Bo Hedén

Acute Myocardial Infarction Detected in the 12-Lead ECG by Artificial Neural Networks

BACKGROUND The 12-lead ECG, together with patient history and clinical findings, remains the most important method for early diagnosis of acute myocardial infarction. Automated interpretation of ECG is widely used as decision support for less experienced physicians. Recent reports have demonstrated that artificial neural networks can be used to improve selected aspects of conventional rule-based interpretation programs. The purpose of this study was to detect acute myocardial infarction in the 12-lead ECG with artificial neural networks. METHODS AND RESULTS A total of 1120 ECGs from patients with acute myocardial infarction and 10,452 control ECGs, recorded at an emergency department with computerized ECGs, were studied. Artificial neural networks were trained to detect acute myocardial infarction by use of measurements from the 12 ST-T segments of each ECG, together with the correct diagnosis. After this training process, the performance of the neural networks was compared with that of a widely used ECG interpretation program and the classification of an experienced cardiologist. The neural networks showed higher sensitivities and discriminant power than both the interpretation program and cardiologist. The sensitivity of the neural networks was 15.5% (95% confidence interval [CI], 12.4 to 18.6) higher than that of the interpretation program compared at a specificity of 95.4% (P<.00001) and 10.5% (95% CI, 7.2 to 13.6) higher than the cardiologist at a specificity of 86.3% (P<.00001). CONCLUSIONS Artificial neural networks can be used to improve automated ECG interpretation for acute myocardial infarction. The networks may be useful as decision support even for the experienced ECG readers.

Detection of frequently overlooked electrocardiographic lead reversals using artificial neural networks

Artificial neural networks can be used to recognize lead reversals in the 12-lead electrocardiogram at very high specificity, and the sensitivity is much higher than that of a conventional interpretation program. The neural networks developed in this and an earlier study for detection of lead reversals, in combination with an algorithm for the right arm/right foot lead reversal, would recognize approximately 75% of lead reversals encountered in clinical practice.

Artificial neural networks for the electrocardiographic diagnosis of healed myocardial infarction.

Artificial neural networks are computer-based expert systems that learn by example, in contrast to the currently used rule-based electrocardiographic interpretation programs. For the purpose of this study, 1,107 electrocardiograms (ECGs) from patients who had undergone cardiac catheterization were used to train and test neural networks for the diagnosis of myocardial infarction. Different combinations of QRS and ST-T measurements were used as input to the neural networks. In a learning process, the networks automatically adjusted their characteristics to correctly diagnose anterior or inferior wall myocardial infarction from the ECG. Two thirds of the ECGs were used in this process. Thereafter, the performance of the networks was studied in a separate test set, using the remaining third of the ECGs. The results from the networks were also compared with that of conventional electrocardiographic criteria. The sensitivity for the diagnosis of anterior myocardial infarction was 81% for the best network and 68% for the conventional criteria (p < 0.01), both having a specificity of 97.5%. The corresponding sensitivities of the network and the criteria for the diagnosis of inferior myocardial infarction were 78% and 65.5% (p < 0.01), respectively, compared at a specificity of 95%. The results indicate that artificial neural networks may be of interest in the attempt to improve computer-based electrocardiographic interpretation programs.

A modified Anderson-Wilkins electrocardiographic acuteness score for anterior or inferior myocardial infarction

BACKGROUND Optimal treatment of acute myocardial infarction (AMI) depends on the duration of the ischemia. The Anderson Wilkins (AW) electrocardiographic acuteness score has been shown to complement the historical timing in estimating the time interval from acute thrombotic coronary occlusion in patients presenting with chest pain and evolving myocardial infarction. The purposes of this study were to (1) compare the distributions of the previously developed AW acuteness score in a training population with either anterior or inferior AMI and (2) propose modifications to the formula to achieve distributions similar to the observed distributions of historical times from onset of pain. METHODS Two hundred three and 177 patients were included as training and testing population, respectively. All patients had an anterior or an inferior AMI and were without confounding factors on the electrocardiogram. RESULTS The training population had similar distributions of historical times from onset of pain, but differences in distributions of AW acuteness scores, between patients with anterior and inferior AMI (P <.0001). Eighty percent of the inferior AMI group had the highest possible AW acuteness score. Modification of a Q-wave criterion from > or =30 to > or =20 ms resulted in similar distributions in patients with anterior and inferior AMI both in the training and an independent testing population. CONCLUSIONS These results suggest that a modified AW acuteness score using a lower Q-wave duration criterion provides similar AMI timing information in patients with anterior and inferior locations. Clinical use of the AW acuteness score will only be practical if the calculation is automated.

