Objective To investigate the predictive value of lactic acid to albumin ratio in the in-hospital mortality of the patients with intra-abdominal infection sepsis in ICU.Methods The clinical data in 175 pa-tients with sepsis caused by intra-abdominal infection admitted and treated in the intensive care medicine de-partment of this hospital from January 2018 to December 2021 were retrospectively analyzed.The patients were divided into the survival group (n=94) and death group (n=81) according to whether or not having in-hospital death.The general data,blood lactic acid and albumin levels of the patients at admission were collect-ed,and the LAR value was calculated.The receiver operating characteristic (ROC) curve was used to evaluate the predictive value of LAR for the in-hospital mortality of sepsis patients in ICU.The Cox regression analysis and Kaplan-Meier curves were used to analyze the independent correlation between LAR and ICU mortality. Results There were statistically significant differences in the acute physiology and chronic health scoring sys-tem Ⅱ (APACHⅡ) score,sequential organ failure assessment (SOFA) score,mean arterial pressure,oxygen-ation index,PCT,lactic acid,albumin,LAR and the proportion of surgical patients between the two groups (P<0.05).The area under the curve (AUC) of LAR for predicting the prognosis in the patients with ICU sepsis was 0.765 (95％CI:0.695-0.835),which was higher than that of the APACHEⅡscore,SOFA score,lactic acid and PCT.With LAR=1.295 as the cutoff value,the sensitivity and specificity for its prediction were 0.679 and 0.707,respectively.The Kaplan-Meier curve showed that the ICU motality rate in high LAR (LAR≥1.29) was higher than that in low LAR,and the difference was statistically significant(63.2％ vs. 41.5％,P<0.05).The Cox regression analysis results showed that the mortality in sepsis showed the increas-ing trend with the LAR level increase (P<0.05).Conclusion LAR is an influencing factor of the death in the intra-abdominal infection sepsis in ICU,which could effectively predict the risk of in-hospital death of the patients.