INSTITUTO ARGENTINO DE MATEMATICA ALBERTO CALDERON
Unidad Ejecutora - UE
Vectorcardiographic and electrocardiographic analysis for identification of patients with myocardial infarction
CORREA L.; CORREA, RAUL; VALENTIBUZZI, MAXIMO E.; ARINI P.D.; LACIAR E.
METHODS OF INFORMATION IN MEDICINE
SCHATTAUER GMBH-VERLAG MEDIZIN NATURWISSENSCHAFTEN
Lugar: Stuttgart ; Año: 2016 vol. 55 p. 242 - 242
Background: The largest morbidityand mortality group worldwide continues to be that suffering Myocardial Infarction(MI). The use of vectorcardiography (VCG) and electrocardiography (ECG) hasimproved the diagnosis and characterization of this cardiac condition.Objective: Herein, weapplied a novel ECG-VCG combination technique to identifying 95 patients withMI and to differentiating them from 52 healthy reference subjects. Subsequently,and with a similar method, the location of the infarcted area permitted patientclassification. Methods: We analyzed 5depolarization and 4 repolarization indexes, say: (a) volume; (b) planar area;(c) QRS loop perimeter; (d) QRS vector difference; (e-g) Area under the QRScomplex, ST segment and T-wave in the (X, Y, Z) leads; (f) ST-T Vector MagnitudeDifference; (h) T-wave Vector Magnitude Difference; and (i) the spatial anglebetween the QRS complex and the T-wave.For classification, patients were divided into two groups according tothe infarcted area, that is, anterior or inferior sectors (MI-ant and MI-inf,respectively).Results: Our resultsindicate that several ECG and VCG parameters show significant differences(p-value<0.05) between Healthy and MI subjects, and between MI-ant andMI-inf. Moreover, combining five parameters, it was possible to classify the MIand healthy subjects with a sensitivity = 95.8%, a specificity = 94.2%, and anaccuracy = 95.2%, after applying a linear discriminant classifier method.Similarly, combining eight indexes, we could separate out the MI patients inMI-ant vs MI-inf with a sensitivity = 89.8%, 84.8%, respectively, and anaccuracy = 89.8%.Conclusions: The newmultivariable MI patient identification and localization technique, based, onECG and VCG combination indexes, offered excellent performance to differentiatingpopulations with MI from healthy subjects. Furthermore, this technique might beapplicable to estimating the infarcted area localization. In addition, theproposed method would be an alternative diagnostic technique in the emergencyroom.