Brian Devine

Publications of Brian Devine

• Modification of ACC/ESC criteria for acute myocardial infarction.

  Authors: Peter W Macfarlane, David Browne, Brian Devine, Elaine Clark, Evan Miller, Jodat Seyal, David Hampton

  Journal of electrocardiology. 02/2004; 37 Suppl:98-103.

  The American College of Cardiology (ACC) and European Society of Cardiology (ESC) recently proposed criteria for acute ST elevation myocardial infarction (STEMI). These criteria were based on STjThe American College of Cardiology (ACC) and European Society of Cardiology (ESC) recently proposed criteria for acute ST elevation myocardial infarction (STEMI). These criteria were based on STj >0.1 mV in limbs leads and V4-V6, or STj >0.2 mV in V1 to V3 with criteria being met in two contiguous leads. The criteria were neither age nor sex dependent and the aim of the present study was to evaluate whether or not improved STEMI criteria that were age and gender dependent could be developed. A training set of 789 ECGs from patients presenting with chest pain due to cardiac and other causes was available for study. Revised criteria for STEMI were developed using these data as well as ECGs from a normal adult population of 859 males and 637 females. A test set of ECGs was available in the form of 1220 ECGs recorded from a separate hospital from patients presenting with chest pain. 248 patients had an acute myocardial infarction on the basis of conventional clinical criteria while 972 did not. There was an improvement in sensitivity using the new criteria compared to the old criteria from 41.5% to 46.7% while specificity improved from 96.0% to 98.5%. Specificity in normals improved from 92.6% to 99.8%. The conclusion drawn is that while the ACC/ESC criteria are simple to apply, they are not particularly specific and can be improved by being supplemented by other ECG measures and optimized for age and sex.

• Neural networks for classification of ECG ST-T segments

  Authors: Lars Edenbrandt, Brian Devine, Peter W. Macfarlane

  Journal of Electrocardiology.

  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 singlyThe 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.