ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV

• URL: http://arxiv.org/abs/2605.11143v1
• Date: Mon, 11 May 2026 18:47:52 GMT
• Title: ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV
• Abstract summary: Reasoning benchmarks measure clinical performance on clean inputs.<n>We evaluate the step before reasoning: retrieval over real EHR notes, where negation, temporality, and family-versus-patient attribution can flip a correct answer to a wrong one.<n>EpiKG carries assertion label and a temporality tag with every fact in a patient knowledge graph, then routes retrieval by question intent.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reasoning benchmarks measure clinical performance on clean inputs. We evaluate the step before reasoning: retrieval over real EHR notes, where negation, temporality, and family-versus-patient attribution can flip a correct answer to a wrong one. EpiKG carries an assertion label and a temporality tag with every fact in a patient knowledge graph, then routes retrieval by question intent. ClinicalBench is a 400-question test over 43 MIMIC-IV patients across 9 assertion-sensitive categories. A 7-condition ablation tests each piece of EpiKG across six LLMs (Claude Opus 4.6, GPT-OSS 20B, MedGemma 27B, Gemma 4 31B, MedGemma 1.5 4B, Qwen 3.5 35B). Three physicians blindly adjudicated 100 paired items. The author-blind primary endpoint, leave-author-out paired exact McNemar on 50 unanimous-strict items rated by two external physicians, yields +22.0 percentage points (95 percent Newcombe CI [+5.1, +31.5], p=0.0192). The architectural novelty, intent-aware KG-RAG over a Contriever dense-RAG baseline (C2b to C4g_kw on the change-excluded n=362 endpoint), is +8.84 percentage points (paired McNemar p=1.79e-3); +12.43 percentage points under oracle intent. Sensitivities agree directionally: three-rater physician majority +24.0 percentage points (subject to single-author circularity); deterministic keyword reproducibility proxy +39.5 percentage points. Across the six models, the gain shrinks as the LLM-alone baseline rises (beta=-1.123, r=-0.921, p=0.009). With n=6 this looks more like regression to the mean than encoding substituting for model size. Physician adjudication identified 56 percent of auto-generated reference answers as defective, a methodological finding indicating that NLP-pipeline clinical-QA benchmarks require physician adjudication to be usable. ClinicalBench, the frozen evaluator, three-rater adjudication data, and the EpiKG output stack are publicly released.

