The fibrosis-4 index, albumin-bilirubin score and neutrophil-lymphocyte ratio are all prognostic markers in patients with heart failure. Recently, the FAN score, which includes all 3 of these markers, was developed as a useful risk stratification tool in patients with cancer. However, its cut-off values have not been validated for heart failure. We aimed to investigate the optimal cut-off and prognostic values of the FAN score in patients with heart failure. We analyzed 669 consecutive patients hospitalized with heart failure (age, 75.8 ± 11.3 years). Their median values of the fibrosis-4 index, albumin-bilirubin score, and neutrophil-lymphocyte ratio at discharge were 2.12, −2.25, and 2.41, respectively. The FAN score for heart failure (HF-FAN score) was calculated using these median values. The primary outcome was a composite of all-cause death and heart failure rehospitalization. Patients were divided into 4 groups according to HF-FAN scores of 0 (n = 112), 1 (n = 231), 2 (n = 242) and 3 (n = 84). Patients with HF-FAN scores of 3 were older, had higher brain natriuretic peptide levels, and larger inferior vena cava diameters. Kaplan-Meier analysis showed a direct correlation between higher HF-FAN scores and occurrence of the primary endpoint (log-rank P < 0.001). Cox proportional hazard analysis revealed a higher HF-FAN score was significantly associated with a worse prognosis even after adjustment for possible prognostic factors. Changing from the FAN score to HF-FAN score provided significant continuous net reclassification improvement. In conclusion, the HF-FAN score at discharge was useful for risk stratification in patients hospitalized with heart failure. The HF-FAN score might be more suitable for patients with heart failure than the FAN score.