The evaluation of an electrocardiographic myocardial ischemia acuteness score to predict the amount of myocardial salvage achieved by early percutaneous coronary intervention Clinical validation with myocardial perfusion single photon emission computed tomography and cardiac magnetic resonance.

BACKGROUND The time from symptom onset to reperfusion in acute myocardial infarction (MI) has been shown to be a poor predictor of patient outcome. Acute electrocardiographic (ECG) changes, however, have been shown useful for estimated acuteness of myocardial ischemia using the Anderson-Wilkins ECG ischemia acuteness score (AW-acuteness score). The aim was to study whether acute ischemic ECG changes can predict the amount of salvageable myocardium in patients with acute ST-elevation MI. METHODS Thirty-eight patients treated with primary percutaneous coronary intervention for first-time ST-elevation MI were retrospectively enrolled. Myocardium at risk (MaR) was determined by myocardial perfusion single photon emission computed tomography acutely or by T2-weighted cardiac magnetic resonance after 1 week, at the same time when final MI size was determined by late gadolinium enhancement. Myocardial salvage was calculated as (MaR - MI size)/MaR and compared with AW-acuteness score and time from symptom onset to primary percutaneous coronary intervention. RESULTS The AW-acuteness score correlated significantly with salvageable myocardium for right coronary artery (RCA) occlusions (r = -0.57; P = .02) but not for left anterior descending artery (LAD) occlusions (r = -0.04; P = .88). Time from symptom onset did not correlate with the amount of salvageable myocardium (LAD, r = 0.04 and P = .87; RCA, r = -0.40 and P = .13). CONCLUSIONS There is a moderate correlation between AW-acuteness score and salvageable myocardium in patients with acute RCA occlusion but not in patients with LAD occlusion.

Discrimination of ST deviation caused by acute coronary occlusion from normal variants and other abnormal conditions, using computed electrocardiographic imaging based on 12-lead ECG.

BACKGROUND Many graphical methods for displaying ST-segment deviation in the ECG have been tried for enhancing decision-making in patients with suspected acute coronary syndromes. Computed electrocardiographic imaging (CEI), based on a mathematical inverse solution, has been recently applied to transform ST-J point measurements made in conventional 12-lead ECG into a display of epicardial potentials in bulls-eye format. The purpose of this study is to assess utility of CEI in the clinical setting. METHODS In 99 patients with stable coronary disease, 12-lead ECGs were recorded during elective percutaneous coronary intervention (PCI), first before balloon-catheter insertion and then when an intracoronary balloon blocked blood supply to a region of myocardium for more than 4minutes (typically 5minutes). Four groups of patients were additionally studied, namely those with preexcitation, pericarditis, early repolarization syndrome (ERS), and left ventricular hypertrophy (LVH) with strain. Comparisons between performances of published criteria for ST-elevation myocardial infarction (STEMI) and quantitative as well as visual assessment of CEI images were based on sensitivities and specificities. RESULTS Visual assessment of CEI outperformed STEMI criteria. This was especially evident for the capability of detecting LCx occlusion with sensitivities for STEMI criteria=35% and for visual assessment of CEI by 2 physicians=71%, i. e. twice as many patients were correctly identified by CEI. False positive rates for CEI were low in patients with LVH with strain as well as with preexcitation for both methods. For pericarditis and ERS, visual as well as quantitative assessment of CEI performed better than STEMI criteria. CONCLUSION Visual assessment of CEI is a promising method for increasing the accuracy of ECG-based triage to PCI or conservative care.

