Brian Devine

Effects of age, sex, and race on ECG interval measurements

The effects of age, sex, and race on the electrocardiogram (ECG) were studied using three separate populations: a pediatric group of 1,782 neonates, infants, and children, and adult white group of 1,555 individuals, and an adult Chinese cohort of 503 individuals. All ECGs were processed using the same computer program, and various interval measurements were derived, including QRS duration, heart rate, QT dispersion, and selected Q-wave durations. Also, a small subgroup of 195 white subjects had a signal-averaged ECG recorded. In the pediatric group, there was a clear link between age and QRS duration, which increased linearly from about 1 year of age to adolescence. In the adults, the principal differences were an increased QRS duration in men compared with women both in the standard and signal-averaged ECG. Upper limits of normal heart rate also tended to be higher in women than in men in the two adult populations. Small racial differences could be seen in some measurements, but were not thought to be of clinical significance.

The university of glasgow (Uni-G) ECG analysis program

The University of Glasgow 12/15 lead ECG analysis program has been in continuous development for over 20 years. It has been adapted to meet the needs of different users and keep abreast of changes in terminology as well as new morphological features described in the literature. It is applicable to neonates as well as adults and takes account of racial variation in wave amplitudes. It has a capability for comparing serially recorded ECGs using one of two different approaches. The many varying features of the software have led to the introduction of the descriptor Uni-G (unique) ECG analysis program

Neural networks for classification of ECG ST-T segments

The usefulness of neural networks for pattern recognition in electrocardiographic (ECG) ST-T segments was assessed. Two thousand ST-T segments from the 12-lead ECG were visually classified singly into 7 different groups. The material was divided into a training set and a test set. Computer-measured ST-T data for each element in the training set, paired with the corresponding classification, was input to various configurations of software-based neural networks during a learning process. Thereafter, the networks correctly classified 90-95% of the individual ST-T segments in the test set. The importance of the size and composition of the training set in determining the performance of a network was clearly demonstrated. In conclusion, neural networks can be used for classification of ST-T segments. If carefully incorporated into a conventional ECG interpretation program, neural networks may well be of value for automated ECG interpretation in the near future.

Comparison of automated measurements of electrocardiographic intervals and durations by computer-based algorithms of digital electrocardiographs

BACKGROUND AND PURPOSE Automated measurements of electrocardiographic (ECG) intervals are widely used by clinicians for individual patient diagnosis and by investigators in population studies. We examined whether clinically significant systematic differences exist in ECG intervals measured by current generation digital electrocardiographs from different manufacturers and whether differences, if present, are dependent on the degree of abnormality of the selected ECGs. METHODS Measurements of RR interval, PR interval, QRS duration, and QT interval were made blindly by 4 major manufacturers of digital electrocardiographs used in the United States from 600 XML files of ECG tracings stored in the US FDA ECG warehouse and released for the purpose of this study by the Cardiac Safety Research Consortium. Included were 3 groups based on expected QT interval and degree of repolarization abnormality, comprising 200 ECGs each from (1) placebo or baseline study period in normal subjects during thorough QT studies, (2) peak moxifloxacin effect in otherwise normal subjects during thorough QT studies, and (3) patients with genotyped variants of congenital long QT syndrome (LQTS). RESULTS Differences of means between manufacturers were generally small in the normal and moxifloxacin subjects, but in the LQTS patients, differences of means ranged from 2.0 to 14.0 ms for QRS duration and from 0.8 to 18.1 ms for the QT interval. Mean absolute differences between algorithms were similar for QRS duration and QT intervals in the normal and in the moxifloxacin subjects (mean ≤6 ms) but were significantly larger in patients with LQTS. CONCLUSIONS Small but statistically significant group differences in mean interval and duration measurements and means of individual absolute differences exist among automated algorithms of widely used, current generation digital electrocardiographs. Measurement differences, including QRS duration and the QT interval, are greatest for the most abnormal ECGs.

Detection of electrocardiographic ‘left ventricular strain’ using neural nets

The use of artificial neural networks for classification of ST-T abnormalities of the electrocardiogram (ECG) was investigated. A training set of 356 lateral leads selected from 105 ECGs was visually classified as exhibiting one particular ST-T morphology (left ventricular (LV) strain) or not. Selected measurements, together with the classification, were fed as input to a three-layer software-based network during the learning process. The performance of the network was evaluated by comparing the results obtained from the network with conventional criteria, using two test sets. Set 1 comprised 63 lateral leads from 32 ECGs with ST-T changes showing atypical forms of LV strain. Set 2 consisted of 80 lateral leads from 20 ECGs containing normal and abnormal T-waves. For set 1, the network outperformed conventional criteria, having a higher sensitivity (96 per cent against 85 per cent) and specificity (67 per cent against 50 per cent). With test set 2, both network and conventional criteria were 100 per cent sensitive and 100 per cent specific. For sets 1 and 2 combined, the network had a higher overall sensitivity (97 per cent agaisst 89 per cent) and specificity (88 per cent against 82 per cent). The results suggest that neural networks may be useful in selected areas of electrocardiography, but care is required when selecting patterns for use in the training process.

