Scholarlink

<p>OpenAI’s GPT-5 demonstration showed a patient uploading pathology reports to guide treatment decisions, though privacy implications were not addressed. We evaluated GPT-5 against 100 gastrointestinal oncology cases with tumor-board validation and found identical 85% concordance to GPT-4o, contradicting superiority claims. We recommend mandatory accuracy disclosures and regulatory oversight for AI health demonstrations to protect patient safety and privacy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Clinical Accuracy and Safety Concerns Following GPT-5 Public Demonstration in Cancer Care

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月29日

查看全文
  • Ivan Capobianco,
  • Andrea Della Penna,
  • André L. Mihaljevic,
  • Michael Bitzer,
  • Carsten Eickhoff,
  • Derna Stifini

摘要

OpenAI’s GPT-5 demonstration showed a patient uploading pathology reports to guide treatment decisions, though privacy implications were not addressed. We evaluated GPT-5 against 100 gastrointestinal oncology cases with tumor-board validation and found identical 85% concordance to GPT-4o, contradicting superiority claims. We recommend mandatory accuracy disclosures and regulatory oversight for AI health demonstrations to protect patient safety and privacy.