Related papers

• DementiaCare-Bench: A Modality-Validated Video Benchmark [83.92703885588868]
  Dementia affects an estimated 57 million people worldwide.<n>For most families the hardest part of care is not memory loss but the behavioral and psychological symptoms of dementia.<n>We present DementiaCare-Bench: 56 professionally produced caregiver training videos segmented into 94 clips across nine BPSD categories.
  arXiv  Detail & Related papers  (2026-09-11T14:52:49Z)
• MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation [0.49454229616760287]
  Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation.<n>We introduce MamaBench, the first counterfactual benchmark for maternal and paediatric AI.<n>We propose Evidence-Anchored RAG, a three-stage retrieval method that replaces aggregate similarity with an evidence coverage objective.
  arXiv  Detail & Related papers  (2026-07-15T21:56:19Z)
• Trivial Prompt Reframing Bypasses Safety Guardrails in Googleś MedGemma-4B [0.0]
  Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications.<n>We quantify that gap for MedGemma-4B-it under attacks that require no technical sophistication.
  arXiv  Detail & Related papers  (2026-07-09T18:31:43Z)
• Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering [0.6768558752130311]
  We show monotone decline with hop count in EHR question-answer pairs across four hop levels.<n>Hop count is a theory-motivated, cross-architecture predictor of large-model error on EHR question answering.
  arXiv  Detail & Related papers  (2026-06-15T16:00:27Z)
• Measuring Epistemic Resilience of LLMs Under Misleading Medical Context [47.20527783144983]
  Large language models (LLMs) now reach expert-level scores on medical licensing exams.<n>We show this assumption is fragile: when misleading context is injected into questions that LLMs originally answer correctly, they abandon the correct answer.<n>We call the ability to maintain correct judgment under adversarial context epistemic resilience, and introduce MedMisBench to measure it.
  arXiv  Detail & Related papers  (2026-06-10T16:27:26Z)
• Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus [13.511095666949055]
  Multiple myeloma is managed through sequential lines of therapy over years to decades.<n>A retrospective evaluation was conducted on longitudinal clinical records of 811 myeloma patients treated at a tertiary centre (2001-2026)<n>An agentic reasoning system was compared against single-pass retrieval-augmented generation (RAG), iterative RAG, and full-context input on 469 patient-question pairs.<n>Agentic reasoning was the only approach to exceed the shared ceiling, with gains concentrated on the most complex questions and longest records.
  arXiv  Detail & Related papers  (2026-04-27T13:41:18Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• Clinician input steers frontier AI models toward both accurate and harmful decisions [10.599240857217811]
  We evaluated 21 large language models (LLMs) across 8 frontier models on differential diagnosis generation and next step recommendations.<n>Expert context significantly improved correct final diagnosis inclusion across all 21 models.<n>In GPT-4o experiments, explicit clinician uncertainty signals improved diagnostic performance after adversarial context.
  arXiv  Detail & Related papers  (2026-03-14T23:47:53Z)
• ThReadMed-QA: A Multi-Turn Medical Dialogue Benchmark from Real Patient Questions [5.63130104359934]
  ThReadMed-QA is a benchmark of 2,437 fully-answered patient-seeking conversation threads extracted from r/AskDocs.<n>We evaluate five state-of-the-art LLMs on a stratified test split of 238 conversations.<n>Even the strongest model, GPT-5, achieves only 41.2% fully-correct responses.
  arXiv  Detail & Related papers  (2026-03-11T20:17:57Z)
• From Days to Minutes: An Autonomous AI Agent Achieves Reliable Clinical Triage in Remote Patient Monitoring [2.0918370570198763]
  Remote patient monitoring ( RPM) generates vast data, yet landmark trials (Tele-HF, BEAT-HF) failed because data volume overwhelmed clinical staff.<n>We developed Sentinel, an autonomous AI agent using Model Context Protocol (MCP) for contextual triage of RPM vitals.
  arXiv  Detail & Related papers  (2026-03-10T00:50:54Z)
• PanCanBench: A Comprehensive Benchmark for Evaluating Large Language Models in Pancreatic Oncology [48.732366302949515]
  Large language models (LLMs) have achieved expert-level performance on standardized examinations, yet multiple-choice accuracy poorly reflects real-world clinical utility and safety.<n>We developed a human-in-the-loop pipeline to create expert rubrics for de-identified patient questions.<n>We evaluated 22 proprietary and open-source LLMs using an LLM-as-a-judge framework, measuring clinical completeness, factual accuracy, and web-search integration.
  arXiv  Detail & Related papers  (2026-03-02T00:50:39Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine [69.08855631283829]
  We introduce Med Omni-45 Degrees, a benchmark designed to quantify safety-performance trade-offs under manipulative hint conditions.<n>It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA.<n>Results show a consistent safety-performance trade-off, with no model surpassing the diagonal.
  arXiv  Detail & Related papers  (2025-08-22T08:38:16Z)
• MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks [47.486705282473984]
  Large language models (LLMs) achieve near-perfect scores on medical exams.<n>These evaluations inadequately reflect complexity and diversity of real-world clinical practice.<n>We introduce MedHELM, an evaluation framework for assessing LLM performance for medical tasks.
  arXiv  Detail & Related papers  (2025-05-26T22:55:49Z)
• Multilabel 12-Lead Electrocardiogram Classification Using Gradient Boosting Tree Ensemble [64.29529357862955]
  We build an algorithm using gradient boosted tree ensembles fitted on morphology and signal processing features to classify ECG diagnosis. For each lead, we derive features from heart rate variability, PQRST template shape, and the full signal waveform. We join the features of all 12 leads to fit an ensemble of gradient boosting decision trees to predict probabilities of ECG instances belonging to each class.
  arXiv  Detail & Related papers  (2020-10-21T18:11:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.