Objective To explore the predictive efficacy of nutrient composite index based on principal component model for prognosis of patients with gastric cancer. Method A total of 210 patients with gastric cancer who were treated by Beijing Nuclear Industry Hospital from January 2019 to December 2020 and were followed up until December 2023 were selected as the study objects. The patients were divided into poor prognosis group n = 57 and good prognosis group n = 153 according to whether there was recurrence or distant metastasis or death within 3 years of postoperative follow-up. Baseline data gender age BMI smoking history drinking history hypertension history diabetes history tumor size clinical stage differentiation degree preoperative lymph node metastasis vascular invasion trace elements copper Cu zinc Zn iron Fe magnesium Mg selenium Se Cu / Zn ratio were compared between the two groups. Spearman method was used to analyze the correlation between trace elements and clinical characteristics of gastric cancer patients. Pearson method was used to analyze the correlation between the indexes of trace elements. The parameters of nutrient composite index were constructed by principal component analysis and the AUC sensitivity and specificity of nutrient composite index in predicting prognosis of patients with gastric cancer were analyzed by drawing receiver operating characteristic ROC curve. Result The proportion of clinical stage Ⅲ low differentiation preoperative lymph node metastasis,vascular invasion and other baseline data Cu and Cu / Zn in the poor prognosis group were higher than those in the good prognosis group while Zn Mg and Se were lower than those in the good prognosis group P < 0. 05 . There was no significant difference in Fe between the two groups P > 0. 05 . Spearman correlation analysis showed that clinical stage differentiation degree preoperative lymph node metastasis and vascular invasion were positively correlated with Cu and Cu / Zn and negatively correlated with Zn Mg and Se P < 0. 05 . The results of principal component analysis showed that the weight coefficients of Zn Mg Se Cu / Zn and Cu were all > 0. 1 suggesting that they had a great impact on the prognosis of patients with gastric cancer. ROC curve analysis results showed that the AUC values of Cu Zn Mg Se Cu / Zn and composite index in predicting the prognosis of gastric cancer patients were 0. 637 0. 680 0. 739 0. 752 0. 769 0. 819. Conclusion In patients with poor prognosis of gastric cancer the abnormal expression of Cu Zn Mg Se Cu / Zn and other nutrients indicates that their expression levels are affected by prognosis. Dynamic monitoring of micronutrient changes is conducive to providing a reference for evaluating the prognosis of patients with gastric cancer