Title: Patient Survival Prediction with Machine Learning Algorithms

Abstract: In this study, the intensive care unit patient survival is predicted by machine learning algorithms according to the examinations performed in the first 24 hours. The data of intensive care patients collected from approximately two hundred hospitals over a period of one year were used. Algorithms are run in Python environment. Machine learning models were compared with the Cross-Validation method, and the random forest algorithm is used. The model made the prediction with 92,53% accuracy rate.

Keywords: Machine learning; intensive care unit; patient survival

Başlık: Makine Öğrenmesi Algoritmaları ile Hastanın Hayatta Kalım Tahmini

Özet: Bu çalışmada, yoğun bakım ünitelerinde yatan hastaların, ilk 24 saatte yapılan tetkiklerine göre hayatta kalma durumları makine öğrenmesi algoritmalarıyla tahmin edilmiştir. Çalışmada, bir yıllık süre zarfında yaklaşık iki yüz hastaneden toplanan yoğun bakım hastalarının verileri kullanılmıştır. Algoritmalar Python ortamında koşturulmuştur. Çapraz Doğrulama yöntemi ile makine öğrenmesi modelleri karşılaştırılmış, en iyi sonuç veren Rastgele Orman algoritması kullanılmıştır. Kullanılan model %92,53 doğruluk oranı ile tahminlemeyi gerçekleştirmiştir.

Anahtar kelimeler: Makine öğrenmesi; yoğun bakım; hayatta kalım

• Nielsen AB, Thorsen-Meyer HC, Belling K, Nielsen AP, Thomas CE, Chmura PJ, Lademann M, Moseley PL, Heimann M, Dybdahl L, Spangsege L, Hulsen P, Perner A, Brunak S. Survival prediction in intensive-care units based on aggregation of long-term disease history and acute physiology: A retrospective study of the Danish National Patient Registry and electronic patient records. The Lancet Digital Health 2019; 1(2): e78-e89.
• Hollinger A, Gayat E, Feliot E, Paugam-Burtz C, Fournier MC, Duranteau J, Lefrant JY, Leone M, Jaber S, Mebazaa A, Arrigo M. Gender and survival of critically ill patients: Results from the FROG-ICU study. Annals of Intensive Care 2019; 9(1): 43.
• Raffin TA Intensive care unit survival of patients with systemic illness. The American Review Respiratory Disease 1989; 140: S28-S35.
• Escher M, Ricou B, Nendaz M, Scherer F, Cullati S, Hudelson P, Perneger T. ICU physicians' and internists’ survival predictions for patients evaluated for admission to the intensive care unit. Annals of Intensive Care 2018; 8(1): 108.
• Simchen E, Sprung CL, Galai N, Zitser-Gurevich Y, Bar-Lavi Y, Levi L, Zveibil F, Mandel M, Mnatzaganian G, Goldschmidt N, Ekka-Zohar A, Weiss-Salz I. Survival of critically ill patients hospitalized in and out of intensive care. Critical Care Medicine 2007; 35(2): 449-457.
• Kaggle. WiDS Datathon, 2020. Retrieved from https://www.kaggle.com/c/widsdatathon2020/overview
• Seker SE. Is zekasi ve veri madenciligi. 1st edition, Cinius, 2000.
• Wu CL, Chau KW, Li YS. Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques. Water Resources Research 2009; 45(8).
• Browne MW. Cross-validation methods. Journal of Mathematical Psychology 2000; 44(1): 108-132.
• Wong TT. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition 2015; 48(9): 2839-2846.
• Akar O, Gungor O. Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation 2012; 1(2): 139-146.
• Tagil S. Change of habitat fragmentation and quality in the balıkesir plain and its surroundings with landscape pattern metrics (1975-2000). Ekoloji 2006; 60: 24-36.
• Townsend JT. Theoretical analysis of an alphabetic confusion matrix. Perception & Psychophysics 1971; 9(1): 40-50.