Assessment of the Post-Traumatic Damage of Myocardium in Patients with Combat Trauma Using a Data Mining Analysis of an Electrocardiogram

Goal of this study is to develop an objective assessment of the severity of the physical status of the wounded combatants based on ECG records using the system of comprehensive ECG scoring. Cluster analysis of module Data Mining (Statictica 10) was carried out to identify homogeneous subgroups in patients with combat trauma based on the composite indicators of functional states of the cardiovascular system. Data-mining analysis was carried out using the CART decision tree algorithm for these composite indicators. The best combination of ECG markers, including their possible discriminator limits for the assessment of the severity of damage and functional state of cardiovascular system was found by the classification and regression trees method. The percentage of correct classification was 76,2.