The development of a neural network-based ambulatory ECG monitor

The number of hospital cardiac referrals and the delay to appropriate treat ment could potentially be reduced by the use of new technology which enable s the primary care provider to carry out a long term cardiac examination. T he technology uses neural computing techniques in a portable battery powere d unit to analyse a patient's electrocardiogram (ECG) in real time. At the end of the examination the unit is connected directly to a printer to provi de a detailed report of the findings. The report can be used as the basis f or a referral decision. This paper describes the development of the device and studies carried out to evaluate the performance of the technology emplo yed by the unit. The device employs a panel of Kohonen neural networks toge ther with conventional processing and is embedded in a custom 32 bit micro- controller circuit powered by four AA cells. The first study examined 26 mi nute ECG traces from 67 individuals comprising cardiac in-patients, rehabil itation patients and healthy subjects and compared the results of arrhythmi c analysis with a total of five cardiologist's interpretations. The results show that the technology is at least as good as the cardiologists, averagi ng 96% accuracy compared to an average of 89.25% for the cardiologists. The second study employed 24 hour ECG monitoring using the device on 121 patie nts reporting to General Practitioners with possible cardiac symptoms and e xamined the effect of using the device on subsequent cardiac referrals. The results showed a reduction of 50% in the number of referrals and a 65% red uction in waiting time for those patients still referred.