prognostic prediction within established but early-stage cirrhosis is more critical because this specific disease stage comprises the majority of the target patient population indicated for regular follow-up and HCC surveillance as recommended in the clinical practice guidelines. Recently emerging non-invasive blood test- or elastography-based methods of liver fibrosis detection are not sensitive enough to classify early-stage cirrhosis patients into prognostic subgroups.…”

A Variant in PNPLA3 Associated With Fibrosis Progression but not Hepatocellular Carcinoma in Patients With Hepatitis C Virus Infection

“…However, predictive models with clinical variables alone appear to only partially account for differences in risk [5]. Family history among first-degree relatives is a significant risk factor for cirrhosis and HCC development, highlighting the potential importance of genetic predisposition in these processes [6].…”