ICU-Transformer: Multi-Head Attention Expert System for ICU Resource Allocation Robust to Data Poisoning Attacks

Intensive Care Units (ICUs) face unprecedented challenges in resource allocation, particularly during health crises in which algorithmic systems may be exposed to adversarial manipulation. A transformer-based expert system, ICU-Transformer, is presented to optimize resource allocation across 200 ICUs in Physionet while maintaining robustness against data poisoning attacks. The framework incorporates a Robust Multi-Head Attention mechanism that achieves an AUC-ROC of 0.891 in mortality prediction under 20% data contamination, outperforming conventional baselines. The system is trained and evaluated using data from the MIMIC-IV and eICU Collaborative Research Database and is deployed to manage more than 50,000 ICU admissions annually. A Resource Optimization Engine (ROE) is introduced to dynamically allocate ventilators, Extracorporeal Membrane Oxygenation (ECMO) machines, and specialized clinical staff based on predicted deterioration risk, resulting in an 18% reduction in preventable deaths. A Surge Capacity Planner (SCP) is further employed to simulate disaster scenarios and optimize cross-hospital resource distribution. Deployment across the Physionet ICU Network demonstrates improvements, including a 2.1-day reduction in average ICU bed turnover time, a 31% decrease in unnecessary admissions, and an estimated USD 142 million in annual operational savings. During the observation period, 234 algorithmic manipulation attempts were detected, with targeted disparities identified and mitigated through enhanced auditing protocols.

• Publication year

  2025

• Venue

  Future Internet

• Publication date

  2025-12-22

• Fields of study

  Not labeled

• Identifiers
  DOI 10.3390/fi18010006
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Optimizing ICU Resource Allocation During the COVID-19 Crisis: An AI-Driven Approach

  2025cited by this paper
• Privacy-Aware Hierarchical Federated Learning in Healthcare: Integrating Differential Privacy and Secure Multi-Party Computation

  2025cited by this paper
• Decentralized Federated Learning for Private Smart Healthcare: A Survey

  2025cited by this paper
• Predicting outcomes using neural networks in the intensive care unit

  2025cited by this paper
• Large Language Models and Artificial Neural Networks for Assessing 1-Year Mortality in Patients With Myocardial Infarction: Analysis From the Medical Information Mart for Intensive Care IV (MIMIC-IV) Database

  2025cited by this paper
• Blockchain-Based Privacy-Enhancing Federated Learning in Smart Healthcare: A Survey

  2025cited by this paper
• Transformer-based model for predicting length of stay in intensive care unit in sepsis patients

  2025cited by this paper
• Medical large language models are vulnerable to data-poisoning attacks

  2025cited by this paper
• Advances in attention mechanisms for medical image segmentation

  2025cited by this paper
• A 3D medical image segmentation network based on gated attention blocks and dual-scale cross-attention mechanism

  2025cited by this paper
• A new method for long-term temperature compensation of structural health monitoring by ultrasonic guided wave

  2025cited by this paper
• Multi-scale conv-attention U-Net for medical image segmentation

  2025cited by this paper
• Privacy-Preserving Federated Learning Framework for Multi-Source Electronic Health Records Prognosis Prediction

  2025cited by this paper
• Federated Learning in Smart Healthcare: A Comprehensive Review on Privacy, Security, and Predictive Analytics with IoT Integration

  2024cited by this paper
• EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records

  2024cited by this paper
• Real-time machine learning model to predict short-term mortality in critically ill patients: development and international validation

  2024cited by this paper
• Symptom-BERT: Enhancing Cancer Symptom Detection in EHR Clinical Notes.

  2024cited by this paper
• Transformer models in biomedicine

  2024cited by this paper
• Zero shot health trajectory prediction using transformer

  2024cited by this paper
• Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook

  2024cited by this paper
• Dual-attention transformer-based hybrid network for multi-modal medical image segmentation

  2024cited by this paper
• Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications

  2024cited by this paper
• Minimal data poisoning attack in federated learning for medical image classification: An attacker perspective

  2024cited by this paper
• Enhancing the adversarial robustness in medical image classification: exploring adversarial machine learning with vision transformers-based models

  2024cited by this paper
• A novel deep learning algorithm for real-time prediction of clinical deterioration in the emergency department for a multimodal clinical decision support system

  2024cited by this paper
• Privacy-Preserving Federated Learning-Based Intrusion Detection System for IoHT Devices

  2024cited by this paper
• Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction

  2020cited by this paper
• BEHRT: Transformer for Electronic Health Records

  2019cited by this paper
• Deep Learning for Medical Image Analysis

  2017cited by this paper
• Systematic Poisoning Attacks on and Defenses for Machine Learning in Healthcare

  2015cited by this paper

• No citing papers are available for this paper.