摘要：Screening for possible development of hepatocellular carcinoma (HCC) in patients with chronic hepatitis B (CHB) is essential for risk prediction and early therapy. This study reported a novel model comprised of routine laboratory variables for predicting HCC from CHB. A retrospective study was performed among 463 participants. alpha-fetoprotein (AFP), platelet and alanine aminotransferase (ALT) ratio (APAR) was constructed to differentiate HCC from CHB or non-cancer with area under the receiver operating characteristic curves (AUC) of 0.815 and 0.868 in the training set, 0.831 and 0.861 in the validation set, respectively. In participants with low or normal AFP (<100 ng/mL), the diagnostic efficacy of APAR measured by AUC were 0.817 and 0.809 for predicting HCC from CHB or non-cancer, and at a cutoff of 0.47, the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 89%, 60%, 67% and 86%, respectively. For participants with normal AFP (<20 ng/mL), the AUC of APAR were 0.839 and 0.746 accompanied by a cutoff of 0.36 with sensitivity, specificity, PPV, and NPV of 88%, 69%, 71%, and 87%, respectively. In conclusion, APAR is an effective model for HCC screening especially in those with low even normal serum AFP levels.
