Applications of Artificial Intelligence for Patient Monitoring in the Intensive Care Unit: A Comprehensive Narrative Review

Al Moosewy, Ameer Abbas

doi:10.66723/zjaia.2026.164857.1005

	Applications of Artificial Intelligence for Patient Monitoring in the Intensive Care Unit: A Comprehensive Narrative Review
Al-Zahraa Journal for Artificial Intelligence Applications
Article 5, Volume 0, Issue 1, September 2026, Pages 48-59 PDF (327.44 K)
Document Type: Review Article
DOI: 10.66723/zjaia.2026.164857.1005
Author
Ameer Abbas Al moosewy^*
Al -Zahraa University for Women
Abstract
Intensive Care Units (ICUs) require continuous, high-resolution monitoring to detect early clinical deterioration. Artificial intelligence (AI) has emerged as a transformative tool capable of enhancing predictive accuracy and supporting real-time clinical decision-making. This review aims to critically evaluate current applications of AI in ICU patient monitoring, identify performance trends across different clinical domains, and address existing gaps in validation, implementation, and clinical integration. Using databases including PubMed, Scopus, and Google Scholar, a systematic literature review was carried out. Studies that concentrated on AI - based monitoring systems used in intensive care unit settings that were published between 2015 and 2025 were considered. After being extracted, pertinent data was grouped thematically. AI models demonstrated strong predictive performance across multiple ICU applications. Sepsis prediction models achieved AUROC values ranging from 0.83 to 0.94, while ventilator weaning models reported AUROC values between 0.76 and 0.93, with sensitivity reaching up to 91% for extubation success prediction. Hemodynamic monitoring systems, particularly those based on waveform analysis, achieved AUROC values around 0.89 for hypotension prediction. Multimodal AI platforms integrating electronic health records (EHR), physiological signals, and wearable data achieved AUROC values between 0.76 and 0.82. Despite these promising results, fewer than 30% of models underwent external validation. AI-based monitoring systems significantly enhance early detection of clinical deterioration and support proactive ICU management. However, their clinical implementation remains limited by challenges in external validation, interpretability, and workflow integration. Future research should prioritize prospective multicenter trials, development of explainable AI models, and integration into real-time ICU systems to improve patient outcomes and ensure safe adoption in clinical practice.
Keywords
Early warning systems; Critical care; Intensive care units; Patient monitoring; Artificial intelligence

References
[1] K. Kirkland, F. O. Arafat, and G. J. Beilman, “Monitoring and managing the critically ill patient in the intensive care unit,” in Handbook of Cardiac Anatomy, Physiology, and Devices, Cham: Springer Nature Switzerland, Dec. 9, 2024, pp. 477–488. doi: https://doi.org/10.1007/978-3-031-72581-4_24 [2] S. Verderber, S. Gray, S. Suresh-Kumar, D. Kercz, and C. Parshuram, “Intensive care unit-built environments: A comprehensive literature review (2005–2020),” HERD: Health Environments Research & Design Journal, vol. 14, no. 4, pp. 368–415, Oct. 2021. doi: https://doi.org/10.1177/19375867211009273 [3] K. A. Connell, B. Lin, H. Figueroa, and C. Bethel, “The nurse work environment and staffing in critical care,” Critical Care Nursing Clinics, Aug. 23, 2025. doi: https://doi.org/10.1016/j.cnc.2025.07.002 [4] B. Ashokka, C. Dong, L. S. Law, S. Y. Liaw, F. G. Chen, and D. D. Samarasekera, “A BEME systematic review of teaching interventions to equip medical students and residents in early recognition and prompt escalation of acute clinical deteriorations: BEME Guide No. 62,” Medical Teacher, vol. 42, no. 7, pp. 724–737, Jul. 2020. doi: https://doi.org/10.1080/0142159X.2020.1763286 [5] N. A. Halpern, E. Scruth, M. Rausen, and D. Anderson, “Four decades of intensive care unit design evolution and thoughts