A Novel Hematological Nomogram for Preoperative Prediction of Microvascular Invasion Risk in Patients with Hepatocellular Carcinoma

Background: Microvascular invasion(MVI) plays an important role in tumor progression. The aim of this study is to establish and validate an effective hematological nomogram for MVI prediction in hepatocellular carcinoma. Methods: We established a nomogram in a primary cohort that include 1306 patients with clinicopathologically diagnosed with HCC. A validation cohort contained 563 continuous patients. Univariate and multivariate Cox hazard analysis was used to identified the factors that included both clinicopathologic factors and hemostatic factors. We tested the accuracy of the nomograms by discrimination and calibration, and then plotted decision curves to assess the benefits of the nomogram-assisted decisions in a clinical context. The discrimination ability of the nomogram was assessed by AUC. Results: The AUC in the primary and validation cohort were 0.6810 and 0.7021. The hosmer-leme show test showed good point estimate associated P value between predicted and observed risk across the deciles. Moreover, the calibration performance the nomogram risk scores in each decile of the primary cohort was within 5 percentage points of the mean predicted risk score, and in the validation cohort the observed risk in 90% decile was within 5 percentage points of the mean predicted risk score. Conclusions: A noninvasive and easy-to-use nomogram was established to predicting preoperative MVI in HCC. Funding Statement: This work was supported by grants from the Guangzhou science and technology planning project (201604016070). Declaration of Interests: The authors have declared that no competing interest exists. Ethics Approval Statement: The study was approved by the ethics committees in Sun Yat-sen University Cancer Center (SYSUCC, Guangdong, China).