This study was conducted to explore the application of age-male-ALBI-platelets (aMAP) score for predicting late recurrence of hepatocellular carcinoma (HCC) following radiofrequency ablation (RFA) and develop an aMAP score based-nomogram to predict prognosis in Chinese population.HCC patients who developed late recurrence following RFA at National Cancer Center (NCC) of China, First Hospital of Shanxi Medical University and Beijing Hospital of Traditional Chinese Medicine from January 2011 to December 2016 were included as a training cohort, and patients who were treated at Affiliated Cancer Hospital of Zhengzhou University between January 2012 and December 2016 were included as an external validation cohort. The optimal cut-off value for aMAP score was determined using X-tile software to discriminate the performance of recurrence-free survival (RFS).A total of 339 eligible patients were included in this study. Patients were grouped into low-risk (aMAP score ≤64.2), medium-risk (64.3 ≤aMAP score ≤68.6) and high-risk (aMAP score ≥68.7) groups by X-tile plots. The prognostic factors that affected RFS were the number of lesions and aMAP score. A nomogram was constructed to predict the RFS with a C-index of 0.793 (95% CI: 0.744-0.842). The time-dependent receiver operating characteristic curves (t-AUCs) of the nomogram to predict 3, 4 and 5-year RFS were 0.808, 0.820 and 0.764, respectively. The model was then tested with data from an external validation cohort. The calibration curve confirmed the optimal agreement between the predicted and observed values.The aMAP score provided a well-discriminated risk stratification and is an independent prognostic factor for the late recurrence of HCC following RFA. The aMAP score-based nomogram could help to strengthen prognosis-based decision making and formulate adjuvant therapeutic and preventive strategies.