Yapay Zekâ ve Rejyonal Anestezi
Özet
Rejyonal anestezi, 1884 yılında kokainin topikal kullanımıyla başlayan ve zamanla ultrasonografi ile robotik cihazların entegre edildiği hızlı bir gelişim süreci yaşamıştır. Geleneksel olarak palpasyon yardımıyla körlemesine yapılan nöroaksiyal girişimler; obezite, gebelik veya vertebra anomalileri gibi faktörler nedeniyle başarısızlıkla ve enfeksiyon, kanama ya da nörolojik hasar gibi komplikasyonlarla sonuçlanabilmektedir. Ultrasonografinin santral ve periferik bloklara dahil edilmesi başarı oranını artırıp yaralanmaları azaltsa da sonografik görüntülerin yorumlanması ciddi bir tecrübe gerektirmektedir. Bu zorluğu aşmak adına günümüzde yapay zeka destekli uygulamalar geliştirilmektedir. Yapay zeka ve makine öğrenimi algoritmaları, ultrasonografi görüntülerinde iğne giriş yeri, açısı ve derinliğini belirleme ile spinal seviyeleri ve sakrum gibi anatomik yapıları otomatik tanımlama imkanı sunmaktadır. Ayrıca makine öğrenimiyle hastaların klinik verileri işlenerek postoperatif sinir bloğu gereksinimleri tahmin edilebilmektedir. Robotik alanda ise iğne sürücü sistemler, floroskopi kılavuz yazılımları ve da Vinci ile Magellan gibi robotik kollar vasıtasıyla otomatik sinir blokları uygulanabilmektedir. Son dönemde geliştirilen yerli yazılım Nerveblox gibi sistemler hedef sinirleri gerçek zamanlı tespit ederek hem klinik uygulamalarda hem de eğitim süreçlerinde geçerli birer araç olduklarını kanıtlamışlardır. Henüz araştırma aşamasında olan bu teknolojiler, gelecekte tüm sürecin tam otomasyonla yapılmasına kapı aralamaktadır.
Regional anesthesia has undergone a rapid evolution since the first topical use of cocaine in 1884, moving toward the integration of ultrasonography and robotic devices. Traditional neuraxial interventions performed blindly via palpation can result in failures and complications—such as infection, bleeding, or neurological damage—due to factors like obesity, pregnancy, or vertebral anomalies. Although the introduction of ultrasonography in central and peripheral blocks increases success rates and reduces injuries, interpreting sonographic images demands significant expertise. To overcome this challenge, AI-assisted applications are currently being developed. AI and machine learning algorithms enable the determination of needle insertion sites, angles, and depths, while automatically identifying spinal levels and anatomical structures like the sacrum on ultrasound images. Furthermore, machine learning models process clinical data to predict postoperative nerve block requirements. In robotics, automated nerve blocks can be performed using robotic needle drivers, fluoroscopy-guided software, and systems like the da Vinci Surgical System or Magellan. Recently developed systems, such as the local software Nerveblox, detect target nerves in real time, proving to be valid tools in both clinical practice and training. Still in the research and development phase, these technologies pave the way for fully automated procedures in the near future.
Referanslar
Koller C. On the use of cocaine for producing anaesthesia on the eye. Lancet. 1884;2:990– 992.
Hall RJ. Hydrochlorate of cocaine. NY Med J. 1884;40:643–644.
Halsted WS. Practical comments on the use and abuse of cocaine; suggested by its invariably successful employment in more than a thousand minor surgical operations. N Y Med J. 1885; 42: 294–295.
Greenblatt GM, Denson JS. Needle nerve stimulatorlocator: nerve blocks with a new instrument for locating nerves. Anesth Analg. 1962;41:599-602.
Kapral S, Krafft P, Eibenberger K, et al. Ultrasound-guided supraclavicular approach for regional anesthesia of the brachial plexus. Anesth Analg. 1994;78(3):507-513.
Cleary K, Stoianovici D, Patriciu A, et al. Robotically assisted nerve and facet blocks: a cadaveric study. Acad Radiol. 2002;9(7):821-825.
Türk Dil Kurumu(2021). Zeka.(22.10.2021 tarihinde https://sozluk.gov.tr/. adresinden ulaşılmıştır).
Yılmaz, A. (2018). Yapay Zeka Nedir?. Gizem Aksan(Ed.), Yapay Zeka içinde (s. 4-6). İstanbul: Kodlab Yayın Dağıtım Yazılım LTD.ŞTİ.