for the future,” Critical Care Clinics, vol. 39, no. 3, pp. 577–602, Jul. 2023. doi: https://doi.org/10.1016/j.ccc.2023.01.008 [6] K. A. Connell, B. Lin, H. Figueroa, and C. Bethel, “The nurse work environment and staffing in critical care,” Critical Care Nursing Clinics, Aug. 23, 2025. doi: https://doi.org/10.1016/j.cnc.2025.07.002 [7] V. M. Chigboh, S. J. Zouo, and J. Olamijuwon, “Predictive analytics in emergency healthcare systems: A conceptual framework for reducing response times and improving patient care,” World Journal of Advanced Pharmaceutical and Medical Research, vol. 7, no. 2, pp. 119–127, 2024. doi: https://doi.org/10.53346/wjapmr.2024.7.2.0050 [8] N. L. Rane, M. Paramesha, S. P. Choudhary, and J. Rane, “Artificial intelligence, machine learning, and deep learning for advanced business strategies: A review,” Partners Universal International Innovation Journal, vol. 2, no. 3, pp. 147–171, Jun. 25, 2024. doi: https://doi.org/10.5281/zenodo.12208298 [9] V. R. Cossich, D. Carlgren, R. J. Holash, and L. Katz, “Technological breakthroughs in sport: Current practice and future potential of artificial intelligence, virtual reality, augmented reality, and modern data visualization in performance analysis,” Applied Sciences, vol. 13, no. 23, p. 12965, Dec. 4, 2023. doi: https://doi.org/10.3390/app132312965 [10] G. Beltrao, W. A. Martins, B. S. M. R., M. Alaee-Kerahroodi, U. Schroeder, and D. Tatarinov, “Adaptive nonlinear least squares framework for contactless vital sign monitoring,” IEEE Transactions on Microwave Theory and Techniques, vol. 71, no. 4, pp. 1696–1710, Nov. 29, 2022. doi: https://doi.org/10.1109/TMTT.2022.3222384 [11] M. Feinstein, D. Katz, S. Demaria, and I. S. Hofer, “Remote monitoring and artificial intelligence: Outlook for 2050,” Anesthesia & Analgesia, vol. 138, no. 2, pp. 350–357, Feb. 1, 2024. doi: https://doi.org/10.1213/ANE.0000000000006712 [12] Z. Ahmed, K. Mohamed, S. Zeeshan, and X. Dong, “Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine,” Database, vol. 2020, p. baaa010, 2020. doi: https://doi.org/10.1093/database/baaa010 [13] R. A. El Arab, M. S. Abu-Mahfouz, F. H. Abuadas, H. Alzghoul, M. Almari, A. Ghannam, and M. M. Seweid, “Bridging the gap: From AI success in clinical trials to real-world healthcare implementation-A narrative review,” Healthcare, vol. 13, no. 7, p. 701, Mar. 22, 2025. doi: https://doi.org/10.3390/healthcare13070701 [14] C. A. Hansen and A. G. Ozkil, “From idea to production: A retrospective and longitudinal case study of prototypes and prototyping strategies,” Journal of Mechanical Design, vol. 142, no. 3, Mar. 1, 2020. doi: https://doi.org/10.1115/1.4045385 [15] L. Rehberg and A. Brem, “Industrial prototyping in the German automotive industry: Bridging the gap between physical and virtual prototypes,” Journal of Engineering and Technology Management, vol. 71, p. 101798, Jan. 1, 2024. doi: https://doi.org/10.1016/j.jengtecman.2024.101798 [16] C. Stylianides et al., “AI advances in ICU with an emphasis on sepsis prediction: An overview,” Machine Learning and Knowledge Extraction, vol. 7, no. 1, p. 6, Jan. 8, 2025. doi: https://doi.org/10.3390/make7010006 [17] D. Park et al., “Early warning score and feasible complementary approach using artificial intelligence-based bio-signal monitoring system: A review,” Biomedical Engineering Letters, pp. 1–8, Jun. 25, 2025. doi: https://doi.org/10.1007/s13534-025-00486-4 [18] S. Nemati, A. Holder, F. Razmi, M. D. Stanley, G. D. Clifford, and T. G. Buchman, “An interpretable machine learning model for accurate prediction of sepsis in the ICU,” Critical Care Medicine, vol. 46, no. 4, pp. 547–553, Apr. 1, 2018. doi: https://doi.org/10.1097/CCM.0000000000002936 [19] P. Rockenschaub et al., “External validation of AI-based scoring systems in the ICU: A systematic review and meta-analysis,” BMC Medical Informatics and Decision Making, vol. 25, no. 1, p. 5, Jan. 6, 2025. doi: https://doi.org/10.1186/s12911-024-02830-7 [20] Z. Zeng, X. Tang, Y. Liu, Z. He, and X. Gong, “Interpretable