Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction

• URL: http://arxiv.org/abs/2510.11745v1
• Date: Sat, 11 Oct 2025 14:57:07 GMT
• Title: Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction
• Authors: Qingwen Li, Xiaohang Zhao, Xiao Han, Hailiang Huang, Lanjuan Liu,
• Abstract summary: We propose a novel ICU mortality prediction framework that delivers intrinsic interpretability while integrating all three elements of the ICU decision-making practices into its reasoning process.<n>ProtoDoctor features two key innovations: the Prognostic Clinical Course Identification module and the Demographic Heterogeneity Recognition module.<n>Extensive empirical evaluations demonstrate that ProtoDoctor outperforms state-of-the-art baselines in predictive accuracy.
• Score: 7.809857381429602
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Intensive Care Unit (ICU) mortality prediction, which estimates a patient's mortality status at discharge using EHRs collected early in an ICU admission, is vital in critical care. For this task, predictive accuracy alone is insufficient; interpretability is equally essential for building clinical trust and meeting regulatory standards, a topic that has attracted significant attention in information system research. Accordingly, an ideal solution should enable intrinsic interpretability and align its reasoning with three key elements of the ICU decision-making practices: clinical course identification, demographic heterogeneity, and prognostication awareness. However, conventional approaches largely focus on demographic heterogeneity, overlooking clinical course identification and prognostication awareness. Recent prototype learning methods address clinical course identification, yet the integration of the other elements into such frameworks remains underexplored. To address these gaps, we propose ProtoDoctor, a novel ICU mortality prediction framework that delivers intrinsic interpretability while integrating all three elements of the ICU decision-making practices into its reasoning process. Methodologically, ProtoDoctor features two key innovations: the Prognostic Clinical Course Identification module and the Demographic Heterogeneity Recognition module. The former enables the identification of clinical courses via prototype learning and achieves prognostication awareness using a novel regularization mechanism. The latter models demographic heterogeneity through cohort-specific prototypes and risk adjustments. Extensive empirical evaluations demonstrate that ProtoDoctor outperforms state-of-the-art baselines in predictive accuracy. Human evaluations further confirm that its interpretations are more clinically meaningful, trustworthy, and applicable in ICU practice.

Related papers

• Benchmarking Egocentric Clinical Intent Understanding Capability for Medical Multimodal Large Language Models [48.95516224614331]
  We introduce MedGaze-Bench, the first benchmark leveraging clinician gaze as a Cognitive Cursor to assess intent understanding across surgery, emergency simulation, and diagnostic interpretation.<n>Our benchmark addresses three fundamental challenges: visual homogeneity of anatomical structures, strict temporal-causal dependencies in clinical, and implicit adherence to safety protocols.
  arXiv  Detail & Related papers  (2026-01-11T02:20:40Z)
• Ensemble Deep Learning and LLM-Assisted Reporting for Automated Skin Lesion Diagnosis [2.9307254086347427]
  We introduce a unified framework that reimagines AI integration for dermatological diagnostics.<n>First, a purposefully heterogeneous ensemble of architecturally diverse convolutional neural networks provides complementary diagnostic perspectives.<n>Second, we embed large language model capabilities directly into the diagnostic workflow, transforming classification outputs into clinically meaningful assessments.
  arXiv  Detail & Related papers  (2025-10-05T08:07:33Z)
• Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust [19.107204920543676]
  Distal myopathy represents a heterogeneous group of skeletal muscle disorders with broad clinical manifestations.<n>We propose a novel multimodal attention-aware fusion architecture that combines features extracted from two distinct deep learning models.<n>Our approach integrates these features through an attention gate mechanism, enhancing both predictive performance and interpretability.
  arXiv  Detail & Related papers  (2025-08-02T11:08:55Z)
• Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications [59.721265428780946]
  Large Language Models (LLMs) in medicine have enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning.<n>This paper provides the first systematic review of this emerging field.<n>We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies and test-time mechanisms.
  arXiv  Detail & Related papers  (2025-08-01T14:41:31Z)
• Severity Classification of Chronic Obstructive Pulmonary Disease in Intensive Care Units: A Semi-Supervised Approach Using MIMIC-III Dataset [0.0]
  Chronic obstructive pulmonary disease (COPD) represents a significant global health burden.<n>This study introduces an innovative machine learning framework for COPD severity classification.
  arXiv  Detail & Related papers  (2025-04-24T09:37:52Z)
• Uncertainty-aware abstention in medical diagnosis based on medical texts [87.88110503208016]
  This study addresses the critical issue of reliability for AI-assisted medical diagnosis.<n>We focus on the selection prediction approach that allows the diagnosis system to abstain from providing the decision if it is not confident in the diagnosis.<n>We introduce HUQ-2, a new state-of-the-art method for enhancing reliability in selective prediction tasks.
  arXiv  Detail & Related papers  (2025-02-25T10:15:21Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.<n>Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• XAI for In-hospital Mortality Prediction via Multimodal ICU Data [57.73357047856416]
  We propose an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.
  arXiv  Detail & Related papers  (2023-12-29T14:28:04Z)
• Uncertainty Quantification in Machine Learning Based Segmentation: A Post-Hoc Approach for Left Ventricle Volume Estimation in MRI [0.0]
  Left ventricular (LV) volume estimation is critical for valid diagnosis and management of various cardiovascular conditions.<n>Recent machine learning advancements, particularly U-Net-like convolutional networks, have facilitated automated segmentation for medical images.<n>This study proposes a novel methodology for post-hoc uncertainty estimation in LV volume prediction.
  arXiv  Detail & Related papers  (2023-10-30T13:44:55Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)

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.