Prognostic factors for long-term outcome in bifocal hepatocellular carcinoma after resection

Development of a machine learning-based model to predict prognosis of alpha-fetoprotein-positive hepatocellular carcinoma

BACKGROUND

Patients with alpha-fetoprotein (AFP)-positive hepatocellular carcinoma (HCC) have aggressive biological behavior and poor prognosis. Therefore, survival time is one of the greatest concerns for patients with AFP-positive HCC. This study aimed to demonstrate the utilization of six machine learning (ML)-based prognostic models to predict overall survival of patients with AFP-positive HCC.

METHODS

Data on patients with AFP-positive HCC were extracted from the Surveillance, Epidemiology, and End Results database. Six ML algorithms (extreme gradient boosting [XGBoost], logistic regression [LR], support vector machine [SVM], random forest [RF], K-nearest neighbor [KNN], and decision tree [ID3]) were used to develop the prognostic models of patients with AFP-positive HCC at one year, three years, and five years. Area under the receiver operating characteristic curve (AUC), confusion matrix, calibration curves, and decision curve analysis (DCA) were used to evaluate the model.

RESULTS

A total of 2,038 patients with AFP-positive HCC were included for analysis. The 1-, 3-, and 5-year overall survival rates were 60.7%, 28.9%, and 14.3%, respectively. Seventeen features regarding demographics and clinicopathology were included in six ML algorithms to generate a prognostic model. The XGBoost model showed the best performance in predicting survival at 1-year (train set: AUC = 0.771; test set: AUC = 0.782), 3-year (train set: AUC = 0.763; test set: AUC = 0.749) and 5-year (train set: AUC = 0.807; test set: AUC = 0.740). Furthermore, for 1-, 3-, and 5-year survival prediction, the accuracy in the training and test sets was 0.709 and 0.726, 0.721 and 0.726, and 0.778 and 0.784 for the XGBoost model, respectively. Calibration curves and DCA exhibited good predictive performance as well.

CONCLUSIONS

The XGBoost model exhibited good predictive performance, which may provide physicians with an effective tool for early medical intervention and improve the survival of patients.

Collateral vessels on preoperative enhanced computed tomography for predicting pathological grade of clear cell renal cell carcinoma: A retrospective study

OBJECTIVES

To retrospectively evaluate the association between the presence of collateral vessels and grade of clear cell renal cell carcinoma (ccRCC) and whether the presence of collateral vessels could serve as a predictor to differentiate high- and low-grade ccRCC.

MATERIALS AND METHODS

From May 2018 to September 2022, a total of 160 ccRCC patients with pathological diagnosis were enrolled in this study. Patients were divided into a high-grade group and a low-grade group according to World Health Organization/International Society of Urological Pathology (WHO/ISUP) grading system. The significant variables were extracted based on the univariate analyses using Student t test, Mann-Whitney U test, Chi-square test or Fisher's exact test. Multivariate logistic regression analyses were performed to determine independent factors among extracted variables. We calculated the sensitivity, specificity and their 95% confidence intervals (CI) of collateral vessels for predicting high WHO/ISUP grade to quantify its predictive performance. Furthermore, to investigate the additional predictive contribution of collateral vessels, a primary model and a control model were constructed to predict WHO/ISUP grade. The primary model included all extracted significant variables and the control model included significant variables except collateral vessels.

RESULTS

The proportion of ccRCC patients with collateral vessels was significantly larger in high-grade ccRCC than those in low-grade ccRCC (87.5 % vs. 26.8 %, P < 0.001). Multivariate logistic regression analyses showed that the presence of collateral vessels was an independent predictor for high WHO/ISUP grade (P < 0.001). The sensitivity and specificity of the presence of collateral vessels for differentiating high- and low-grade ccRCC were 87.5 % (95 % CI 0.753-0.941) and 73.2 % (95 % CI 0.643-0.806) respectively. Including collateral vessels in predictive model improves predictive performance for WHO/ISUP grade, increasing the area under the curve (AUC) value from 0.889 to 0.914.

