Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data. / Precisión diagnóstica mejorada para la imagen de perfusión miocárdica usando redes neuronales artificiales en diferentes variables de entrada incluyendo datos clínicos y de cuantificación.

OBJECTIVE: Diagnostic accuracy of myocardial perfusion imaging (MPI) is not optimal to predict the result of angiography. The current study aimed at investigating the application of artificial neural network (ANN) to integrate the clinical data with the result and quantification of MPI. METHODS: Out of 923 patients with MPI, 93 who underwent angiography were recruited. The clinical data including the cardiac risk factors were collected and the results of MPI and coronary angiography were recorded. The quantification of MPI polar plots (i.e. the counts of 20 segments of each stress and rest polar plots) and the Gensini score of angiographies were calculated. Feed-forward ANN was designed integrating clinical and quantification data to predict the result of angiography (normal vs. abnormal), non-obstructive or obstructive coronary artery disease (CAD), and Gensini score (≥10 and <10). The ANNs were designed to predict the results of angiography using different combinations of data as follows: reports of MPI, the counts of 40 segments of stress and rest polar plots, and the count of these 40 segments in addition to age, gender, and the number of risk factors. The diagnostic performance of MPI with different ANNs was compared. RESULTS: The accuracy of MPI to predict the result of angiography, obstructive CAD, and Gensini score increased from 81.7% to 92.9%, 65.0% to 85.7%, and 50.5% to 92.9%, respectively by ANN using counts and clinical risk factors. CONCLUSION: The diagnostic accuracy of MPI could be improved by ANN, using clinical and quantification data.

Hemodynamic effect of atrioventricular and interventricular dyssynchrony in patients with biventricular pacing: Implications for the pacemaker syndrome.

BACKGROUND/OBJECTIVES: Pacemaker syndrome was mainly described as the sequel of atrioventricular (AV) dyssynchrony. The role of interventricular (VV) dyssynchrony has not been studied yet. The aims of this study were to noninvasively assess the hemodynamic effects of different ventricular pacing sites with and without AV and VV dyssynchrony and to observe the patients for clinical symptoms of the pacemaker syndrome during the AV sequential and ventricular-only pacing modes. MATERIALS AND METHODS: Between March 2009 and February 2010, 40 patients (28 men; mean age, 61 ± 15 years) with biventricular (BiV) device were enrolled. Mean systolic and diastolic blood pressures (BP) of 5 beats were measured 5 minutes after each mode change using fingertip plethysmography. The patients were also observed for the occurrence of symptoms suggestive of the pacemaker syndrome, including dyspnea, palpitations, dizziness, presyncope, and syncope. RESULTS: There was no difference in mean systolic BP among different ventricular-only pacing modes (all P = NS). However, mean systolic BP was significantly higher in AV sequential biventricular pacing (DDD-BiV) compared with ventricular-only pacing modes (all P<0.05). In addition, there was no difference in terms of pacemaker syndrome-related symptoms following mode change from DDD-BiV to DDD-RV or DDD-LV (all P>0.05). CONCLUSIONS: The present study showed that the non-AV sequential BiV and LV pacing may have no significant benefit compared with RV pacing in terms of systolic blood pressure. However, there was marked hemodynamic improvement following mode change to AV sequential BiV pacing. This study may have important implications for pathogenesis of pacemaker syndrome.