Background: Some measures have been proposed for the prediction of death after trauma; however, there is a lack of studies on this issue in trauma patients. Therefore, this study was conducted to compare the validity of four scales in predicting the death of trauma patients, and we hypothesized that the accuracies of various scales are different. Methods: This descriptive-analytical study was conducted prospectively on 600 trauma patients admitted at the emergency ward of Imam Khomeini Hospital in Ilam, Ilam province, west of Iran. The subjects were selected by convenience sampling. Data were collected using the checklists developed for trauma patients, including the Full Outline of UnResponsiveness (FOUR) score, Glasgow Coma Scale (GCS), Revised Trauma Score (RTS), and Trauma and Injury Severity Score (TRISS), and then the data were analyzed using the chi-square test and the area under the receiver operating characteristic curve (AUC). Results: Among the 600 patients, most of them were male (76.8%), with a mean and standard deviation of the age of 31.16 ± 18.06 years, and road traffic accident was the most common cause of trauma (73%). The FOUR scale was the most valid in predicting the mortality of trauma patients, and its sensitivity, specificity, positive and negative predictive values, and accuracy were equal to 93.2, 94.5, 64.7, 99.2, and 94.3%, respectively. The AUC was equal to 0.938 for the FOUR scale, followed by the RTS (0.787). Conclusion: Results of the study about the predictive value of the scales for mortality prediction of trauma patients showed that the FOUR scale had the highest accuracy compared to other scales. Thus, for applying this scale in trauma and emergency centers, besides our results, further studies are needed to support the study findings.