Skip to main content
Fig. 3 | BMC Rheumatology

Fig. 3

From: Performance of the Large Language Models in African rheumatology: a diagnostic test accuracy study of ChatGPT-4, Gemini, Copilot, and Claude artificial intelligence

Fig. 3

Histogram of differential diagnosis scores based on Bond et al. ordinal score [6]: (a) ChatGPT-4 (b) Gemini (c) Copilot (d) Claude AI. (5) The actual diagnosis is included in the differential. (4) A very close suggestion is included. (3) A roughly approximate but useful suggestion is included. (2) A related but unlikely useful suggestion is included. (0) No relevant suggestion

Back to article page

BMC Rheumatology

ISSN: 2520-1026

Contact us