Aims: Achievement of a complete response (CR) after transarterial chemoembolization (TACE) is the most robust predictor of favorable outcomes in patients with hepatocellular carcinoma (HCC). The aim of this study was to identify blood-based biomarkers to predict a sustained CR after TACE using targeted proteomics. Methods: Consecutive patients with HCC who had undergone TACE were drawn from our prospective cohort [training set (n=100) and validation set (n=80)]. Serum samples were obtained before and 6 months after TACE. Treatment responses were evaluated using the modified Response Evaluation Criteria in Solid Tumors (mRECIST). Multiple reaction monitoring-mass spectrometry (MRM-MS) was used to measure marker candidate proteins (MCPs) with regard to their association with the recurrence of HCC and a sustained CR after TACE. Results: In the training set, the MRM-MS assay identified 5 MCPs (MRM-MS marker panel). When this 5-marker panel was combined with the best-performing clinical variables (tumor number, baseline PIVKA, and baseline AFP), the resulting ensemble model had the highest area under the receiver operating curve (AUROC) value in predicting a sustained CR after TACE in the training and validation sets (0.881 and 0.813, respectively). Further, the ensemble model remained an independent predictor of rapid progression (hazard ratio, 2.889; 95% confidence interval, 1.612-5.178; P<0.001) in the entire population by multivariate analysis. Conclusions: Our ensemble model before TACE can predict a sustained CR after TACE. Therefore, this model can aid in determining the best candidates for TACE and the need for adjuvant therapy.