Racial differences in the ECG — selected aspects

INTRODUCTION Racial differences in the ECG have been known about for many years but there has been no significant comparison of large population groups. This study set out to remedy this shortcoming. METHODS Digital ECG data were available for four population samples gathered in Scotland, Taiwan, Nigeria and India. All ECGs were recorded in the different countries and processed centrally by the University of Glasgow ECG Analysis Program. Measurements were analysed statistically to look for significant differences. RESULTS There were 4223 individuals in the study (2559 males and 1664 females). In general terms, findings such as QRS duration being longer in males than females applied to all four races. More specifically, QRS voltages were higher in young black males compared to others, while ST amplitudes, as in V2, were higher in Chinese and Nigerian males than in Caucasians. CONCLUSION Race requires to be taken into account to enhance automated interpretation of the ECG.

Use of artificial neural networks within deterministic logic for the computer ECG diagnosis of inferior myocardial infarction.

An investigation into the use of software-based artificial neural networks for the electrocardiographic (ECG) detection of inferior myocardial infarction was made. A total of 592 clinically validated subjects, including 208 with inferior myocardial infarction, 300 normal subjects, and 84 left ventricular hypertrophy cases, were used in this study. A total of 200 ECGs (100 from patients with inferior myocardial infarction and 100 from normal subjects) were fed to 66 supervised feedforward neural networks for training using a back-propagation algorithm. QRS and ST-T wave measurements were used as the input parameters for the neural networks. The best performing network using QRS measurements only and the best using QRS and ST-T data were selected by assessing a test set of 292 ECGs (108 from patients with inferior myocardial infarction, 84 from patients with left ventricular hypertrophy, and 100 from normal subjects). These two networks were then implanted separately into the deterministic Glasgow program for further study. After the implementation, it was found necessary to include a small inferior Q criterion to improve the specificity of reporting inferior myocardial infarction, thereby producing a small loss of sensitivity as compared with use of the network alone. The use of an artificial neural network within the deterministic logic performed better than either alone in the diagnosis of inferior myocardial infarction, producing a 20% gain in sensitivity with 2% loss in overall specificity compared with the original deterministic logic.

Normal limits of the electrocardiogram in Nigerians

BACKGROUND There has been no large study of ECG measures derived by automated methods in an apparently healthy indigenous West African population. METHODS ECGs were recorded from apparently healthy Nigerians and analysed using automated methods. Age and sex based normal ranges were then established. RESULTS A total of 782 males and 479 females aged between 20 and 87years were studied. Mean QRS duration in males was 87.9±9.4ms and 83.4±7.6ms in females (P<.0001). Mean QTc (Hodges) was 393±16ms in males and 406±16ms in females (P<.0001). The Cornell index (SV3+RaVL) was higher in males and decreased with increasing age in males though the reverse was true in females (P<.0001). STj amplitude was lower in older compared to younger males and higher in males. CONCLUSION This is the first large study of automated ECG measurements from healthy blacks living in West Africa which allows the determination of ECG normal limits in such a population.

Artificial neural networks for the diagnosis of atrial fibrillation

Different forms of artificial intelligence have been applied to pattern recognition in medicine. Recently, however, a relatively new technique involving software-based neural networks has become more readily available. Deterministic logic is currently applied to rhythm analysis in computer-assisted ECG interpretation method developed in the University of Glasgow. The aim of the present study is to compare an artificial neural network with deterministic logic for separating sinus rhythm (SR) with supraventricular extrasystoles (SVEs) and/or ventricular extrasystoles (VEs) from atrial fibrillation (AF) at a particular point in the diagnostic logic of the Glasgow Program. A total of 2363 ECGs with 1495 AF and 868 SR+(SVEs and/or VEs) are used for training and testing a variety of neural networks, and the optimum design is selected. Methods for combining the results of the neural-network classification and the deterministic interpretation are also developed. A further 717 ECGs are used to test the selected network. The results show that the use of an artificial neural network can improve the sensitivity of reporting AF from 88.5% using the deterministic approach to 92%, without sacrificing specificity (92.3%).

Evaluation of age and sex dependent criteria for ST elevation myocardial infarction

An evaluation of the Glasgow ECG analysis program criteria for acute ST elevation myocardial infarction (STEMI) was undertaken using two Board Certified cardiologists as the reference. Out of a data base of 1220 patients presenting with chest pain, 248 cases of confirmed MI were available for evaluation and 52 control cases were added from the remainder. The age and sex based Glasgow criteria were also assessed against existing ESC/ACC criteria. Irrespective of whichever way the criteria were evaluated, the Glasgow age and sex based criteria proved to have a superior performance compared to the non age and sex based criteria. The overall sensitivity of the Glasgow criteria was 89% in a set of 219 patients with an MI, of whom 113 had a cardiologist reported STEMI. Evaluation of specificity in this population is not meaningful. The corresponding ESC/ACC criteria evaluated by computer were 75% sensitive.