Incorporation of liver chemistry score in predicting survival of liver-involved advanced gastric cancer patients who received palliative chemotherapy

Background Gastric cancer liver metastasis (GCLM) patients usually accompany by abnormal serum liver function tests (LFTs) more or less; however, the prognostic value of LFTs is not fully understood. This study aimed to develop a liver chemistry score (LCS) based on LFTs and incorporate it into prognosis determination for GCLM patients who received palliative chemotherapy. Methods Data were derived from hospitalized GCLM patients in two general hospitals in China. LCS was generated based on the results of LFTs by LASSO regression. Cutoff value of the score was determined by restricted cubic spline. The score was then incorporated into Cox regression analysis to construct a predictive nomogram; the model was then evaluated internally and externally by AUC of time-dependent receiver operating characteristic curves (ROC) and calibration curves. Results Three hundred and thirty-six and 72 patients were included in development and validation cohort, respectively. LASSO regression analysis in development cohort finally reached a two-parametric LCS calculated on AST and ALP levels as 0.03343515 x ln (AST, U/L) + 0.02687997 x ln (ALP, U/L), and 0.232 was set as optimal cutoff value. Patients in low (LCS < 0.232) or high (LCS >= 0.232) score group experienced different survival times; median OS was 13.54 (95% CI: 11.1-15.6) months in the low LCS group and 7.3 (6.6-9.3) months in the high LCS group (p < 0.001). A nomogram including LCS and other clinical parameters was constructed and showed superior performance than model not including LCS. AUC of 6-month ROC improved from 0.647 (95% CI: 0.584-0.711) to 0.699 (0.638-0.759) in internal validation, and 0.837 (0.734-0.940) to 0.875 (0.784-0.966) in external validation. Conclusions Liver chemistry score is useful in determining the prognosis of gastric cancer patients with liver metastasis and may be helpful to clinicians in decision-making.