The value of clinical indicators combined with imaging tumor burden score in predicting microvascular invasion of hepatocellular carcinoma.

To explore the value of a new clinical prediction model combined serological indicators and tumor burden score (TBS) in predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC) patients. This study retrospectively analyzed a total of 605 patients who underwent liver tumor resection at our hospital from January 2021 to December 2023. The required clinical data before surgery were collected from the electronic medical record system. All patients were randomly divided into a training group and a validation group according to the ratio of 7 : 3. Univariate and multivariate analyses were conducted to identify factors associated with MVI. Based on the combined factors, a nomogram for predicting MVI was constructed and its diagnostic performance was evaluated. There were 123 (20.3%) female patients and 482 (79.7%) male patients were enrolled, with an average age of 59 years. There were 182 (30.1%) patients with positive MVI and 423 (69.9%) patients with negative MVI. On multivariate logistic analysis, prealbumin (0.993 [0.986, 1.000]), AFP (0.993 [0.987, 1.000]), PIVKA-II (1.000 [1.000, 1.000]) were independently associated with MVI. The nomogram constructed based on the aforementioned variables and TBS exhibited area under the curve (AUC) of 0.804 and 0.742 in the training group and a validation group, respectively. The calibration curves in both training group and a validation group showed good fit, and the decision curve analysis revealed a net benefit across a wide range of threshold probabilities. The newly developed nomogram was an independent biomarker for predict MVI, which might take precision medicine one step further.