y0news
← Feed
Back to feed
🧠 AI🟢 BullishImportance 7/10

MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM

arXiv – CS AI|Wenliang Li, Rui Yan, Xu Zhang, Li Chen, Hongji Zhu, Jing Zhao, Junjun Li, Mengru Li, Wei Cao, Zihang Jiang, Wei Wei, Kun Zhang, Shaohua Kevin Zhou||6 views
🤖AI Summary

Researchers developed MACD, a Multi-Agent Clinical Diagnosis framework that enables large language models to self-learn clinical knowledge and improve medical diagnosis accuracy. The system achieved up to 22.3% improvement over clinical guidelines and 16% improvement over physician-only diagnosis when tested on 4,390 real-world patient cases.

Key Takeaways
  • MACD framework allows LLMs to accumulate and apply clinical experience through a multi-agent pipeline, mimicking how physicians develop expertise.
  • Testing on 4,390 patient cases across seven diseases showed up to 22.3% improvement in diagnostic accuracy over established clinical guidelines.
  • Human-AI collaborative workflow demonstrated 18.6% improvement over physician-only diagnosis, highlighting synergistic potential.
  • The self-learned clinical knowledge exhibits cross-model stability and transferability across different LLMs.
  • Framework was successfully tested on multiple open-source models including Llama-3.1 8B/70B and DeepSeek-R1-Distill-Llama 70B.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles