Metraipolis › archive › dc_3dae059462b9

CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives — arXiv:2609.19585

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19585
License (as archived)
CC0-1.0
Archived
2026-10-10T03:23:19.798Z
SHA-256 of the archived text
4476835aa42fe731c2c483afe5176236427d477d892d0ec87d26f4c7041a0d51
Stable URL of this page
https://metraipolis.com/documento/dc_3dae059462b9

How to cite

CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives — arXiv:2609.19585 — arXiv (en), https://arxiv.org/abs/2609.19585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3dae059462b9 (Metraipolis archive dc_3dae059462b9, sha256 4476835aa42fe731c2c483afe5176236427d477d892d0ec87d26f4c7041a0d51)
BibTeX
@misc{dc3dae059462b9,
  title = {CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives — arXiv:2609.19585},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19585},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3dae059462b9; sha256 4476835aa42fe731c2c483afe5176236427d477d892d0ec87d26f4c7041a0d51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In mental health care, reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of biological, psychological, and social events, are often spread across disparate unstructured text narratives, making temporal recovery challenging. We present CliniCIRCA, a multi-stage LLM framework for Calendar-anchored, Imprecision-aware Reconstruction of Clinical Annals. To our knowledge, CliniCIRCA is the first to temporally classify clinical events across unstructured discharge summaries without event-level timestamps. From 14,882 MIMIC-III mental health admissions, we first construct a benchmark of 52 discharge summaries on which CliniCIRCA produces 15,891 temporally tagged events. After correcting 629 errors based on a clinician-in-the-loop evaluation, we produce verified gold-standard labels. Finally, the corrected timelines drive a temporally grounded summarization stage that compresses each source 1.52 times into a date-grouped chronological record. We then scale the framework to generate 1,000 silver-standard timelines and evaluate them as training data. Compared with zero- and few-shot prompting, instruction tuning generally improves five open-weight models on event extraction, temporal tagging, and summarization across silver and clinician-verified evaluations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19585 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:04:13.832Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).