Scholarlink

<p>Clinical AI has advanced rapidly for bounded in-visit tasks such as prediction, documentation, and message generation, yet many costly failures in care occur outside the encounter when follow-up, handoffs, and communication break down. We argue that the next challenge for clinical AI is not only better task performance, but better operational follow-through across the care journey. We propose the PACT framework (Patient-centered, AI-enabled Continuity and Timely action) that reframes clinical AI as a health system function designed to support continuity, completion, escalation, and equity across pre-visit, visit, and post-visit care. The PACT framework specifies the operational elements required for accountable action, including ownership, communication channels, confirmation rules, escalation pathways, and outcome measures. We illustrate its practical use through post-visit coordination, a high-impact setting in which health systems can test workflow integration, monitoring, and tiered human support.</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

Designing clinical AI for patient-centered support beyond the visit: the PACT framework for health systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Saif Khairat,
  • Charles Safran

摘要

Clinical AI has advanced rapidly for bounded in-visit tasks such as prediction, documentation, and message generation, yet many costly failures in care occur outside the encounter when follow-up, handoffs, and communication break down. We argue that the next challenge for clinical AI is not only better task performance, but better operational follow-through across the care journey. We propose the PACT framework (Patient-centered, AI-enabled Continuity and Timely action) that reframes clinical AI as a health system function designed to support continuity, completion, escalation, and equity across pre-visit, visit, and post-visit care. The PACT framework specifies the operational elements required for accountable action, including ownership, communication channels, confirmation rules, escalation pathways, and outcome measures. We illustrate its practical use through post-visit coordination, a high-impact setting in which health systems can test workflow integration, monitoring, and tiered human support.