recurrent neural network models for dynamic prediction of the extubation failure risk in patients with invasive mechanical ventilation in the intensive care unit,” BioData Mining, vol. 15, no. 1, p. 21, Sep. 27, 2022. doi: https://doi.org/10.1186/s13040-022-00309-7 [21] A. Pakbin, A. Su, D. K. Lee, and B. J. Mortazavi, “Realtime, multimodal invasive ventilation risk monitoring using language models and BoXHED,” arXiv preprint arXiv:2410.03725, Sep. 29, 2024. doi: https://doi.org/10.48550/arXiv.2410.03725 [22] A. Yoosoofsah, “Predicting extubation failure in intensive care: The development of a novel, end-to-end actionable and interpretable prediction system,” arXiv preprint arXiv:2412.00105, Nov. 27, 2024. doi: https://doi.org/10.48550/arXiv.2412.00105 [23] N. Ashrafi, Y. Liu, X. Xu, Y. Wang, Z. Zhao, and M. Pishgar, “Deep learning model utilization for mortality prediction in mechanically ventilated ICU patients,” Informatics in Medicine Unlocked, vol. 49, p. 101562, Jan. 1, 2024. doi: https://doi.org/10.1016/j.imu.2024.101562 [24] S. Nanini, M. Abid, Y. Mamouni, A. Wiedemann, P. Jouvet, and S. Bourassa, “Machine and deep learning models for hypoxemia severity triage in CBRNE emergencies,” Diagnostics, vol. 14, no. 23, p. 2763, Dec. 8, 2024. doi: https://doi.org/10.3390/diagnostics14232763 [25] J. Ripolles-Melchor et al., “Hypotension prediction index: From reactive to predictive hemodynamic management, the key to maintaining hemodynamic stability,” Frontiers in Anesthesiology, vol. 2, p. 1138175, Apr. 13, 2023. doi: https://doi.org/10.3389/fanes.2023.1138175 [26] M. Mollura, L. W. Lehman, R. G. Mark, and R. Barbieri, “A novel artificial intelligence based intensive care unit monitoring system: Using physiological waveforms to identify sepsis,” Philosophical Transactions of the Royal Society A, vol. 379, no. 2212, p. 20200252, Dec. 13, 2021. doi: https://doi.org/10.1098/rsta.2020.0252 [27] F. S. Alamri, T. Sadad, A. S. Almasoud, R. A. Aurangzeb, and A. Khan, “Mango disease detection using fused vision transformer with ConvNeXt architecture,” Computers, Materials & Continua, vol. 83, no. 1, Apr. 1, 2025. doi: https://doi.org/10.32604/cmc.2025.061890 [28] Y. Li et al., “Advances in the application of AI robots in critical care: Scoping review,” Journal of Medical Internet Research, vol. 26, p. e54095, May 27, 2024. doi: https://doi.org/10.2196/54095 [29] C. Stylianides et al., “AI advances in ICU with an emphasis on sepsis prediction: An overview,” Machine Learning and Knowledge Extraction, vol. 7, no. 1, p. 6, Jan. 8, 2025. doi: https://doi.org/10.3390/make7010006 [30] J. Gao, Y. Lu, N. Ashrafi, I. Domingo, K. Alaei, and M. Pishgar, “Prediction of sepsis mortality in ICU patients using machine learning methods,” BMC Medical Informatics and Decision Making, vol. 24, no. 1, p. 228, Aug. 16, 2024. doi: https://doi.org/10.1186/s12911-024-02630-z [31] S. Chen, J. Fan, E. Pishgar, K. Alaei, G. Placencia, and M. Pishgar, “XGBoost-based prediction of ICU mortality in sepsis-associated acute kidney injury patients using MIMIC-IV database with validation from eICU database,” medRxiv, Feb. 25, 2025. doi: https://doi.org/10.1101/2025.02.24.25322816 [32] D. Syed et al., “Deep learning-based short-term load forecasting approach in smart grid with clustering and consumption pattern recognition,” IEEE Access, vol. 9, pp. 54992–55008, Apr. 8, 2021. doi: https://doi.org/10.1109/ACCESS.2021.3071654 [33] P. Hadweh et al., “Machine learning and artificial intelligence in intensive care medicine: Critical recalibrations from rule-based systems to frontier models,” Journal of Clinical Medicine, vol. 14, no. 12, p. 4026, Jun. 6, 2025. doi: https://doi.org/10.3390/jcm14124026 [34] J. R. Teoh, J. Dong, X. Zuo, K. W. Lai, K. Hasikin, and X. Wu, “Advancing healthcare through multimodal data fusion: A comprehensive review of techniques and applications,” PeerJ Computer Science, vol. 10, p. e2298, Oct. 30, 2024. doi: https://doi.org/10.7717/peerj-cs.2298
Statistics Article View: 11 PDF Download: 5