Assessment of a Deep Learning Model to Predict Hepatocellular Carcinoma in Patients With Hepatitis C Cirrhosis

HCV eradication by antiviral treatment reduces but does not eliminate HCC risk. Patients with established cirrhosis require HCC surveillance "indefinitely" after sustained virologic response (SVR) because they appear to have a high risk of HCC even many years after SVR. Patients without established or known cirrhosis may still require surveillance after SVR if they have a sufficiently high HCC risk. In all patients who achieve SVR, the key question is how we can reliably estimate HCC risk, and the change in HCC risk over time, to determine whether the patient might benefit from HCC surveillance. HCC risk is one of the most important factors that should inform decisions of whether and how to screen for HCC. Promising strategies for estimating HCC risk include simplified scoring systems (such as fibrosis-4), liver elastography and multivariable HCC risk calculators. Such tools may enable risk stratification and individualised, risk-based surveillance strategies ("precision HCC screening") in the future.

show abstract

“…A deep learning, recurrent neural network model predicting HCC in patients with HCV was recently published. 37…”

Section: "Deep Learning" Hcc Prediction Modelsmentioning

confidence: 99%

HCC surveillance after SVR in patients with F3/F4 fibrosis

Ioannou

2021

Journal of Hepatology

Self Cite

122

View full text Add to dashboard Cite

show abstract

“…In particular, SVR patients could be classified as having low or moderate HCC risk according to these simple biological parameters. Similarly, deep learning models were recently applied to data in the VA database [ 49 ]. In this context, use of a recurrent neural network (RNN) outperformed conventional models in identifying patients with the highest HCC risk regardless of their SVR status.…”

Section: Identification Of Patients Infected With Hcv With Higher mentioning

confidence: 99%

Stratification of Hepatocellular Carcinoma Risk Following HCV Eradication or HBV Control

Nahon

Quang

Ganne-Carrié

2021

JCM

View full text Add to dashboard Cite

Hepatocellular carcinoma (HCC) incidence has dramatically decreased in patients infected with HCV and HBV due to the widespread use of highly effective antiviral agents. Nevertheless, a substantial proportion of patients with advanced fibrosis or cirrhosis following HCV clearance of in case of HBV control whatever the stage of fibrosis remains at risk of liver cancer development. Cancer predictors in these virus-free patients include routine parameters estimating coexisting comorbidities, persisting liver inflammation or function impairment, and results of non-invasive tests which can be easily combined into HCC risk scoring systems. The latter enables stratification according to various liver cancer incidences and allocation of patients into low, intermediate or high HCC risk probability groups. All international guidelines endorse lifelong surveillance of these patients using semi-annual ultrasound, with known sensibility issues. Refining HCC prediction in this growing population ultimately will trigger personalized management using more effective surveillance tools such as contrast-enhanced imaging techniques or circulating biomarkers while taking into account cost-effectiveness parameters.

show abstract

“…Traditional analysis depends on expert‐defined phenotyping and ad hoc feature engineering 42 ; however, the generalizability of results is often limited. DL models have been successfully applied to healthcare to predict clinical events, disease classification, and EHR data augmentation, 43 because of the better performance of DL and the capability to analyze complex datasets. The selected applications of AI using EHR are listed in Table 4.…”

Section: Artificial Intelligence In Electronic Health Recordsmentioning

confidence: 99%

“…Inannou et al . used the DL RNN models to analyze raw longitudinal data from EHR and investigated the risk of HCC among 48 151 patients with chronic hepatitis C‐related cirrhosis with at least 3‐year follow‐up 43 . They found that RNN models with longitudinal data (AUROC: 0.759) outperforms logistic regression model using cross‐sectional or longitudinal inputs (AUROC: 0.68–0.69).…”

Section: Artificial Intelligence In Electronic Health Recordsmentioning

confidence: 99%

Artificial intelligence in precision medicine in hepatology

Kao

2021

J of Gastro and Hepatol

View full text Add to dashboard Cite

The advancement of investigation tools and electronic health records (EHR) enables a paradigm shift from guideline‐specific therapy toward patient‐specific precision medicine. The multiparametric and large detailed information necessitates novel analyses to explore the insight of diseases and to aid the diagnosis, monitoring, and outcome prediction. Artificial intelligence (AI), machine learning, and deep learning (DL) provide various models of supervised, or unsupervised algorithms, and sophisticated neural networks to generate predictive models more precisely than conventional ones. The data, application tasks, and algorithms are three key components in AI. Various data formats are available in daily clinical practice of hepatology, including radiological imaging, EHR, liver pathology, data from wearable devices, and multi‐omics measurements. The images of abdominal ultrasonography, computed tomography, and magnetic resonance imaging can be used to predict liver fibrosis, cirrhosis, non‐alcoholic fatty liver disease (NAFLD), and differentiation of benign tumors from hepatocellular carcinoma (HCC). Using EHR, the AI algorithms help predict the diagnosis and outcomes of liver cirrhosis, HCC, NAFLD, portal hypertension, varices, liver transplantation, and acute liver failure. AI helps to predict severity and patterns of fibrosis, steatosis, activity of NAFLD, and survival of HCC by using pathological data. Despite of these high potentials of AI application, data preparation, collection, quality, labeling, and sampling biases of data are major concerns. The selection, evaluation, and validation of algorithms, as well as real‐world application of these AI models, are also challenging. Nevertheless, AI opens the new era of precision medicine in hepatology, which will change our future practice.

show abstract

Assessment of a Deep Learning Model to Predict Hepatocellular Carcinoma in Patients With Hepatitis C Cirrhosis

Cited by 116 publications

References 51 publications

HCC surveillance after SVR in patients with F3/F4 fibrosis

HCC surveillance after SVR in patients with F3/F4 fibrosis

Stratification of Hepatocellular Carcinoma Risk Following HCV Eradication or HBV Control

Artificial intelligence in precision medicine in hepatology

Contact Info

Product

Resources

About