A new study published on arXiv evaluated the diagnostic and management capabilities of AI systems and human physicians in primary care settings. The AI system Doctorina demonstrated superior performance compared to eight human physicians in diagnostic accuracy and treatment planning across 150 synthetic consultations. Among frontier language models, Kimi K3 showed strong diagnostic performance, while Claude Opus 5 led in management estimates, indicating potential for AI to augment or improve primary care diagnostics and treatment. AI
IMPACT AI systems like Doctorina show potential to significantly improve diagnostic accuracy and treatment planning in primary care, potentially augmenting physician capabilities.
RANK_REASON Research paper published on arXiv detailing AI performance in diagnostics. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- Claude Opus
- DagsHub
- Doctorina
- Gotit.pub
- Hugging Face
- Kimi K3
- Opus
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →