Acil Tıpta yapay zeka

Öz

Bu derleme, acil serviste yapay zekâ ve makine öğrenimi uygulamalarının triyaj, yatış kararları ve tıbbi görüntüleme alanlarındaki etkilerini güncel bilimsel çalışmaların bulgularına dayanarak özetlemektedir. Triyaj süreçlerinde elektronik sistemler ve derin öğrenme modelleri, manuel yöntemlere kıyasla kritik bakım ve hastaneye yatış gereksinimini daha doğru öngörmektedir. Yatış kararlarının desteklenmesinde doğal dil işleme teknikleri ve sinir ağı tabanlı modeller, erken kapasite planlamasını iyileştirerek kaynak kullanımını optimize etmektedir. Tıbbi görüntülemede derin öğrenme uygulamaları, bilgisayarlı tomografi ve radyografi incelemelerinde acil müdahale gerektiren bulguların daha hızlı saptanmasını sağlamaktadır. Genel olarak yapay zekâ ve makine öğrenimi tabanlı karar destek sistemleri, acil servislerde hız, doğruluk ve hasta güvenliğini artırma potansiyeline sahiptir; bu teknolojilerin yaygın klinik kullanımı için çok merkezli, ileriye dönük doğrulama çalışmaları ve entegrasyon süreçlerinin desteklenmesi gerekmektedir.

Anahtar Kelimeler

• Yapay zekâ
• makine öğrenimi
• acil servis
• triyaj
• yatış
• yoğun bakım
• tıbbi görüntüleme
• karar destek sistemi

Artificial intelligence in Emergency Medicine

Öz

This review summarizes current evidence on the impact of artificial intelligence and machine learning in triage, hospital admission decisions, and medical imaging within emergency departments. In triage, electronic systems and deep learning models outperform manual assessments in predicting the need for critical care and hospitalization. For admission decisions, natural language processing and neural network–based models enhance early capacity planning and optimize resource utilization. In medical imaging, deep learning applications accelerate the detection of urgent findings in computed tomography and radiography, improving diagnostic accuracy. Overall, artificial intelligence and machine learning-based decision support systems have the potential to improve speed, accuracy, and patient safety in emergency care; multicenter prospective validation studies and integration into clinical workflows are essential for widespread implementation.

Anahtar Kelimeler

• artificial intelligence
• machine learning
• emergency department
• triage
• admission
• intensive care
• medical imaging
• decision support system

Kaynakça

1. Almagharbeh HM, Alhamad H, Altarawneh M, et al. A scoping umbrella review of artificial intelligence applications in emergency medicine: Current evidence and future directions. J Am Coll Emerg Physicians Open. 2025;6(2):e13245.
2. Cameron A, Ibrahim A, McKay GA, Stark A, Lowe DJ. Predicting admission at triage: are nurses better than a simple objective score? Emerg Med J. 2017;34(1):2-7.
3. Levin S, Toerper M, Hamrock E, et al. Machine-learning-based electronic triage more accurately differentiates patients with respect to clinical outcomes compared with the emergency severity index. Ann Emerg Med. 2018;71(5):565-74.
4. Kwon J-M, Lee Y, Lee S, Park H, Park J. Validation of deep-learning-based triage and acuity score using a large national dataset. PLoS One. 2018;13(10):e0205836.
5. Sitthiprawat P, Wittayachamnankul B, Sirikul W, Laohavisudhi K. Development and internal validation of an AI-based emergency triage model for predicting critical outcomes in emergency department. Sci Rep. 2025;15:31212.
6. Choi A, Kim C, Ryoo J, et al. A pediatric emergency prediction model using natural language processing in the pediatric emergency department. Sci Rep. 2025;15:3574.
7. Chang YH, Lin YC, Huang FW, et al. Using machine learning and natural language processing in triage for prediction of clinical disposition in the emergency department. BMC Emerg Med. 2024;24:237.
8. Zlotnik A, Castaño AM, Pérez Pérez MC, Gallardo-Antolín A, Montero Martínez JM. Building a decision support system for inpatient admission prediction with the Manchester Triage System and administrative check-in variables. Comput Inform Nurs. 2016;34(5):224-30.

9. Zhang X, Kim J, Patzer RE, Pitts SR, Patzer A, Schrager JD. Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks. Methods Inf Med. 2017;56(5):377-89.
10. Handly N, Tennyson D, Li J, Chuirazzi DM, Venkat A. Evaluation of a hospital admission prediction model adding coded chief complaint data using neural network methodology. Eur J Emerg Med. 2015;22(2):87-91.
11. Das A, Ben-Menachem T, Cooper GS, et al. Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model. Lancet. 2003;362(9392):1261–6.
12. Prevedello LM, Erdal BS, Ryu JL, et al. Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology. 2017;285(3):923-31.
13. Li YH, Zhao L, Hu QM, Li HW, Jia FC, Wu JH. Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans. Int J Comput Assist Radiol Surg. 2012;7(4):507-16.
14. Yuh EL, Gean AD, Manley GT, Callen AL, Wintermark M. Computer-aided assessment of head computed tomography (CT) studies in patients with suspected traumatic brain injury. J Neurotrauma. 2008;25:1163-72.
15. Xiao F, Lee C, Huang KC, Chiang IJ, Wong JM. Automated assessment of midline shift in head injury patients. Clin Neurol Neurosurg. 2010;112:785-90.
16. Olczak J, Fahlberg N, Maki A, et al. Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms—are they on par with humans for diagnosing fractures? Acta Orthop. 2017;88:581-6.
17. Lindsey R, Daluiski A, Chopra S, et al. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A. 2018;115(45):11591–6.