Open AccessICU Patient Prediction for Moving with Decision Tree C4.5 and Naïve Bayes Algorithm
Author(s) -
Sumpena Sumpena,
Yuma Akbar,
Nirat Nirat,
Mario Hengky
Publication year - 2019
Publication title -
sinkron
Language(s) - English
Resource type - Journals
eISSN - 2541-2019
pISSN - 2541-044X
DOI - 10.33395/sinkron.v4i1.10150
Subject(s) - decision tree , bayes' theorem , naive bayes classifier , intensive care unit , intensive care , computer science , tree (set theory) , data mining , medicine , algorithm , decision tree learning , machine learning , artificial intelligence , medical emergency , emergency medicine , intensive care medicine , mathematics , bayesian probability , support vector machine , mathematical analysis
Critical patients need intensive care and supervision by the medical team in the Intensive Care Unit (ICU), including ventilators, monitors, Central Venous Pressure (CVP), Electrocardiogram (ECG), Echocardiogram (ECHO), medical supply, and medical information that is fast, precise, and accurate. In the ICU treatment room requires data that needs to be processed and analyzed for decision making. This study analyzed the ventilator, CVP and also Sepsis Diagnosis related to the data of moving patients and patients dying. This study also uses the decision tree algorithm C.45 and Naive Bayes to determine the level of accuracy of patient care and supervision information in the ICU. The results showed that the decision tree algorithm C.45 has an accuracy of 81.55% and Naive Bayes of 81.54%. The decision tree C.45 algorithm has almost the same advantages as the Naive Bayes algorithm.