Domain-Adapted Small Language Models for Reliable Clinical Triage

• URL: http://arxiv.org/abs/2604.26766v1
• Date: Wed, 29 Apr 2026 15:00:09 GMT
• Title: Domain-Adapted Small Language Models for Reliable Clinical Triage
• Abstract summary: This study evaluates whether open-source small language models (SLMs) can serve as reliable, privacy-preserving decision-support tools for clinical triage.
• Score: 4.836986736624673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-text triage documentation contributes to mistriage and workflow inefficiencies. This study evaluates whether open-source small language models (SLMs) can serve as reliable, privacy-preserving decision-support tools for clinical triage. We systematically compared multiple SLMs across diverse prompting pipelines and found that clinical vignettes, concise summaries of triage narratives, yielded the most accurate predictions. The SLM, Qwen2.5-7B, demonstrated the strongest balance of accuracy, stability, and computational efficiency. Through large-scale domain adaptation using expert-curated and silver-standard pediatric triage data, fine-tuned Qwen2.5-7B models substantially reduced discordance and clinically significant errors, outperforming all baseline SLMs and advanced proprietary large language models (LLMs, e.g., GPT-4o). These findings highlight the feasibility of institution-specific SLMs for reliable, privacy-preserving ESI decision support and underscore the importance of targeted fine-tuning over more complex inference strategies.

Related papers

• From Many to Meaningful: Feature-Guided Zero-Shot Chronic Kidney Disease Screening Using Large Language Models [0.5442955439283729]
  This study examines the feasibility of using large language models (LLMs) for early-stage CKD screening in a zero-shot setting.<n>We propose a feature-guided framework that evaluates LLM performance using a selected set of clinically meaningful, readily available community-based features.<n>Generalizability was assessed across three heterogeneous CKD datasets spanning three countries.
  arXiv  Detail & Related papers  (2026-07-14T02:00:58Z)
• Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports [49.5225801722164]
  Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar.<n>We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance.
  arXiv  Detail & Related papers  (2026-06-17T08:10:30Z)
• Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors [10.853232316677362]
  Large language models (LLMs) and vision-language models (VLMs) have demonstrated strong adaptability to natural images.<n> RAD3D-Prefix is a framework that minimizes the need for extensive parameter training.<n>Our method requires minimal trainable parameters and mitigates the risk of overfitting on small, domain-specific datasets.
  arXiv  Detail & Related papers  (2026-06-15T18:51:31Z)
• Dynamic Summary Generation for Interpretable Multimodal Depression Detection [23.358673852385337]
  Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening.<n>We propose a coarse-to-fine, multi-stage framework that leverages large language models for accurate and interpretable detection.
  arXiv  Detail & Related papers  (2026-04-13T11:34:40Z)
• Is Clinical Text Enough? A Multimodal Study on Mortality Prediction in Heart Failure Patients [1.6784199253342376]
  We evaluate transformer-based models on a French heart failure cohort.<n>We show that enriching clinical text with entity-level representations improves prediction over CLS embeddings alone.<n>Large language models perform inconsistently across modalities and decoding strategies.
  arXiv  Detail & Related papers  (2026-04-02T11:41:36Z)
• DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data [2.3915781021862332]
  DISCO-TAB is a novel framework that orchestrates a fine-tuned LLM with a multi-objective discriminator system optimized via Reinforcement Learning.<n>We rigorously validate our framework across diverse benchmarks, including high-dimensional, small-sample medical datasets.<n>Our results demonstrate that hierarchical feedback yields state-of-the-art performance, achieving up to 38.2% improvement in downstream clinical utility.
  arXiv  Detail & Related papers  (2026-04-01T23:37:58Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning [58.355275813623685]
  This work looks at a critical gap in the calibration of large language models (LLMs) within multilingual settings.<n>Even in low-resource languages, model confidence can increase significantly after instruction-tuning on high-resource language SFT datasets.<n>However, improvements in accuracy are marginal or non-existent, highlighting a critical shortcoming of standard SFT for multilingual languages.
  arXiv  Detail & Related papers  (2026-01-04T04:29:12Z)
• Self-Correction Distillation for Structured Data Question Answering [50.98882432829651]
  Small-scale language models (LLMs) are prone to errors in generating structured queries.<n>We propose a self-correction distillation (SCD) method to improve the structured data QA ability of small-scale LLMs.
  arXiv  Detail & Related papers  (2025-11-11T09:01:51Z)
• OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction [2.904892426557913]
  Large language models (LLMs) have shown strong performance in biomedical NLP.<n>We present a unified, multi-task learning framework that aligns autoregressive LLMs with clinical reasoning for outcome prediction.<n>Our findings underscore the importance of reasoning-aware alignment in multi-task clinical modeling.
  arXiv  Detail & Related papers  (2025-10-20T13:35:12Z)
• LLM-Assisted Emergency Triage Benchmark: Bridging Hospital-Rich and MCI-Like Field Simulation [0.0]
  We introduce an open, LLM-assisted emergency triage benchmark for deterioration prediction.<n>The benchmark defines two regimes: (i) a hospital-rich setting with vitals, labs, notes, chief complaints, and structured observations, and (ii) an MCI-like field simulation limited to vitals, observations, and notes.
  arXiv  Detail & Related papers  (2025-09-30T14:54:58Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

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.