Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark
Summary
This paper introduces Clinical Intent Extraction (CIE) and the CIRCA benchmark, which harmonizes clinical intents into structured records aligned with FHIR R4, exposing performance gaps in current models.
View Cached Full Text
Cached at: 09/25/26, 09:22 AM
# Clinical Intent Extraction: A FHIR-Aligned Representation and the CIRCA Benchmark Source: [https://arxiv.org/abs/2609.29479](https://arxiv.org/abs/2609.29479) [View PDF](https://arxiv.org/pdf/2609.29479) > Abstract:Prospective clinical actions, the follow\-ups, orders, referrals, and instructions that deter\-mine what happens to a patient next, are annotated today in thin fragments across incom\-patible corpora: each records a text span and one coarse category\. We introduce Clinical Intent Extraction \(CIE\), the task of recovering these actions as complete structured rec\-ords, and the Clinical Intent Representation \(CIR\), which decomposes each action into its verb, type, coded target, timing, and condition, and adds two axes prior datasets do not jointly represent: request\-intent, the authority behind the action \(proposal, plan, order, or option, aligned to HL7 FHIR\), and modality, a seven\-valued scale of clinical strength\. Re\-expressing five heterogeneous corpora \(CLIP, MedDec, ap\_parsing, PaniniQA, SIMORD\) in the CIR yields CIRCA: 10,011 harmonized intents spanning two note distributions, with a human\-validated subset, source\-to\-CIR crosswalks, and a deterministic FHIR R4 mapper\. CIRCA is built by three\-model consensus that auto\-accepts high\-agreement in\-tents and routes the rest to human review; the audited agreement stratum matches human decisions 88\.4% of the time\. Benchmarking five existing models without task\-specific training exposes the gap CIRCA targets: given the span, they label type well \(85 to 91%\) but get all four closed fields right only 18 to 35% of the time\. All artifacts are released, with MIMIC\-derived layers shared as stand\-off annotations under PhysioNet credentialed access\. ## Submission history From: Yehudit Aperstein \[[view email](https://arxiv.org/show-email/24b0ca7e/2609.29479)\] **\[v1\]**Mon, 24 Aug 2026 07:42:58 UTC \(879 KB\)
Similar Articles
Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
ACIE, an agentic RAG system for clinical information extraction, achieves 96.5% acceptance rate in nuclear-medicine physicians' judgments across 7,326 instances, addressing challenges of heterogeneous patient contexts and missing metadata.
CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR
Introduces CliniCARE-Bench, a deployment-oriented benchmark for evaluating AI agents on clinical audit tasks over longitudinal EHR data, with 25 clinician-validated scenarios and 750 patient cases. It assesses verdict accuracy, evidence grounding, policy adherence, and calibrated abstention, finding that raw accuracy overstates investigation quality.
ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
This paper introduces ClinicalBench and the EpiKG system, evaluating assertion-aware retrieval for clinical question answering on MIMIC-IV data across multiple LLMs. It demonstrates that handling negation and temporality in retrieval significantly improves performance over standard baselines.
CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives
CliniCIRCA is a multi-stage LLM framework for reconstructing longitudinal mental health patient journeys from unstructured EHR narratives, achieving temporal classification without event-level timestamps and using clinician-in-the-loop evaluation for verification.
Inhibitory Attention for Clinical Long-Context Reasoning: Characterizing and Mitigating Lost-in-the-Middle Effects in EHR Processing
This paper characterizes the lost-in-the-middle effect in clinical LLM applications for EHR processing and introduces Query-Conditioned Clinical Suppression (QCCS) to mitigate it, demonstrating improved accuracy over existing retrieval methods.