Submaximal adenosine-induced coronary hyperaemia with 12 h caffeine abstinence: implications for clinical adenosine perfusion imaging tests.

Adenosine is widely used as a vasodilator agent in myocardial perfusion imaging. Caffeine inhibits the effect, but the time of caffeine abstinence needed is under discussion and varies from 12 to 24 h. Therefore, our aim was to examine whether the time of caffeine abstinence affects the hyperaemic response using quantification of coronary sinus flow (CSF) with cardiac magnetic resonance (CMR) during adenosine infusion.

Peak oxygen uptake in relation to total heart volume discriminates heart failure patients from healthy volunteers and athletes

BackgroundAn early sign of heart failure (HF) is a decreased cardiac reserve or inability to adequately increase cardiac output during exercise. Under normal circumstances maximal cardiac output is closely related to peak oxygen uptake (VO2peak) which has previously been shown to be closely related to total heart volume (THV). Thus, the aim of this study was to derive a VO2peak/THV ratio and to test the hypothesis that this ratio can be used to distinguish patients with HF from healthy volunteers and endurance athletes. Thirty-one patients with HF of different etiologies were retrospectively included and 131 control subjects (60 healthy volunteers and 71 athletes) were prospectively enrolled. Peak oxygen uptake was determined by maximal exercise test and THV was determined by cardiovascular magnetic resonance. The VO2peak/THV ratio was then derived and tested.ResultsPeak oxygen uptake was strongly correlated to THV (r2 = 0.74, p < 0.001) in the control subjects, but not for the patients (r2 = 0.0002, p = 0.95). The VO2peak/THV ratio differed significantly between control subjects and patients, even in patients with normal ejection fraction and after normalizing for hemoglobin levels (p < 0.001). In a multivariate analysis the VO2peak/THV ratio was the only independent predictor of presence of HF (p < 0.001).ConclusionsThe VO2peak/THV ratio can be used to distinguish patients with clinically diagnosed HF from healthy volunteers and athletes, even in patients with preserved systolic left ventricular function and after normalizing for hemoglobin levels.

Serial changes in the high-frequency ECG during the first year following acute myocardial infarction.

Background:  Previous studies have shown reduced high‐frequency QRS components (HF‐QRS) after acute myocardial infarction (MI). The purpose of this study was to investigate serial changes in HF‐QRS during the first year following acute MI.

Disappearance of myocardial perfusion defects on prone SPECT imaging: Comparison with cardiac magnetic resonance imaging in patients without established coronary artery disease

BackgroundIt is of great clinical importance to exclude myocardial infarction in patients with suspected coronary artery disease who do not have stress-induced ischemia. The diagnostic use of myocardial perfusion single-photon emission computed tomography (SPECT) in this situation is sometimes complicated by attenuation artifacts that mimic myocardial infarction. Imaging in the prone position has been suggested as a method to overcome this problem.MethodsIn this study, 52 patients without known prior infarction and no stress-induced ischemia on SPECT imaging were examined in both supine and prone position. The results were compared with cardiac magnetic resonance imaging (CMR) with delayed-enhancement technique to confirm or exclude myocardial infarction.ResultsThere were 63 defects in supine-position images, 37 of which disappeared in the prone position. None of the 37 defects were associated with myocardial infarction by CMR, indicating that all of them represented attenuation artifacts. Of the remaining 26 defects that did not disappear on prone imaging, myocardial infarction was confirmed by CMR in 2; the remaining 24 had no sign of ischemic infarction but 2 had other kinds of myocardial injuries. In 3 patients, SPECT failed to detect small scars identified by CMR.ConclusionPerfusion defects in the supine position that disappeared in the prone position were caused by attenuation, not myocardial infarction. Hence, imaging in the prone position can help to rule out ischemic heart disease for some patients admitted for SPECT with suspected but not documented ischemic heart disease. This would indicate a better prognosis and prevent unnecessary further investigations and treatment.