3-agent AI nearly doubles diagnostic accuracy vs physicians at lower cost in 600+ NEJM/ER cases
EricTopol · x · 2026-10-23
Eric Topol and colleagues published in Science: a 3-agent AI system for sequential diagnosis nearly doubled accuracy compared with physicians across 300+ NEJM clinicopathological cases and 300+ ER cases, at substantially lower cost, outperforming many frontier models and physician-plus-AI setups.
The cost-accuracy Pareto chart shows DxO reaching 80% accuracy at $1k of diagnostic tests per case, with a questions-only mode hitting 63% at near-zero cost; physicians overall sit around 20-37%, while GPT-5, Claude 4.1 Opus, Grok 4, and Gemini 2.5 Pro cluster in the 70-80% range at higher spend.
More from Research
- VerifierBench: 222 Tasks Expose How Unreliable Agent-Generated Verifiers Are — Jianing Yin · 2026-10-23
- LM2LM: Frozen World Model Provides Scalable RL Rewards for AI Self-Improvement — Minhua Lin · 2026-10-23
- Stanford prof: LLM-fused models need radically new evals to separate memory from reasoning — anshulkundaje · 2026-10-23
- Stanford professor warns fused LLMs blur the line between memorization and real reasoning — anshulkundaje · 2026-10-23
- NSF picks nine teams for up to $3.5M each to boost super intelligence infrastructure efficiency — sh_reya · 2026-10-23
- CMU professor wins NSF-STRIDE AI Efficiency Challenge grant, hiring PhD students and postdocs — sh_reya · 2026-10-23