Margarido CB, Mikhael R, Arzola C, et al. The intercristal line determined by palpation is not a reliable anatomical landmark for neuraxial anesthesia. Can J Anaesth. 2011;58(3):262–266.
Kim JT, Bahk JH, Sung J. Influence of age and sex on the position of the conus medullaris and Tuffier's line in adults. Anesthesiology. 2003;99(6):1359–1363.
Carvalho JC. Ultrasound-facilitated epidurals and spinals in obstetrics. Anesthesiol Clin. 2008;26(1):145–158.
Perlas A. Evidence for the use of ultrasound in neuraxial blocks. Reg Anesth Pain Med. 2010;35:43–46.
de Filho GR, Gomes HP, da Fonseca MH, et al. Predictors of successful neuraxial block: a prospective study. Eur J Anaesthesiol. 2002;19(6):447–451.
Lim YC, Choo CY, Tan KT. A randomised controlled trial of ultrasound-assisted spinal anaesthesia; Anaesth Intensive Care. 2014; 42(2):191–198.
Yu S, Tan KK, Sng BL, et al. Automatic identification of needle insertion site in epidural anesthesia with a cascading classified. Ultrasound Med Biol. 2014;40(9):1980–1990.
Yu S, Tan KK, Sng BL, et al.(2015). Real-time automatic spinal level identification with ultrasound image processing. IEEE 12th International Symposium on Biomedical Imaging (ISBI), 16-19 April, Brooklyn, NY, USA, pp. 243–246.
Oh TT, Ikhsan M, Tan KK, et al. A novel approach to neuraxial anesthesia: application of an automated ultrasound spinal landmark identification. BMC Anesthesiol. 2019;19(1):57.
Hetherington J, Lessoway V, Gunka V, et al. SLIDE: automatic spine level identification system using a deep convolutional neural network. Int J Comput Assist Radiol Surg. 2017;12(7):1189-1198.
Wu Z, Wang Y. Development of Guidance Techniques for Regional Anesthesia: Past, Present and Future. J Pain Res. 2021;14:1631-1641.
Li H, Wei H, Ma D, et al. Ultrasound and pressure-guided thoracic paravertebral block. Eur J Anaesthesiol. 2020;37:824–826.
Rafii-Tari H, Lessoway VA, Kamani AA, et al. Panorama Ultrasound for Navigation and Guidance of Epidural Anesthesia. Ultrasound Med Biol. 2015;41(8):2220-2231.
Yu S, Tan KK, Sng BL, Li S, Sia AT. Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine. Ultrasound Med Biol. 2015;41(10):2677-2689.
Tighe P, Laduzenski S, Edwards D,et al. Use of machine learning theory to predict the need for femoral nerve block following ACL repair. Pain Med. 2011;12(10):1566-1575.
Cleary K, Watson V, Lindisch D, et al. Precision placement of instruments for minimally invasive procedures using a ‘needle driver’ robot. Int J Med Robot Comp. 2005; 1:40–47.
Glozman D, Shoham M. Image-guided robotic flexible needle steering. IEEE Trans Robot. 2007; 23:459–467.
Tighe PJ, Badiyan SJ, Luria IBS, et al. Robot-assisted regional anesthesia: a simulated demonstration. Anesth Analg. 2010;111:813–816.
Morse J, Wehbe M, Taddei R, et al. Magellan: technical description of a new system for robot-assisted nerve blocks. J Comput. 2013;8:1401– 1405.
Wehbe M, Philippona C, Morse J, et al. (2012) Automated versus manual detection of the sciatic nerve. Anesthesiology 2012: American Society of Anesthesiologists (ASA) 2012 Annual Meeting, October 13 - 17, 2012, Washington, DC,USA.
Gungor I, Gunaydin B, Oktar SO, et al. A real-time anatomy ıdentification via tool based on artificial ıntelligence for ultrasound-guided peripheral nerve block procedures: an accuracy study. J Anesth. 2021;35(4):591-594.
Erdem G, Ermiş Y, Özkan D. Artificial intelligence-powered ultrasound guided regional nerve block in 3 patients: case report. Ağrı. Ahead of Print: AGRI-56887 | DOI: 10.14744/agri.2021.56887 .
Morse J, Terasini N, Wehbe M, et al. Comparison of success rates, learning curves, and inter-subject performance variability of robot-assisted and manual ultrasound-guided nerve block needle guidance in simulation. Br J Anaesth. 2014; 112:1092–1097.
