Abstract - The intensive care unit (ICU) is a complex and information rich department. Patients admitted to ICUs require close and continuous monitoring due to high illness severity and the potential for rapid disease progression. Early hospital mortality prediction is critical as intensivists strive to make efficient medical decisions about the severely ill patients staying in ICU. As a result, various methods have been developed to address this problem based on clinical records. With the development of techniques for data storage with the help of cloud, machine learning (ML) method have attracted considerable research attention with Random Forest (RF), decision tree (DT), k-nearest neighbor (KNN), Naïve Bayes (NB) which have a good performance. Medical information mart for intensive care (MIMIC benchmark dataset is used. In order to predict the risk, quantitative features have been computed based on the sensors like heart rate signals, humidity of ICU, body temperature of patients, equipment’s condition of ICU. Data were prepared and feature selection was processed under the supervision of the ICU equipment’s. Also, the system consists of a response button which helps to know about the cause of death. These results demonstrate the ability and efficiency of our approach to predict ICU mortality.
Index Terms - Intensive care unit, machine learning, dataset, sensors, response button, mortality prediction.
Copyright Form