Liver cancer prediction in a viral hepatitis cohort: A deep learning approach

• Published in: International journal of cancer Vol. 147; no. 10; pp. 2871 - 2878
• Main Authors: Phan, Dinh‐Van, Chan, Chien‐Lung, Li, Ai‐Hsien Adams, Chien, Ting‐Ying, Nguyen, Van‐Chuc
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 15.11.2020; Wiley Subscription Services, Inc
• Subjects: Adolescent; Adult; Age Factors; Cancer; Child; Child, Preschool; Deep Learning; Female; Hepatitis; Hepatitis, Viral, Human - epidemiology; Hepatitis, Viral, Human - virology; Humans; Infant; Infant, Newborn; Liver cancer; Liver diseases; Liver Neoplasms - epidemiology; Liver Neoplasms - virology; Longitudinal Studies; Male; Medical research; Middle Aged; Neural networks; Neural Networks, Computer; Prevalence; Registries; Retrospective Studies; Taiwan - epidemiology; Young Adult; Taiwan; hepatitis; deep learning; liver cancer
• ISSN: 0020-7136; 1097-0215
• DOI: 10.1002/ijc.33245

Viral hepatitis is the primary cause of liver diseases, among which liver cancer is the leading cause of death from cancer. However, this cancer is often diagnosed in the later stages, which makes treatment difficult or even impossible. This study applied deep learning (DL) models for the early prediction of liver cancer in a hepatitis cohort. In this study, we surveyed 1 million random samples from the National Health Insurance Research Database (NHIRD) to analyze viral hepatitis patients from 2002 to 2010. Then, we used DL models to predict liver cancer cases based on the history of diseases of the hepatitis cohort. Our results revealed the annual prevalence of hepatitis in Taiwan increased from 2002 to 2010, with an average annual percentage change (AAPC) of 5.8% (95% CI: 4.2‐7.4). However, young people (aged 16‐30 years) exhibited a decreasing trend, with an AAPC of −5.6 (95% CI: −8.1 to −2.9). The results of applying DL models showed that the convolution neural network (CNN) model yielded the best performance in terms of predicting liver cancer cases, with an accuracy of 0.980 (AUC: 0.886). In conclusion, this study showed an increasing trend in the annual prevalence of hepatitis, but a decreasing trend in young people from 2002 to 2010 in Taiwan. The CNN model may be applied to predict liver cancer in a hepatitis cohort with high accuracy. What's new? Viral hepatitis is a leading cause of liver cancer worldwide. Many hepatitis patients, however, are not diagnosed with malignancy until advanced stages, greatly reducing their chances of survival. In this study, the authors investigated the ability of a deep learning Convolution Neural Networks (CNN) model to predict liver cancer among hepatitis patients in Taiwan. Analyses reveal an increase in hepatitis prevalence in Taiwan from 2002 to 2010, with the exception of persons under age 30, who exhibited decreasing trends in annual prevalence. The findings further show that the CNN model can predict liver cancer with high accuracy.