Determining the accuracy of an artificial intelligence-based model to automate the screening phase of related studies in the systematic reviews and comparing it with existing models in terms of strengths and weaknesses

Abstract

The purpose of this study was to determine the accuracy of this system and compare it with other similar systems in terms of strengths and weaknesses. Methods and Materials: Search terms were obtained from fellow researchers. After searching each term, the results were stored in a file and sent to fellow researchers. After categorizing the articles by fellow researchers and the model under study, the results were compared and the accuracy of the model was calculated. Then the SR TOOL BOX website was searched to find similar models and the features of each tool were extracted and then compared with The model investigated and the other models were compared. Results: Accuracy of Acuracy = 0.94, Recall = 0.98 and Precision = 0.83 were calculated after comparing the results of human screening studies (fellow researchers) and the model under study. Also, in terms of most features, 3 models received the highest score, one of which is the model under study.