Congestive Heart Failure (CHF) is one of the critical diseases among the patients who are admitted to the Intensive Care Unit (ICU) that has a significant prevalence and mortality rate. Hence, it is essential to identify the parameters that have a high impact on the death risk of congestive heart failure patients. Recognizing the relation between the clinical parameters and the death risk of congestive heart failure has a large impact on choosing better treatment. As the data of vital signs is time series, the variables, which are considered in our study, are age, gender, heart rate variability, systolic/diastolic blood pressure variability, the heart rate alarm, and systolic/diastolic blood pressure alarm. Multiple classification algorithms are applied in this study to classify the patients in high and low death risk based on the clinical parameters. Logistic Regression and Support Vector Machine with linear and polynomial kernel are the methods that are implemented in the study and also their results are compared to each other in terms of their accuracy to predict the risk of mortality among CHF patients. The dataset is applied in this study is the MIMIC-III database that includes comprehensive clinical data from tens of thousands of ICU patients.