Efficacy of radiofrequency ablation for solitary hepatocellular carcinoma 5 cm or smaller and construction of prognostic model by machine learning: a retrospective cohort study

Abstract

Abstract Background The effectiveness of Radiofrequency Ablation (RFA) in improving long-term survival outcomes for patients with solitary hepatocellular carcinoma (HCC) of 5 cm or less remains uncertain. This study was designed to elucidate the impact of RFA therapy on the survival outcomes of these patients and to construct a prognostic model for patients following RFA. Methods This study was performed using the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2017, focusing on patients diagnosed with solitary HCC ≤ 5 cm. We compared the overall survival (OS) and cancer-specific survival (CSS) rates of these patients with those who received hepatectomy, radiotherapy, chemotherapy, or were part of a blank control group. To enhance the reliability of our findings, we employed Stabilized Inverse Probability Treatment Weighting (sIPTW) and stratified analyses. Additionally, we conducted a Cox regression analysis to identify prognostic factors. Extreme Gradient Boosting (XGBoost) models were developed to predict 1-year, 3-year, and 5-year CSS. The XGBoost models were evaluated via ROC curves, calibration plots, decision curve analysis (DCA) curves and so on. Results Regardless of whether the data were unadjusted or adjusted using sIPTW, the RFA group exhibited higher 5-year OS (46.7%) and CSS (58.9%) rates compared to the radiotherapy (27.1%/35.8%), chemotherapy (32.9%/43.7%), and blank control groups (18.6%/30.7%), while being lower than the hepatectomy group (69.4%/78.9%). Stratified analysis based on age and cirrhosis status revealed that RFA and hepatectomy yielded similar OS and CSS outcomes for patients with cirrhosis and aged over 65 years. Age, race, marital status, grade, cirrhosis, tumor size, and AFP levels were selected to build the XGBoost models based on the training cohort. The area under the curve (AUC) of 1, 3, and 5 years in the validation cohort were 0.88, 0.81, 0.79. Calibration plots further demonstrated the consistency between predicted and actual values in both training and validation cohorts. Conclusion RFA can enhance the survival prospects of patients diagnosed with solitary HCC ≤ 5 cm. In certain clinical scenarios, RFA achieve survival outcomes comparable to those of hepatectomy. The XGBoost models developed in this study performed admirably in predicting the CSS of patients with solitary HCC tumors smaller than 5cm following RFA.