CONCLUSION

The presence of collateral vessels has high sensitivity and specificity for differentiating high- and low-grade ccRCC and can improve the predictive performance for high WHO/ISUP grade.

Microvascular invasion-negative hepatocellular carcinoma: Prognostic value of qualitative and quantitative Gd-EOB-DTPA MRI analysis

OBJECTIVES

The purpose of this study was to establish a model for predicting the prognosis of patients with microvascular invasion (MVI)-negative hepatocellular carcinoma (HCC) based on qualitative and quantitative analyses of Gd-EOB-DTPA magnetic resonance imaging (MRI).

MATERIALS AND METHODS

Consecutive patients with MVI-negative HCC who underwent preoperative Gd-EOB-DTPA MRI between January 2015 and December 2019 were retrospectively enrolled.In total, 122 patients were randomly assigned to the training and validation groups at a ratio of 7:3. Univariate and multivariate logistic regression analyses were performed to identify significant clinical parameters and MRI features, including quantitative and qualitative parameters associated with prognosis, which were incorporated into a predictive nomogram. The end-point of this study was recurrence-free survival. Outcomes were compared between groups using the Kaplan-Meier method with the log-rank test.

RESULTS

During a median follow-up period of 58.86 months, 38 patients (31.15 %) experienced recurrence. Multivariate analysis revealed that lower relative enhancement ratio (RER), hepatobiliary phase hypointensity without arterial phase hyperenhancement, Liver Imaging Reporting and Data System category, mild-moderate T2 hyperintensity, and higher aspartate aminotransferase levels were risk factors associated with prognosis and then incorporated into the prognostic model. C-indices for training and validation groups were 0.732 and 0.692, respectively. The most appropriate cut-off value for RER was 1.197. Patients with RER ≤ 1.197 had significantly higher postoperative recurrence rates than those with RER > 1.197 (p = 0.004).

CONCLUSION

The model integrating qualitative and quantitative imaging parameters and clinical parameters satisfactorily predicted the prognosis of patients with MVI-negative HCC.

Preoperative prediction of microvascular invasion in hepatocellular carcinoma using ultrasound features including elasticity

BACKGROUND

Microvascular invasion (MVI) is an important predictor of poor prognosis in patients with hepatocellular carcinoma (HCC). Accurate preoperative prediction of MVI in HCC would provide useful information to guide the choice of therapeutic strategy. Shear wave elastography (SWE) plays an important role in hepatic imaging, but its value in the preoperative prediction of MVI in HCC has not yet been proven.

AIM

To explore the value of conventional ultrasound features and SWE in the preoperative prediction of MVI in HCC.

METHODS

Patients with a postoperative pathological diagnosis of HCC and a definite diagnosis of MVI were enrolled in this study. Conventional ultrasound features and SWE features such as maximal elasticity (Emax) of HCCs and Emax of the periphery of HCCs were acquired before surgery. These features were compared between MVI-positive HCCs and MVI-negative HCCs and between mild MVI HCCs and severe MVI HCCs.

RESULTS

This study included 86 MVI-negative HCCs and 102 MVI-positive HCCs, including 54 with mild MVI and 48 with severe MVI. Maximal tumor diameters, surrounding liver tissue, color Doppler flow, Emax of HCCs, and Emax of the periphery of HCCs were significantly different between MVI-positive HCCs and MVI-negative HCCs. In addition, Emax of the periphery of HCCs was significantly different between mild MVI HCCs and severe MVI HCCs. Higher Emax of the periphery of HCCs and larger maximal diameters were independent risk factors for MVI, with odds ratios of 2.820 and 1.021, respectively.

CONCLUSION

HCC size and stiffness of the periphery of HCC are useful ultrasound criteria for predicting positive MVI. Preoperative ultrasound and SWE can provide useful information for the prediction of MVI in HCCs.