Fig. 5: Diagnostic performance in primary consultation.
From: Enhancing diagnostic capability with multi-agents conversational large language models
a Accuracy of the most likely diagnosis; b Accuracy of the possible diagnoses; c Helpfulness of further diagnostic tests; d Score for the most likely diagnosis; e Score of the possible diagnoses score; f Score of further diagnostic tests. In (a–c), the bars represent percentages. In (d–f), the bars represent mean values and the error bars indicate standard deviation. Statistical values are listed in Supplementary Tables 2 and 3.
