Improving prediction of hepatocellular carcinoma in chronic hepatitis B by machine learning: Productive relationship of medicine with computer science.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Abstract:
      Chronic hepatitis B virus (HBV) infection is a global public health problem affecting over 296 million people, with a global prevalence of 3.8%.[1] Current clinical guidelines recommend potent HBV antiviral treatment in CHB patients who are at risk of disease progression to cirrhosis, hepatocellular carcinoma (HCC) and hepatic decompensation.[[2], [4]] Nucleos(t)ide analogues (NA) including entecavir (ETV), tenofovir disoproxil fumarate (TDF), and tenofovir alafenamide are the first-line oral antiviral therapies that effectively suppress HBV replication and decrease the risk of developing HCC in CHB patients.[[5]] Nevertheless, the risk of HCC is not completely abolished in CHB patients receiving NA therapy.[[5], [7]] Therefore, the Hepatology field has been devoted to better predicting the risk of HCC in NA-treated CHB patients using various risk scoring systems,[[8], [10], [12]] aiming to inform strategies on HCC surveillance.[[14]] In recent years, machine-learning and deep-learning models have been popularized in different domains for enhancing the prediction power over traditional statistical regression models. Real-world effectiveness from the Asia Pacific rim liver consortium for HBV risk score for the prediction of hepatocellular carcinoma in chronic hepatitis B patients treated with oral antiviral therapy. Risk score model for the development of hepatocellular carcinoma in treatment-naive patients receiving oral antiviral treatment for chronic hepatitis B. Clin Mol Hepatol. In the original training cohort, a lazy algorithm that predicts all patients will not develop HCC has a high yet unmeaningful accuracy of 92.8% as only 7.2% of patients developed HCC in 5 years. [Extracted from the article]
    • Abstract:
      Copyright of Liver International is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)