A sharp deterioration of the patient's condition against the backdrop of the development of life-threatening arrhythmias with symptoms of acute heart failure (AHF), multiple organ dysfunction syndrome (MODS) or cerebral edema (CE) can lead to the death of the patient. Since the known methods of automated diagnostics currently cannot accurately and promptly determine that the patient is in a life-threatening condition leading to the fatal outcome caused by AHF, MODS or CE, there is a need to develop appropriate methods. One of the ways to identify predictors of such a state is to apply machine learning methods to the collected datasets. In this article, we consider using data analysis methods to test the hypothesis that there is a predictor of death risk assessment, which can be derived from the previously obtained values of the ECG intervals, which gives a statistically significant difference for the ECG of the two groups of patients: those who suffered deterioration leading to the fatal outcome caused be MODS, AHF or CE, and those with favorable outcome. A method for unifying ECG data was proposed, which allow, based on the sequence of RR and QT intervals, to the construct of a number that is a characteristic of the patient's heart condition. Based on this characteristic, the patients are classified into groups: the main (patients with fatal outcome) and control (patients with favorable outcome). The resulting classification method lays the potential for the development of methods for identifying the patient's health condition, which will automate the detection of its deterioration. The novelty of the result lies in the confirmation of the hypothesis stated above, as well as the proposed classification criteria that allow solving the urgent problem of an automatic detection of the deterioration of the patient's condition.