A Logistic Regression Model for Noninvasive Prediction of AFP-Negative Hepatocellular Carcinoma

Abstract

α-Fetoprotein is commonly used in the diagnosis of hepatocellular carcinoma. However, the diagnostic significance of α-fetoprotein has been questioned because a number of patients with hepatocellular carcinoma are α-fetoprotein negative. It is therefore necessary to develop novel noninvasive techniques for the early diagnosis of hepatocellular carcinoma, particularly when α-fetoprotein level is low or negative. The current study aimed to evaluate the diagnostic efficiency of hematological parameters to determine which can act as surrogate markers in α-fetoprotein-negative hepatocellular carcinoma. Therefore, a retrospective study was conducted on a training set recruited from Zhongnan Hospital of Wuhan University-including 171 α-fetoprotein-negative patients with hepatocellular carcinoma and 102 healthy individuals. The results show that mean values of mean platelet volume, red blood cell distribution width, mean platelet volume-PC ratio, neutrophils-lymphocytes ratio, and platelet count-lymphocytes ratio were significantly higher in patients with hepatocellular carcinoma in comparison to the healthy individuals. Most of these parameters showed moderate area under the curve in α-fetoprotein-negative patients with hepatocellular carcinoma, but their sensitivities or specificities were not satisfactory enough. So, we built a logistic regression model combining multiple hematological parameters. This model presented better diagnostic efficiency with area under the curve of 0.922, sensitivity of 83.0%, and specificity of 93.1%. In addition, the 4 validation sets from different hospitals were used to validate the model. They all showed good area under the curve with satisfactory sensitivities or specificities. These data indicate that the logistic regression model combining multiple hematological parameters has better diagnostic efficiency, and they might be helpful for the early diagnosis for α-fetoprotein-negative hepatocellular carcinoma.

Keywords: AFP-negative HCC; diagnostic model; hematological parameters.

Figure 1.

The flowchart of the retrospective study.

Figure 2.

(A) The ROC curve analysis for the diagnostic value of MPV (AUC = 0.652, 95% CI = 0.587-0.717, P < .0001), RDW (AUC = 0.772, 95% CI = 0.718-0.826, P < .0001), MPV/PC ratio (AUC = 0.779, 95% CI = 0.724-0.834, P < .0001), NLR (AUC = 0.800, 95% CI = 0.749-0.852, P < .0001), PLR (AUC = 0.653, 95% CI = 0.589-0.717, P < .0001), and model (AUC = 0.922, 95% CI = 0.892-0.957, P < .0001) in 171 AFP-negative patients with HCC. (B) MPV–PC ratios of AFP-negative patients with HCC at different clinical stages (P = .034). (C) NLR of AFP-negative patients with HCC at different clinical stages (P = .024). (D) MPV of AFP-negative patients with HCC with different Child-Pugh scores (P = .013). (E) RDW values of AFP-negative patients with HCC with different Child-Pugh scores (P = .005). (F) MPV–PC ratios of AFP-negative patients with HCC at different Child-Pugh scores (P = .003). * P < 0.05, ** P < 0.01. AUC indicates area under the curve; HCC, hepatocellular carcinoma; MPV, mean platelet volume; NLR, neutrophils/lymphocytes ratio; RDW, red blood cell distribution width; PLR, platelet count/lymphocytes ratio; AFP, α-fetoprotein; ROC, receiver–operating characteristic.

Figure 3.

The scatter diagrams of the logistic regression model in 4 external validation sets. (A) Eighteen false-negative AFP-negative patients with HCC and 6 false-positive AFP-negative patients with HCC in the cohort of Zhongnan Hospital. (B) Ten false-negative AFP-negative HCC patients and 5 false-positive AFP-negative patients with HCC in the cohort of Tongji Hospital. (C) Seven false-negative AFP-negative patients with HCC and 4 false-positive AFP-negative patients with HCC in the cohort of Union Hospital. (D) Eight false-negative AFP-negative patients with HCC and 5 false-positive AFP-negative patients with HCC in the cohort of Renmin Hospital. HCC indicates Hepatocellular carcinoma; AFP, α-fetoprotein.