Zastosowanie sztucznej inteligencji w wybranych stanach wymagających intensywnej terapii
Keywords:
sztuczna inteligencja, intensywna terapia, sepsa, wentylacja mechaniczna, udar mózguSynopsis
Abstrakt
Sztuczna inteligencja (AI) znajduje coraz szersze zastosowanie w medycynie, w tym w intensywnej terapii, gdzie szybkie i trafne decyzje terapeutyczne są kluczowe dla życia pacjentów. Niniejsza monografia przedstawia zastosowanie algorytmów AI w diagnostyce, prognozowaniu i wspomaganiu terapii pacjentów hospitalizowanych na oddziałach intensywnej terapii (OIT). Omówiono przykłady wykorzystania AI w takich stanach jak sepsa, ostre udary niedokrwienne mózgu, nagłe zatrzymanie krążenia oraz podczas wentylacji mechanicznej. Przedstawiono modele przewidujące ryzyko zgonu, sukces ekstubacji, wystąpienie delirium czy konieczność intubacji. Wyniki badań wskazują, że AI często przewyższa tradycyjne systemy oceny ryzyka pod względem czułości i swoistości. Pomimo że wiele modeli znajduje się jeszcze w fazie badań, ich potencjał kliniczny wydaje się bardzo obiecujący i może przyczynić się do poprawy jakości opieki nad pacjentami w stanie krytycznym.
Abstract
Artificial intelligence (AI) is increasingly used in medicine, including intensive care, where prompt and accurate therapeutic decisions are critical to patient survival. This monograph presents the application of AI algorithms in the diagnosis, prognosis, and treatment support of patients in intensive care units (ICUs). It discusses the use of AI in conditions such as sepsis, acute ischemic stroke, cardiac arrest, and during mechanical ventilation. The paper highlights models predicting mortality risk, extubation success, the occurrence of delirium, or the need for intubation. Research findings suggest that AI often outperforms traditional scoring systems in sensitivity and specificity. Although many of the described models are still under investigation, their clinical potential appears highly promising and may enhance the quality of care for critically ill patients.
References
Marshall JC, Bosco L, Adhikari NK, et al. What is an intensive care unit? A report of the task force of the World Federation of Societies of Intensive and Critical Care Medicine. J Crit Care. 2017;37:270-276. doi:10.1016/j.jcrc.2016.07.015
Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD). https://www.fda.gov/media/122535/ download. Accessed 20 Aug 2019.
Gutierrez G. Artificial Intelligence in the Intensive Care Unit [published correction appears in Crit Care. 2024 Mar 21;28(1):94. doi: 10.1186/s13054-024-04856-9.]. Crit Care. 2020;24(1):101. Published 2020 Mar 24. doi:10.1186/s13054-020-2785-y
Zaboli A, Brigo F, Sibilio S, et al. Evaluating the National Early Warning Score (NEWS) in triage: A machine learning perspective. Int Emerg Nurs. Published online March 29, 2025. doi:10.1016/j.ienj.2025.101602
Hu H, Li J, Ge H, et al. Prognostic models for unplanned intensive care unit readmission risk prediction: A systematic review and meta-analysis based on HSROC model. Nurs Crit Care. 2025;30(2):e13306. doi:10.1111/nicc.13306
Kumar V. Targeting macrophage immunometabolism: Dawn in the darkness of sepsis. Int Immunopharmacol. 2018;58:173-185. doi:10.1016/j.intimp.2018.03.005
Seymour CW, Liu VX, Iwashyna TJ, et al. Assessment of Clinical Criteria for Sepsis: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) [published correction appears in JAMA. 2016 May 24-31;315(20):2237. doi: 10.1001/jama.2016.5850.]. JAMA. 2016;315(8):762-774. doi:10.1001/jama.2016.0288
Rocheteau P, Chatre L, Briand D, et al. Sepsis induces long-term metabolic and mitochondrial muscle stem cell dysfunction amenable by mesenchymal stem cell therapy. Nat Commun. 2015;6:10145. Published 2015 Dec 15. doi:10.1038/ncomms10145
Huang M, Cai S, Su J. The Pathogenesis of Sepsis and Potential Therapeutic Targets. Int J Mol Sci. 2019;20(21):5376. Published 2019 Oct 29. doi:10.3390/ijms20215376
Shen X, Shang D, Sun W, Ru S. Machine learning approach for the prediction of 30-day mortality in patients with sepsis-associated delirium. PLoS One. 2025;20(4):e0319519. Published 2025 Apr 9. doi:10.1371/journal.pone.0319519
Mao F, Lin L, Liang D, et al. Machine Learning Approach for Sepsis Risk Assessment in Ischemic Stroke Patients. J Intensive Care Med. Published online January 9, 2025. doi:10.1177/08850666241308195
Liu S, Xu Q, Xu Z, et al. Reinforcement Learning to Optimize Ventilator Settings for Patients on Invasive Mechanical Ventilation: Retrospective Study. J Med Internet Res. 2024;26:e44494. Published 2024 Oct 16. doi:10.2196/44494
