This study aims to explore the values of different scoring systems in predicting the prognosis of patients with paraquat poisoning, and find out the most clinical application value of indicators. The patients with paraquat poisoning were included and treated in the emergency department from January 2016 to October 2016, every patient was underwent different scoring system, and the Receiver Operating Characteristic (ROC) curve was used to calculate the optimal cut-off value of different scoring system, in order to calculate the sensitivity and specificity of different scoring system to compare the value of different scoring system in predicting the prognosis. The COX mode was used to evaluate the scoring system's relationship with the prognosis of patients with paraquat poisoning. A total of 107 cases were included, and there were 37 cases of death. Every scoring system to predict the value of a poor prognosis in patients with paraquat poisoning was not the same. The sensitivity and specificity of lactic combined with Severity Index of Paraquat Poisoning (SIPP) were 0.900 and 0.741 respectively; it was superior to other scoring system. The results of COX model found that the Risk Ratio (RR) value of lactic combined with SIPP was 12.098 (95% CI: 2.473, 59.178), P value was 0.002, and it was superior to other scoring system. Every scoring system can effectively judge the severe degree of the patients with paraquat poisoning and effective predict the prognosis of patients, and the lactic combined with SIPP is superior to other scoring system.