Nomograms for Preoperative Prediction of Microvascular Invasion and Lymph Node Metastasis Risk in Hepatocellular Carcinoma

Abstract

Background: To develop and validate accurate preoperative nomograms to predict microvascular invasion (MVI) and lymph node metastasis (LNM) in hepatocellular carcinoma. Methods: A total of 302 patients with resected HCC were divided into a training set (n=202) in an earlier period and a validation set (n=100) thereafter. Risk factors for MVI and LNM were assessed based on logistic regression. The blood signatures were established with the least absolute shrinkage and selection operator algorithm. Nomograms were constructed by combining risk factors and blood signatures. Performance was evaluated in the training set and validated in the validation set. The clinical values of the nomograms were measured by decision curve analysis. Findings: The risk factors for MVI were hepatitis B virus history and three CT imaging features, namely, tumor number, size and encapsulation, while only tumor number and size were associated with LNM. The blood signatures achieved favorable prediction efficacy with C-indexes of 0.725 and 0.709 in MVI and LNM nomograms. The nomograms incorporating the risk factors and the blood signatures also achieved good C-indexes of 0.792 and 0.771 in predicting MVI in the training and validation sets, while 0.784 and 0.844 of the LNM nomogram. Calibration curves demonstrated good fit. The decision curves indicated significant clinical usefulness. Interpretation: Our novel validated nomograms for HCC patients are noninvasive preoperative prediction tools that can effectively predict the individualized risk of MVI and LNM, and this predictive power can help doctors formulate rational individual treatments. Funding Statement: This work was supported in part by the National Natural Science Foundation of China (No. 81572407, 81602112, 81672405, 81702404 ); Key project of Natural Science Foundation of Guangdong Province, China (No. 4210016041); Science and Technology Program of Guangdong Province, China (No.2015A030313096, 2016A030313184, 2017A030313536); Natural Science Foundation of Guangzhou, China (No. 4250016043). Declaration of Interests: The authors declare that they have no conflicts of interest. Ethics Approval Statement: The retrospective study with anonymous data was approved by the institutional Ethics Committee of Sun Yat-sen Memorial Hospital, Sun Yat-sen University.