Park JE, Kim DY, Park JW, et al. Development of a Machine Learning Model for Predicting Weaning Outcomes Based Solely on Continuous Ventilator Parameters during Spontaneous Breathing Trials. Bioengineering (Basel). 2023;10(10):1163. Published 2023 Oct 5. doi:10.3390/bioengineering10101163
Liu CF, Hung CM, Ko SC, et al. An artificial intelligence system to predict the optimal timing for mechanical ventilation weaning for intensive care unit patients: A two-stage prediction approach. Front Med (Lausanne). 2022;9:935366. Published 2022 Nov 18. doi:10.3389/fmed.2022.935366
Lombardi R, Jozwiak M, Dellamonica J, Pasquier C. Using weak signals to predict spontaneous breathing trial success: a machine learning approach. Intensive Care Med Exp. 2025;13(1):34. Published 2025 Mar 18. doi:10.1186/s40635-025-00724-0
Cheng KH, Tan MC, Chang YJ, et al. The Feasibility of a Machine Learning Approach in Predicting Successful Ventilator Mode Shifting for Adult Patients in the Medical Intensive Care Unit. Medicina (Kaunas). 2022;58(3):360. Published 2022 Mar 1. doi:10.3390/medicina58030360
Bakkes T, van Diepen A, De Bie A, et al. Automated detection and classification of patient-ventilator asynchrony by means of machine learning and simulated data. Comput Methods Programs Biomed. 2023;230:107333. doi:10.1016/j.cmpb.2022.107333
Liu J, Duan X, Duan M, et al. Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unit. Sci Rep. 2024;14(1):27174. Published 2024 Nov 8. doi:10.1038/s41598-024-77798-5
Weizman O, Hamzi K, Henry P, et al. Machine learning score to predict in-hospital outcomes in patients hospitalized in cardiac intensive care unit. Eur Heart J Digit Health. 2024;6(2):218-227. Published 2024 Dec 20. doi:10.1093/ehjdh/ztae098
Ni P, Zhang S, Zhang G, et al. Development and validation of machine learning-based prediction model for outcome of cardiac arrest in intensive care units. Sci Rep. 2025;15(1):8691. Published 2025 Mar 13. doi:10.1038/s41598-025-93182-3
Hill CJ, Sykora CA, Schmugge S, et al. Eye movement detection using electrooculography and machine learning in cardiac arrest patients. Resuscitation. Published online March 22, 2025. doi:10.1016/j.resuscitation.2025.110577
Niu Y, Chen X, Fan J, et al. Explainable machine learning model based on EEG, ECG, and clinical features for predicting neurological outcomes in cardiac arrest patient. Sci Rep. 2025;15(1):11498. Published 2025 Apr 3. doi:10.1038/s41598-025-93579-0
Kim TJ, Suh J, Park SH, Kim Y, Ko SB. System for Predicting Neurological Outcomes Following Cardiac Arrest Based on Clinical Predictors Using a Machine Learning Method: The Neurological Outcomes After Cardiac Arrest Method. Neurocrit Care. Published online February 20, 2025. doi:10.1007/s12028-025-02222-3
Sacco RL, Kasner SE, Broderick JP, et al. An updated definition of stroke for the 21st century: a statement for healthcare professionals from the American Heart Association/American Stroke Association [published correction appears in Stroke. 2019 Aug;50(8):e239. doi: 10.1161/STR.0000000000000205.]. Stroke. 2013;44(7):2064-2089. doi:10.1161/STR.0b013e318296aeca
World Health Organization. Stroke (Cerebrovascular Accident). WHO - EMRO. Accessed April 12, 2025. https://www.emro.who.int/health-topics/stroke-cerebrovascular-accident/index.html
Rowland LP, Pedley TA, eds. Merritt’s Neurology. 14th ed. Volume 1. Wolters Kluwer; 2021.
Maeng JY, Sung J, Kim GH, Kim JW, Yum KS, Park S. Machine learning-based diagnostic model for stroke in non-neurological intensive care unit patients with acute neurological manifestations. Sci Rep. 2024;14(1):29610. Published 2024 Nov 28. doi:10.1038/s41598-024-80792-6
Cummins JA, Gerber BS, Fukunaga MI, Henninger N, Kiefe CI, Liu F. In-Hospital Mortality Prediction among Intensive Care Unit Patients with Acute Ischemic Stroke: A Machine Learning Approach. Health Data Sci. 2025;5:0179. Published 2025 Mar 17. doi:10.34133/hds.0179
Kim H, Kim M, Kim DY, Seo DG, Hong JM, Yoon D. Prediction of delirium occurrence using machine learning in acute stroke patients in intensive care unit. Front Neurosci. 2025;18:1425562. Published 2025 Jan 9. doi:10.3389/fnins.2024.1425562
Blum C, Single C, Laichinger K, et al. Retrospective analysis of amantadine response and predictive factors in intensive care unit patients with non-traumatic disorders of consciousness. Front Neurol. 2025;15:1512227. Published 2025 Jan 6. doi:10.3389/fneur.2024.1512227
Published
September 14, 2025
Copyright (c) 2025 Bartosz Bula, Maciej Baron, Andrzej Skrzypiec, Maciej Czwakiel, Magdalena Stencel
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
