Circulating Biomarkers Predict Immunotherapeutic Response in Hepatocellular Carcinoma Using a Machine Learning Method

Abstract

Background: Immune checkpoint inhibitor (ICI) therapy is a promising treatment for cancer. However, the response rate to ICI therapy in hepatocellular carcinoma (HCC) patients is low (approximately 30%). Thus, an approach to predict whether a patient will benefit from ICI therapy is required. This study aimed to design a classifier based on circulating indicators to identify patients suitable for ICI therapy.

Methods: This retrospective study included HCC patients who received immune checkpoint inhibitor therapy between March 2017 and September 2023 at Nanjing Drum Tower Hospital and Jinling Hospital. The levels of the 17 serum biomarkers and baseline patients' characters were assessed to discern meaningful circulating indicators related with survival benefits using random forest. A prognostic model was then constructed to predict survival of patients after treatment.

Results: A total of 369 patients (mean age 56, median follow-up duration 373 days,) were enrolled in this study. Among the 17 circulating biomarkers, 11 were carefully selected to construct a classifier. Receiver operating characteristic (ROC) analysis yielded an area under the curve (AUC) of 0.724. Notably, patients classified into the low-risk group exhibited a more positive prognosis (P = 0.0079; HR, 0.43; 95% CI 0.21-0.87). To enhance efficacy, we incorporated 11 clinical features. The extended model incorporated 12 circulating indicators and 5 clinical features. The AUC of the refined classifier improved to 0.752. Patients in the low-risk group demonstrated superior overall survival compared with those in the high-risk group (P = 0.026; HR 0.39; 95% CI 0.11-1.37).

Conclusion: Circulating biomarkers are useful in predicting therapeutic outcomes and can help in making clinical decisions regarding the use of ICI therapy.

Keywords: hepatocellular carcinoma; immunotherapy; machine learning; predictive model.

Figure 1

Workflow chart of the machine learning method to predict outcomes of HCC patients receiving ICI treatment.

Figure 2

Performance of the model using baseline biomarker level. (A) The importance of selected circulating biomarkers in the random forest model. Importance refers to the reciprocal of the minimal depth, which indicates how much influence the variable has on final decision. (B) C-index of the model for training and test cohorts. (C) Receiver operating characteristic curve (ROC) of the model on test cohort; Kaplan–Meier curves for overall survival of “high risk” and “low risk” groups for training (D) and test (E) set. The “high risk” and “low risk” groups were defined using cut-off value of risk score optimized by training set, the risk scores stand for risk of event occurrence.

Figure 3

Performance of the model using baseline biomarker level and clinical features. (A) The importance of selected circulating biomarkers and clinical features in the random forest model. Importance refers to the reciprocal of the minimal depth, which indicates how much influence the variable has on final decision. (B) C-index of the model for training and test cohorts. (C)Receiver operating characteristic curve (ROC) of the model on test cohort; Kaplan–Meier curves for overall survival of “high risk” and “low risk” groups for training (D) and test (E) set. The “high risk” and “low risk” groups were defined using cut-off value of risk score optimized by training set, the risk scores stand for risk of event occurrence.