Chronological change in serum albumin as a prognostic factor in patients with hepatocellular carcinoma treated with lenvatinib: proposal of albumin simplified grading based on the modified albumin-bilirubin score (ALBS grade)

Background The albumin-bilirubin (ALBI) score and the modified ALBI (mALBI) grade are known useful prognostic factors for patients with hepatocellular carcinoma (HCC) treated with lenvatinib (LEN-HCC). However, the ALBI score requires complicated logarithmic calculations. Therefore, we attempted to create a simplified score. Methods We developed the albumin simplified (ALBS) grade that corresponded to mALBI using the data of 5985 newly developed HCC and examined the usefulness of this grading system for the prediction of the prognosis of 678 patients with LEN-HCC. Results The analysis using Cox proportional hazard models revealed that the overall survival of patients with LEN-HCC was not correlated with the total bilirubin but albumin (Alb), which means that the prediction with Alb alone was logical. The ALBS grade cutoffs that corresponded to mALBI grade 1, 2a, 2b, and 3 were Alb >= 4.0 g/dL, 4.0 g/dL > Alb >= 3.5 g/dL, 3.5 g/dL > Alb >= 2.8 g/dL, and Alb < 2.8 g/dL, respectively. The stratification ability of the ALBS grade for LEN-HCC was good. The Akaike information criterion (AIC) and c-index were comparable with those of mALBI (AIC 4096.3 vs. 4090.7, c-index 0.765 vs. 0.778). The prognosis of LEN-HCC was stratified by the ALBS grade at 1 month after starting LEN, and patients with ALBS grade 1/2a demonstrated better survival than patients with ALBS grade 2b/3 regardless of the ALBS grade before treatment. Conclusion The ALBS grade is easy to calculate and is useful for the prediction of the prognosis of LEN-HCC.