Deep learning model for prediction of hepatocellular carcinoma in patients with HBV-related cirrhosis on antiviral therapy

Joon Yeul Nam; Dong Hyun Sinn; Junho Bae; Eun Sun Jang; Jin-Wook Kim; Sook-Hyang Jeong

doi:10.1016/j.jhepr.2020.100175

Deep learning model for prediction of hepatocellular carcinoma in patients with HBV-related cirrhosis on antiviral therapy

JHEP Rep. 2020 Aug 30;2(6):100175. doi: 10.1016/j.jhepr.2020.100175. eCollection 2020 Dec.

Authors

Joon Yeul Nam¹, Dong Hyun Sinn², Junho Bae³, Eun Sun Jang¹, Jin-Wook Kim¹, Sook-Hyang Jeong¹

Affiliations

¹ Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seoul, Republic of Korea.
² Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
³ DEEPNOID Inc., Seoul, Republic of Korea.

Abstract

Background & aims: Personalised risk prediction of the development of hepatocellular carcinoma (HCC) among patients with liver cirrhosis on potent antiviral therapy is important for targeted screening and individualised intervention. This study aimed to develop and validate a new model for risk prediction of HCC development based on deep learning, and to compare it with previously reported risk models.

Methods: A novel deep-learning-based model was developed from a cohort of 424 patients with HBV-related cirrhosis on entecavir therapy with 2 residual blocks, including 7 layers of a neural network, and it was validated using an independent external cohort (n = 316). The deep-learning-based model was compared to 6 previously reported models (platelet, age, and gender-hepatitis B score [PAGE-B], Chinese University HCC score [CU-HCC], HCC-Risk Estimating Score in CHB patients Under Entecavir [HCC-RESCUE], age, diabetes, race, etiology of cirrhosis, sex, and severity HCC score [ADRESS-HCC], modified PAGE-B score [mPAGE], and Toronto HCC risk index [THRI]) using Harrell's concordance (c)-index.

Results: During a median 5.2 yr of follow-up (inter-quartile range 2.8-6.9 yr), 86 patients (20.3%) developed HCC. The deep-learning-based model had a Harrell's c-index of 0.719 in the derivation cohort and 0.782 in the validation cohort. Goodness of fit was confirmed by the Hosmer-Lemeshow test (p >0.05). Moreover, this model in the validation cohort had the highest c-index among the 6 previously reported models: PAGE-B (0.570), CU-HCC (0.548), HCC-RESCUE (0.577), ADRESS-HCC (0.551), mPAGE (0.598), and THRI (0.587) (all p <0.001). The misclassification rate of this model was 23.7% (model accuracy: 76.3%) in the validation group.

Conclusions: The deep-learning-based model had better performance than the previous models for predicting the HCC risk in patients with HBV-related cirrhosis on potent antivirals.

Lay summary: For early detection of hepatocellular carcinoma, it is important to maintain regular surveillance. However, there is currently no standard prediction model for risk stratification that can be used to establish a personalised surveillance strategy. We develop and validate a deep-learning-based model that showed better performance than previous models.

Keywords: ADRESS-HCC, age, diabetes, race, etiology of cirrhosis, sex, and severity HCC score; CU-HCC, Chinese University HCC score; Cirrhosis; Convolutional neural network; HCC, hepatocellular carcinoma; HCC-RESCUE, HCC-Risk Estimating Score in CHB patients Under Entecavir; Hepatitis B virus; Hepatocellular carcinoma; PAGE-B, platelet, age, and gender-hepatitis B score; Prediction model; SMC, Samsung Medical Center; SNUBH, Seoul National University Bundang Hospital; THRI, Toronto HCC risk index; US, ultrasonography; c-index, concordance index; mPAGE-B, modified platelet, age, and gender-hepatitis B score.