mlsanityData to 14 Oct 2026

Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset

arXiv 2608.26109 ↗First posted 21 May 2026cs.AIcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Machine-learning models can predict ICU mortality accurately, but feature-attribution methods alone rarely provide the clinical narrative needed for bedside use. Large language models (LLMs) may bridge this gap, and multi-step agentic pipelines are a plausible extension because they separate data interpretation, guideline checking, and final explanation. This revised feasibility study preserves the original standalone-versus-agentic comparison while making the main clinical findings more explicit. Using the retained local eICU Demo artifact set (2,353 ICU stays; 8.1% mortality), XGBoost achieved an AUROC of 0.855 (95% CI 0.796--0.906) and an AUPRC of 0.332 (95% CI 0.217--0.494). On a stratified 38-case explanation subset, the standalone LLM produced 1 explanation with explicit outcome leakage, whereas the four-step agentic pipeline produced none. Among the 14 cases that overlapped with the SHAP review subset, the standalone LLM showed higher SHAP alignment (mean Jaccard 0.171 versus 0.077) and higher direction consistency (92.9% versus 78.6%), while the agentic pipeline showed higher guideline grounding (0.762 versus 0.143), higher value specificity (0.236 versus 0.143), and slightly higher plausibility (0.700 versus 0.671). Clinically, the results suggest that agentic decomposition may improve safety-relevant grounding and patient-specific detail, but it should be paired with attribution-based checks before use in high-stakes risk explanation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 9 of its 17 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

9 of 17 references.

References · 9

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  6. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  7. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  8. 2017Multitask learning and benchmarking with clinical time series datacited by 290
  9. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 135

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
  2. 2025Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction
  3. 2024Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries
  4. 2026CodeClinic: Evaluating Automation of Coding Skills for Clinical Reasoning Agents
  5. 2025Explainable AI for Clinical Outcome Prediction: A Survey of Clinician Perceptions and Preferences
  6. 2026Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical Domains
  7. 2024Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication
  8. 2026CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance