engleski

Comparison Of Three Artificial Intelligence Algorithms For Sepsis Prediction

Sepsis is the most severe consequence of bac- terial infections, in other words, a potentially life-threatening condition. During infection, some components of the innate immune response can, under certain circumstances, cause multiple organ dysfunction and tissue damage. Fortunately, timely treatment can prevent the consequences. The algorithms used to solve the problem of predicting sep-sis occurrence are Support-Vector Machine (SVM), K- Nearest Neighbors (KNN) and Ar-tificial Neural Network (ANN). The dataset used for this research consists of 23 different medical parameters for each patient, which is the total of 2277 data-points. For each of the aforementioned algorithms, different combi- nations of parameters were examined as well as different types of kernel functions (SVM), architectures (ANN), and number of nearest neighbors (KNN). The experimental results showed that the ANN approach achieves the highest AUC value (0.992) compared to the other approaches like SVM and KNN. (PDF) Comparison of Three Artificial Intelligence Algorithms for Sepsis Prediction. Available from: https://www.researchgate.net/publication/344152 372_Comparison_of_Three_Artificial_Intelligence _Algorithms_for_Sepsis_Prediction [accessed Sep 07 2020].

Sepsis, Artificial Neural Networks, Support Vector Machines, K-Nearest Neigh-bors

nije evidentirano