LLM framework reconstructs patient mental health journeys from EHRs

Researchers have developed CliniCIRCA, a novel framework utilizing large language models to reconstruct longitudinal patient journeys from unstructured electronic health record (EHR) narratives. This system is designed to temporally classify clinical events within mental health care, even when explicit timestamps are absent. CliniCIRCA was evaluated on MIMIC-III data, producing over 15,000 temporally tagged events, which were then refined through clinician feedback to create a verified gold-standard dataset. This framework aims to improve clinical understanding of patient progression and can be scaled to generate training data for other models. AI

影响 This framework could enhance clinical decision-making by providing structured patient histories, potentially improving mental health treatment.

排序理由 The cluster contains an academic paper detailing a new framework and methodology. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• arXiv
• CliniCIRCA
• electronic health records
• Hugging Face
• MIMIC-III

• 论文
• 模型发布
• 产品

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →