P wave changes during exercise in normal subjects and in patients with hemodynamic evidence of left atrial overload

Exploiting exercise electrocardiography to improve early diagnosis of atrial fibrillation with deep learning neural networks

Atrial fibrillation (AF) is the most common type of sustained arrhythmia. It results from abnormal irregularities in the electrical performance of the atria, and may cause heart thrombosis, stroke, arterial disease, thromboembolism, and heart failure. Prior to the onset of atrial fibrillation, most people experience atrial cardiomyopathy which, if effectively managed, can be prevented from progressing to atrial fibrillation. Electrocardiogram (ECG) can show changes in the heartbeats, and is a common and painless tool to detect heart problems. P-waves in exercise ECGs change more drastically than those in regular ECG, and are more effective in the detection of atrial myocardial diseases. In this paper, we propose a deep learning system to help clinicians to early detect if a patient has atrial enlargement or fibrillation. Firstly, a Convolutional Recurrent Neural Network is employed to locate the P-waves in the patient's exercise ECGs taken in the exercise ECG test process. Relevant parameters are then calculated from the located P-waves. Then a Parallel Bi-directional Long Short-Term Memory Network is applied to analyze the obtained parameters and make a diagnosis for the patient. With our proposed deep learning system, the changes of P-waves collected in different phases in the exercise ECG test can be analyzed simultaneously to get more stable and accurate results. The system can take data of different length as input, and is also applicable to any number of ECG collections. We conduct various experiments to show the effectiveness of our proposed system. We also show that the more ECG data collected in the exercise phase are involved, the more effective our system is in diagnosis of the diseases.

Limited utility of interatrial block in predicting ischemia on coronary angiography in patients with suboptimal exercise performance

INTRODUCTION

Interatrial block (P waves > or = 110 ms) is thought to be associated with underlying myocardial ischemia during exercise but has not been extensively investigated in patients with suboptimal or borderline exercise tolerance tests (< 3 min exercise). We utilized coronary angiography to assess the relationship of both, the resting baseline and exercise induced increase in P-wave duration with coronary artery disease among patients who had undergone such tests.

METHODS

We prospectively identified 51 consecutive patients with interatrial block who had coronary artery disease and hypertension but not atrioventricular valvular heart disease, and had undergone coronary angiography to evaluate myocardial ischemia after a suboptimal exercise tolerance test. A control group of 64 consecutive exercise tolerance test patients with similar preliminary characteristics but without interatrial block at rest was used for comparison. Patients from both groups were then appraised for significant obstructive lesions (> 70%) on coronary angiography that were suggestive of myocardial ischemia.

RESULTS

Obstructive coronary artery lesions suggestive of myocardial ischemia were more frequent among interatrial block patients but this was not statistically significant (p=0.25). However, change in P-wave duration of > 20 ms occurred more frequently in interatrial block patients in the presence of a positive exercise tolerance test. Among patients without interatrial block at baseline, more patients who developed new interatrial block had significant disease on coronary angiography.

CONCLUSION

The utility of using interatrial block toward predicting myocardial ischemia among patients with suboptimal exercise tolerance tests is limited. However, further investigation on the early change in P-wave duration in patients with interatrial block and the development of new interatrial block during exercise could be helpful in optimizing exercise tolerance tests, particularly when borderline or suboptimal.

Interatrial block during exercise tolerance tests as an additional parameter for the diagnosis of ischemic heart disease

INTRODUCTION

Interatrial block (IAB; P-wave duration, >or=120 milliseconds) is associated with increases of left atrial pressure. We studied the use of IAB during exercise tolerance test (ETT) in diagnosis of ischemic heart disease.

METHOD

Exercise tolerance tests were performed in 149 patients (mean age, 50 years; male, 60.4%). P-wave duration was measured at rest, at each stage of exercise using the Bruce protocol, and in recovery. As clinically indicated, 71 patients subsequently underwent nuclear stress test and/or catheterization. The evidence of ischemia (EOI) was considered present according to the more definite test, that is, catheterization over nuclear stress test over ETT.

RESULTS

Among patients who did not have IAB at rest (n=115), 63 patients (54.7%) developed IAB during the ETT. The incidence of IAB during the ETT was higher in patients with EOI than patients without EOI (88.9% vs 51.9%, P=.03). When IAB during the ETT and positive ETT were used together to detect EOI, they were more accurate (86.1% vs 81.7%) than the ETT alone. Among patients with IAB at rest (n=34), patients with EOI had a higher incidence of P-wave duration increase of more than 20 milliseconds during the recovery period than patients without EOI (100% vs 21.8%, P=.015). When using P-wave duration increase of more than 20 milliseconds during the recovery period in conjunction with positive ETT, the sensitivity in detecting EOI was higher than using the ETT alone (100% vs 0%), but the specificity was worsened (68.8% vs 84.4%).

CONCLUSION

New IAB and worsening of IAB during ETT appeared in patients with ischemic heart disease and may be used as additional parameters for the ETT interpretation.

Exercise P-vector magnitude changes in angina pectoris: Frank-Vectorcardiographic and hemodynamic correlations

Multistage bicycle ergometer exercise testings with Frank vectorcardiogram and M-mode echocardiogram were performed on 12 patients with effort angina pectoris. The left atrial and left ventricular end-diastolic volume (LAV and LVEDV) were calculated as a cube of the left atrial and left ventricular end-diastolic dimension. The mean pulmonary artery wedge pressure (mPAWP) was measured with a Swan-Ganz catheter during the testing. At peak exercise a statistically significant increase was observed in mPAWP (p less than 0.001), LAV (p less than 0.005), the maximal horizontal P-vector magnitude (Hmax) (p less than 0.05) and the percent change in Hmax (%Hmax). %Hmax showed a significant correlation with the increment of mPAWP (delta mPAWP) (r = 0.66, p less than 0.05), the increment of LVEDV (delta LVEDV) (r = 0.83, p less than 0.01) and the increment of LAV (delta LAV) (r = 0.81, p less than 0.001). Multiple regression analysis was performed on %Hmax as a dependent variable with delta LAV, delta mPAWP, and the increment of heart rate (delta HR) as independent variables (r = 0.84, p less than 0.05), but the partial correlation coefficients of delta mPAWP and delta HR were not significant. The present study demonstrated that the increase in Hmax had a close relationship with the increase in mPAWP and LVEDV and that the preload of the left ventricle during exercise-induced anginal attack could be predicted noninvasively by %Hmax. The increase in Hmax was thought to be due to the increase in LAV during anginal attack.

Treadmill exercise test in children with cardiomyopathy and postmyocarditic myocardial hypertrophy

The treadmill exercise test with the Bruce protocol was performed in three patients with post-myocarditic myocardial hypertrophy (PMH) and ten patients with cardiomyopathy, including three with dilated cardiomyopathy (DCM), five with hypertrophic obstructive cardiomyopathy (HOCM), and two with hypertrophic and nonobstructive cardiomyopathy (HCM). The endurance time was below the normal level in all but one case and was normal or near normal in the three cases with PMH. ST depression was observed in five cases, none of which were of HCM. A marked increase in amplitude of the negative phase of the P wave in V1 was observed in one patient with DCM. The response of blood pressure during the exercise was abnormal in patients with DCM and HCM but was normal in PMH.