aiqbench analysis
CliniCIRCA introduces a novel LLM framework capable of reconstructing longitudinal patient timelines from unstructured mental health records without relying on explicit timestamps. By leveraging instruction tuning over large-scale datasets, the system effectively compresses clinical narratives while maintaining high accuracy in event extraction and temporal classification. This advancement addresses a critical gap in handling imprecise medical data, offering a scalable solution for building robust digital patient journeys.
CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives
arXiv:2609.19585v1 Announce Type: cross Abstract: 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.
Abstract: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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
arXiv:2609.19585 [cs.CL]
(or arXiv:2609.19585v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.19585 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 275 words
Related coverage
MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support
arXiv · Oct 16, 2026
A Safety-Gated Multimodal AI Backend for Mental-Health Support: Hierarchical State Representation, Conservative Risk Fusion, and Controlled Generation in Anian
arXiv · Aug 28, 2026
Peer-Grounded Counterfactual Path Planning for Chronic Health Management
arXiv · Sep 28, 2026
Models Can't Remember Their Training. Neither Can You.
LessWrong · Jul 19, 2026