Predicting Sepsis in the Intensive Care Unit (ICU) through Vital Signs using Support Vector Machine (SVM)

Background: As sepsis is one of the life-threatening diseases, predicting with high accuracy could help save lives. Methods: Efficiency and can be enhanced through optimal feature selection. In this work, a support vector machine model proposed to automatically predict patient’s risk based on physiological data collected from ICU. Results: The algorithm that uses extracted features has great impact prediction, which yields 0.73. Conclusion: Predicting accurately performed using main vital signs machine.