Mekanik Ventilasyonda Yapay Zekâ ve Akıllı Destek Sistemleri
Özet
Bu çalışma, hızla gelişen bilgi teknolojilerinin ve yapay zekânın sağlık sistemindeki, özellikle yoğun bakımların temel araçlarından olan mekanik ventilasyon alanındaki önemini ve uygulamalarını incelemektedir. Solunum fonksiyonu bozulmuş hastalarda hayat kurtarıcı olan mekanik ventilasyon, uzadığı durumlarda yüksek enfeksiyon ve mortalite riskleri taşımaktadır. Yoğun bakımlardaki büyük hacimli hasta verilerinin klinisyenler tarafından hızlıca analiz edilmesi zor olduğundan, bilgisayarlı akıllı karar destek sistemleri (AKDS) hayati bir rol üstlenmektedir. Sistemlerin yapısı açık-döngü (danışmanlık) ve kapalı-döngü (otomatik kontrol) olmak üzere ikiye ayrılır. Kapalı-döngü sistemler, artefaktları temizleyen veri doğrulama algoritmalarıyla çalışarak ventilatörü doğrudan kontrol eder. AKDS'ler temel yapısı itibarıyla kurala dayalı, modele dayalı ve bu ikisinin kombinasyonu olan hibrit sistemler olarak üç grupta sınıflandırılır. Günümüzde SmartCare ve Adaptif Destek Ventilasyon (ASV) gibi ticari modeller, hastanın solunum parametrelerini otomatik ayarlayarak ventilatörden ayrılma (weaning) süreçlerini hızlandırmakta ve bakım maliyetlerini düşürmektedir. Sonuç olarak yapay zekâ destekli bu sistemler, medikal hataları önleme, mortaliteyi azaltma ve hastaya özel optimal tedavi sağlama yönünde kritik öneme sahiptir. Mekanik ventilasyon teknolojileri her geçen gün tamamen otomasyona doğru ilerlemektedir.
This study examines the significance and applications of rapidly developing information technologies and artificial intelligence within the healthcare system, particularly in the field of mechanical ventilation, which is a core tool in intensive care units (ICUs). While mechanical ventilation is life-saving for patients with impaired respiratory functions, prolonged ventilation carries high risks of complications and mortality. Because it is challenging for clinicians to rapidly analyze vast volumes of patient data in ICUs, computerized intelligent decision support systems (IDSS) play a vital role. The structure of these systems is divided into open-loop (advisory) and closed-loop (automatic control) systems. Closed-loop systems operate with data validation algorithms that eliminate artifacts to directly control the ventilator. Based on their core structure, IDSS are classified into three main categories: rule-based, model-based, and hybrid systems combining both. Today, commercial models like SmartCare and Adaptive Support Ventilation (ASV) accelerate the weaning process and reduce care costs by automatically adjusting the patient's respiratory parameters. In conclusion, these AI-supported systems hold critical importance in preventing medical errors, reducing mortality, and providing patient-specific optimal treatment. Mechanical ventilation technologies are progressively moving toward full automation every day.
