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

arXiv: https://arxiv.org/abs/2609.19585 · HTML: https://mlsanity.com/paper/2609.19585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 73 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)
- [ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation](https://mlsanity.com/paper/2306.02022/) (2023)
- [Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries](https://mlsanity.com/paper/2310.13132/) (2023)
- [TIMER: Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records](https://mlsanity.com/paper/2503.04176/) (2025)
- [Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models](https://mlsanity.com/paper/2208.08408/) (2022)
- [Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use](https://mlsanity.com/paper/2410.19155/) (2024)
- [Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction](https://mlsanity.com/paper/2501.18724/) (2025)
- [Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessions](https://mlsanity.com/paper/2508.20764/) (2025)
- [A Large-Language Model Framework for Relative Timeline Extraction from PubMed Case Reports](https://mlsanity.com/paper/2504.12350/) (2025)
- [Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG](https://mlsanity.com/paper/2509.13930/) (2025)
- [REGen: A Reliable Evaluation Framework for Generative Event Argument Extraction](https://mlsanity.com/paper/2502.16838/) (2025)
- [Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach](https://mlsanity.com/paper/2503.18085/) (2025)
- [Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment](https://mlsanity.com/paper/2605.15168/) (2026)
- [ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts](https://mlsanity.com/paper/2511.11883/) (2025)

## Abstract (arXiv)

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.