跳到正文
Turing Post (Ksenia Se)· @TheTuringPost · X·· 6 天前AI 评分58
AI 导读

微软 AI 推出 MAI-DxO 医疗智能框架,相关研究发表在 Science,用语言模型模拟提出诊断、选择检查、质疑假设、核查推理和权衡成本 5 种临床角色,在复杂 NEJM 病例上准确率 83.2%、急诊病例 80.3%,参与研究的全科医生分别为 36.1% 和 46.8%。该框架还提出医疗智能的 6 个维度,并把医疗超级智能的门槛定为在完整诊疗过程中超越最强的人类主导医疗系统。

正文 · 原文

Superintelligence in what, exactly?

Maybe it’s time to be more specific about the domains where we expect AI to go beyond human capabilities.

@MicrosoftAI makes medicine an interesting place to start with its new MAI-DxO research and medical intelligence framework↓

The study, published in Science, explores sequential diagnosis from a partial clinical picture.

MAI-DxO (Microsoft AI Diagnostic Orchestrator) uses a language model to simulate 5 clinical roles: proposing diagnoses, selecting questions and tests, challenging assumptions, checking reasoning, and weighing costs. Its assessment evolves as evidence arrives.

It achieved 83.2% accuracy on complex NEJM cases and 80.3% on emergency-department cases, vs. 36.1% and 46.8% for participating generalist physicians.

→ But what would make this medical superintelligence?

▪️ Microsoft’s framework outlines 6 dimensions of medical intelligence.

Its bar for superintelligence is high: outperforming the strongest human-led health systems in reasoning and coordination across the full course of care.

1. Medical knowledge
It applies current evidence to individual cases and recognizes what it doesn’t know.

2. Diagnostic reasoning and triage
It chooses questions, tests, and urgency, revising its view as evidence arrives. Sequential diagnosis fits here.

3. Therapeutic decision-making
It weighs benefits, risks, costs, and availability, adapting treatment as the patient responds.

4. Longitudinal context
It tracks health over time, preserving sources and uncertainty rather than starting fresh at every visit.

5. Clinical coordination
It brings in expertise, determines who acts next, and checks that follow-up happened.

6. Human values and agency
It respects patients’ goals, preferences, and right to refuse a recommendation.

These capabilities must work together. Treatment responses can change diagnoses; patient priorities can change treatment choices, etc.

That’s why a domain-specific view of superintelligence is useful - we can give a system clear tasks and criteria it needs to meet.

来源:Turing Post (Ksenia Se) · x.com