RÉSUMÉ
This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonocardiographic (PCG) recordings. The proposed methodology aims to model the estimated TFRs, and extract relevant features to perform classification between normal and pathologic PCG recordings (with murmur). Modeling of TFR is done by means of SVR, and the distance between regressions is calculated through dissimilarity measures based on dot product. Finally, a k-nn classifier is used for the classification stage, obtaining a validation performance of 97.85%.
Sujet(s)
Souffles cardiaques/diagnostic , Phonocardiographie/statistiques et données numériques , Adulte , Intelligence artificielle , Génie biomédical , Études cas-témoins , Diagnostic assisté par ordinateur/statistiques et données numériques , Analyse de Fourier , Souffles cardiaques/classification , Souffles cardiaques/physiopathologie , Humains , Dynamique non linéaire , Analyse de régression , Traitement du signal assisté par ordinateurRÉSUMÉ
With the purpose to compare phonomechanocardiography and echo Doppler in the assessment of diastolic function of the left ventricle, we study 45 patients (30 male and 15 female) average age 50 +/- 9 years. We performed phonomechanocardiogram, echo-M, 2-D and Doppler transmitral. They were classified in four group according to mitral flow pattern: normal 14 patients; pattern I by Appleton (PI) 14 patients, 11 with aortic stenosis and 3 with hypertrophic cardiomyopathy; pattern II (PII) 12 patients with dilated cardiomyopathy grade III-IV and the last group of 5 patients with myocardial infarction with normal mitral flow but with impaired diastolic function by phonomechanocardiography. The phonomechanocardiographic index of ventricular relaxation (A2-O, ITRAT), compliance (a/D) and global diastolic function (ITAD) correlated with Doppler index (A2-D, E/A, atrial filling fraction, E-F slope and deceleration time) in N + PI group. The correlation was not significant when N + PI + PII or PI + PII groups were considered. The ITAD and E/A had r = 0.713 (p < 0.001) in N + PI, r = 0.12 (NS) in N + PI + PII and r = -0.308 (NS) in PI + PII. There was a dissociation between increased "a" wave in apexcardiogram and little "A" wave in PII patients suggesting "atrial failure". The patients with myocardial infarction received isosorbide dinitrate 5 mg showing changes of "pseudonormalizated" pattern in PI with normalized ITAD. This findings suggest that assessment of diastolic function by Doppler is dependent of loading conditions (specially preload), and cannot evaluate relaxation in PII but this is possible by phonomechanocardiography. It is advised the combination of the two technics for better assessment of diastolic function.