Machine learning-based model for predicting tumor recurrence after interventional therapy in HBV-related hepatocellular carcinoma patients with low preoperative platelet-albumin-bilirubin score

Abstract

Introduction: This study aimed to develop a prognostic nomogram for predicting the recurrence-free survival (RFS) of hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC) patients with low preoperative platelet-albumin-bilirubin (PALBI) scores after transarterial chemoembolization (TACE) combined with local ablation treatment.

Methods: We gathered clinical data from 632 HBV-related HCC patients who received the combination treatment at Beijing You'an Hospital, affiliated with Capital Medical University, from January 2014 to January 2020. The patients were divided into two groups based on their PALBI scores: low PALBI group (n=247) and high PALBI group (n=385). The low PALBI group was then divided into two cohorts: training cohort (n=172) and validation cohort (n=75). We utilized eXtreme Gradient Boosting (XGBoost), random survival forest (RSF), and multivariate Cox analysis to pinpoint the risk factors for RFS. Then, we developed a nomogram based on the screened factors and assessed its risk stratification capabilities and predictive performance.

Results: The study finally identified age, aspartate aminotransferase (AST), and prothrombin time activity (PTA) as key predictors. The three variables were included to develop the nomogram for predicting the 1-, 3-, and 5-year RFS of HCC patients. We confirmed the nomogram's ability to effectively discern high and low risk patients, as evidenced by Kaplan-Meier curves. We further corroborated the excellent discrimination, consistency, and clinical utility of the nomogram through assessments using the C-index, area under the curve (AUC), calibration curve, and decision curve analysis (DCA).

Conclusion: Our study successfully constructed a robust nomogram, effectively predicting 1-, 3-, and 5-year RFS for HBV-related HCC patients with low preoperative PALBI scores after TACE combined with local ablation therapy.

Keywords: extreme gradient boosting (Xgboost); hepatitis B virus (HBV); hepatocellular carcinoma (HCC); nomogram; random survival forest (RSF); recurrence-free survival (RFS).

Figure 1

Patient enrollment flowchart. HBV, hepatitis B virus; HCC, hepatocellular carcinoma; TACE, transcatheter arterial chemoembolization; PALBI, platelet-albumin-bilirubin; XGBoost, eXtreme Gradient Boosting; C-index, Harrell’s concordance index; AUC, area under the curve.

Figure 2

Kaplan-Meier curves of high PALBI group and low PALBI group. PALBI, platelet-albumin-bilirubin; RFS, recurrence-free survival.

Figure 3

Variable selection process. (A) Variable selection for RFS using eXtreme Gradient Boosting. (B) Variable selection for RFS using random survival forest. (C) Venn diagram showing the intersection of eXtreme Gradient Boosting and random survival forest. RFS, recurrence-free survival; GGT, gamma glutamyl transpeptidase; PTA, prothrombin time activity; DBIL, direct bilirubin; AST, aspartate aminotransferase; PLT, platelet; Fib, fibrinogen; Lym, lymphocyte; PTR, prothrombin time ratio; INR, international normalized ratio; PT, prothrombin time; PTA, prothrombin time activity.

Figure 4

Nomogram for 1-, 3-, and 5-year RFS prediction in HBV-related HCC patients with low preoperative PALBI score after TACE combined with ablation therapy. Abbreviations: RFS, recurrence-free survival; HBV, hepatitis B virus; HCC, hepatocellular carcinoma; PALBI, platelet-albumin-bilirubin; TACE, transcatheter arterial chemoembolization; AST, aspartate aminotransferase; PTA, prothrombin time activity.

Figure 5

Kaplan-Meier curves of different risk groups stratified by nomogram-derived points in the training cohort. RFS, recurrence-free survival.

Figure 6

Receiver operating characteristic (ROC) curves in the training cohort. AUC, area under the curve.

Figure 7

Calibration curves in the training cohort. (A) Calibration curve of 1-year RFS. (B) Calibration curve of 3-year RFS. (C) Calibration curve of 5-year RFS. RFS, recurrence-free survival.

Figure 8

Decision curve analysis (DCA) in the training cohort. (A) DCA curve of 1-year RFS. (B) DCA curve of 3-year RFS. (C) DCA curve of 5-year RFS. RFS, recurrence-free survival.