{
  "id": 6382930,
  "title": "Performance of Clinical AI System and Physicians and Frontier Language Models in primary care diagnostics",
  "url": "https://urgent.news/2026/09/08/performance-of-clinical-ai-system-and-physicians-and-frontier",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-08T17:25:47.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.09070v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Clinical AI evaluation should encompass diagnosis and management after adaptive information gathering. We compared Doctorina, eight physicians and four standalone frontier language models in 150 synthetic Polish-language primary-care consultations. Doctorina achieved 82.0% Top-1 concordance versus 57.0% for physicians (difference, 25.0 percentage points; 95% confidence interval, 17.7-32.7) and…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}