Referanslar
Esteban A et al. Characteristics and outcomes in adult patients receiving mechanical ventilation. Am Med Assoc. 2002;287(3):345-355
Tobin MJ . Mechanical ventilation. N Engl J Med. 1994;330(15):1056-1061
Melsen WG, Rovers MM, Koeman M, Bonten MJM. Estimating the atributable mortality of v, entilator-associated pneumonia from ramdomized prevention studies. Crit Care Med. 2011;39(12):2736-2742
Bekaert M et al. Attributable mortality of ventilator-associated pneumonia: a reappraisal using causal analysis. Am J Respir Crit Care Med. 2011;184(10):1133-1139
Mehta AB, Syeda SN, Wiener RS, Walkey AJ. Epidemiologyical trends in invasive mechanical ventilation in the United States: a population-based study. J Crit Care.2015;30(6):1217-1221
Wunsch H, Linde-Zwirble WT, Angus DC, Hartman ME, Milbrandt EB, Kahn JB, The epidemiology of mechanical ventilation use in the United States. Crit Care Med. 2010;38(10):1947-1953
Fleur T.Tehrani, James H.Roum. Intelligent decision support systems for mechanical ventilation. Artificial intelligence in medicine.2008;44:171-182
Chatburn R, El-Khatih M, Mireles-Cabodevilla E. A taxonomy for mechanical ventilation: 10 fundamental maxims. Respir. Care. 2014;59(11):1747-1763
Chatburn RL Mireles-Cabodevilla E. Closed-loop control of mechanical ventilation: description and classification of targeting schemes. Respir Care. 2011;56(1):85-102
Tehrani FT, Roum JH, FLEX: a new computerized system for mechanical ventilation. J Clin Monit Comput. 2008a;22(2):121-130
Tehrani FT, Roum JH. Intelligent decision support systems for mechanical ventilation. Artif Intell Med. 2008b;44(3):171-182
Esteban A, Frutos F, Tobin MJ, Alia I, Solsona JF, Valverdu I et al. Fort he Spanish Lung Failure Collaborative Group. A comparison of four methods of weaning patients from mechanical ventilation. The New England Journal of Medicine. 1995;332:345-50
Epstein SK, Ciubotaru RL. Independent effects of ethiology of failure and time to reintubation on outcome for patients failing extubation. American Journal of Respiratory and Critical Care Medicine. 1998;158: 489-93
Saura P, Blanch L, Mestre J, Valles J, Artigas A, Fernandez R. Clinical consequences of the implementation of a weaning protocol. Intensive Care Medicine. 1996;22:1052-6
Kolief MH, Shapiro SD, Silver P, St.John RE, Prentice D, Sauer S et al. A randomized controlled trial of protocol-directed versus physician-directed weaning from mechanical ventilation. Critical Care Medicine.1997; 25:567-74
Weavind L, Shaw AD, Feeley TW. Monitoring ventilator weaning-predictors of success. Journal of Clinical Monitoring and Computing. 2000;16:409-16
Tehrani Fleur T. (2020). Intelligent decision support for lung ventilation. In Elsevier Inc.. Control Application for Biomedical Engineering Systems(359-381). United States
Zadeh LA. The role of fuzzy logic in management of uncertanity in expert systems. Fuzzy Sets Syst.1983;11:199-227
Shortliffe E. Medical expert systems knowledge tools for physicians. West J Med. 1986;145:830-839
Tehrani FT, Abbasi S. A model-based decision support systems for critiquing mechanical ventilation treatments. J Clin Monit Comput. 2012;26(3):207-215
Fincham WF, Tehrani FT. A mathematical model of the human respiratory system. J Biomed Eng. 1983a;5(2):125-133
Tehrani FT. Mathematical analysis and computer stimulation of the respiratory system in the newborn infant. IEEE Trans Biomed Eng. 1993;40(5):475-481
Dojat M, Brochard L, Lemaire F, Harf A. A knowledge-based system for assisted ventilation of patients in intensive care units. Int J Clin Monit Comput. 1992;9(4):239-250
Lellouche F, Mancebo J, Jolliet P, Roeseler J, Schortgen F, Dojat M, Cabello B, Bouadma L, Rodriguez P, Maggiore S, Reynaert M, Mersmann S, Brochard L. A multicenter randomized trial of computer driven protocolized weaning from mechanical ventilation. Am J Respir Crit Care Med. 2006;174:894-900
Tehrani FT. Automatic control of an artificial respirator. In: Proceedings of the 13th Annual International Conference of IEEE Engineering in Medicine and Biology,pp. 1991a;1738-1739
Tehrani FT. Method and Apparatus for Controlling an Artificial Respirator, US Patent No.4,986,268, issued January 22. 1991b
Tehrani FT, Abbasi S. Evaluation of a computerized system for mechanical ventilation of infants. J Clin Monit Comput. 2009;23(2):93-104
