{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:31:09Z","timestamp":1766727069260,"version":"3.48.0"},"reference-count":30,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/fi18010006","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:27:47Z","timestamp":1766500067000},"page":"6","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ICU-Transformer: Multi-Head Attention Expert System for ICU Resource Allocation Robust to Data Poisoning Attacks"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-6897","authenticated-orcid":false,"given":"Manal","family":"Alghieth","sequence":"first","affiliation":[{"name":"Department of Information Technology, College of Computer, Qassim University, Buraydah 51452, Saudi Arabia"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"25704","DOI":"10.1038\/s41598-024-76234-y","article-title":"Dual-attention transformer-based hybrid network for multi-modal medical image segmentation","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"6159","DOI":"10.1038\/s41598-025-90339-y","article-title":"A 3d medical image segmentation network based on gated attention blocks and dual-scale cross-attention mechanism","volume":"15","author":"Jiang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1038\/s41591-024-03445-1","article-title":"Medical large language models are vulnerable to data-poisoning attacks","volume":"31","author":"Alber","year":"2025","journal-title":"Nat. Med."},{"key":"ref_4","first-page":"9","article-title":"Optimizing icu resource allocation during the COVID-19 crisis: An ai-driven approach","volume":"1","author":"Sabrou","year":"2025","journal-title":"Biomed. Inform. Smart Healthc."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kim, J., Kim, G.-H., Kim, J.-W., Kim, K.H., Maeng, J.-Y., Shin, Y.-G., and Park, S. (2025). Transformer-based model for predicting length of stay in intensive care unit in sepsis patients. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1473533"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"103024","DOI":"10.1016\/j.artmed.2024.103024","article-title":"Minimal data poisoning attack in federated learning for medical image classification: An attacker perspective","volume":"159","author":"Kumar","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1109\/JBHI.2014.2344095","article-title":"Systematic poisoning attacks on and defenses for machine learning in healthcare","volume":"19","author":"Raghunathan","year":"2015","journal-title":"IEEE J. Biomed. Heal. Inform."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e67253","DOI":"10.2196\/67253","article-title":"Large language models and artificial neural networks for assessing 1-year mortality in patients with myocardial infarction","volume":"27","author":"Shi","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Madan, S., Lentzen, M., Brandt, J., Rueckert, D., Hofmann-Apitius, M., and Fr\u00f6hlich, H. (2024). Transformer models in biomedicine. BMC Med. Inform. Decis. Mak., 24.","DOI":"10.1186\/s12911-024-02600-5"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e59505","DOI":"10.2196\/59505","article-title":"Multimodal large language models in health care: Applications, challenges, and future outlook","volume":"26","author":"AlSaad","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"30116","DOI":"10.1038\/s41598-024-80268-7","article-title":"A novel deep learning algorithm for real-time prediction of clinical deterioration in the emergency department for a multimodal clinical decision support system","volume":"14","author":"Choi","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100966","DOI":"10.12998\/wjcc.v13.i11.100966","article-title":"Predicting outcomes using neural networks in the intensive care unit","volume":"13","author":"Sridhar","year":"2025","journal-title":"World J. Clin. Cases"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1186\/s13054-024-04866-7","article-title":"Real-time machine learning model to predict short-term mortality in critically ill patients: Development and international validation","volume":"28","author":"Lim","year":"2024","journal-title":"Crit. Care"},{"key":"ref_14","first-page":"245","article-title":"Zero shot health trajectory prediction using transformer","volume":"7","author":"Zilker","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7971","DOI":"10.1007\/s00521-024-10516-4","article-title":"Enhancing the adversarial robustness in medical image classification: Exploring adversarial machine learning with vision transformers-based models","volume":"37","author":"Gulsoy","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s10462-024-11005-9","article-title":"Robustness in deep learning models for medical diagnostics: Security and adversarial challenges towards robust ai applications","volume":"57","author":"Javed","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Alshwaheen, A., Khan, M., Sherani, A., Qayyum, M., and Hussain, H. (2024). Federated learning in smart healthcare: A comprehensive review on privacy, security, and predictive analytics with iot integration. Healthcare, 12.","DOI":"10.3390\/healthcare12242587"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ngoupayou Limbepe, Z., Gai, K., and Yu, J. (2025). Blockchain-based privacy-enhancing federated learning in smart healthcare: A survey. Blockchains, 3.","DOI":"10.3390\/blockchains3010001"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhao, H., Sui, D., Wang, Y., Ma, L., and Wang, L. (2025). Privacy-preserving federated learning framework for multi-source electronic health records prognosis prediction. Sensors, 25.","DOI":"10.3390\/s25082374"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Cheng, H., Qu, Y., Liu, W., Gao, L., and Zhu, T. (2025). Decentralized federated learning for private smart healthcare: A survey. Mathematics, 13.","DOI":"10.3390\/math13081296"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Singh, J., Kumar, R., and Patel, S. (2025). Privacy-aware hierarchical federated learning in healthcare: Integrating differential privacy and secure multi-party computation. Futur. Internet, 17.","DOI":"10.3390\/fi17080345"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Mohammadi, F., and Rezaei, A. (2024). Privacy-preserving federated learning-based intrusion detection system for ioht devices. Electronics, 14.","DOI":"10.3390\/electronics14010067"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"100721","DOI":"10.1016\/j.cosrev.2024.100721","article-title":"Advances in attention mechanisms for medical image segmentation","volume":"55","author":"Zhang","year":"2025","journal-title":"Comput. Sci. Rev."},{"key":"ref_24","first-page":"96101","article-title":"Multi-scale conv-attention u-net for medical image segmentation","volume":"15","author":"Pan","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_25","first-page":"2356","article-title":"Deep learning on medical image analysis","volume":"9","author":"Wang","year":"2024","journal-title":"CAAI Trans. Intell. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104605","DOI":"10.1016\/j.jbi.2024.104605","article-title":"Ehrbert: A bert-based model for effective anomaly detection in electronic health records","volume":"150","author":"Niu","year":"2024","journal-title":"J. Biomed. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1016\/j.jpainsymman.2024.05.015","article-title":"Symptom-bert: Enhancing cancer symptom detection in ehr clinical notes","volume":"68","author":"Zeinali","year":"2024","journal-title":"J. Pain Symptom Manag."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","article-title":"Behrt: Transformer for electronic health records","volume":"10","author":"Li","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","article-title":"Med-bert: Pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction","volume":"4","author":"Rasmy","year":"2021","journal-title":"npj Digit. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"117310","DOI":"10.1016\/j.measurement.2025.117310","article-title":"A new method for long-term temperature compensation of structural health monitoring by ultrasonic guided wave","volume":"252","author":"Liu","year":"2025","journal-title":"Measurement"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/18\/1\/6\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T05:29:04Z","timestamp":1766726944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/18\/1\/6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["fi18010006"],"URL":"https:\/\/doi.org\/10.3390\/fi18010006","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2025,12,22]]}}}