AN ARTIFICIAL NEURAL-NETWORK SYSTEM FOR DIAGNOSIS OF ACUTE MYOCARDIAL-INFARCTION (AMI) IN THE ACCIDENT AND EMERGENCY DEPARTMENT - EVALUATION AND COMPARISON WITH SERUM MYOGLOBIN MEASUREMENTS

Recent studies have confirmed that artificial neural networks (ANNs) a re adept at recognising patterns in sets of clinical data. The diagnos is of acute myocardial infarction (AMI) in patients presenting with ch est pain remains one of the greatest challenges in emergency medicine. The aim of this study was to evaluate the performance of an ANN train ed to analyse clinical data from chest pain patients. The ANN was comp ared with serum myoglobin measurements-cardiac damage is associated wi th increased circulating myoglobin levels, and this is widely used as an early marker for evolving AMI. We used 39 items of clinical and ECG data from the time of presentation to derive 53 binary inputs to a ba ck propagation network. On test data (200 cases), overall accuracy, se nsitivity, specificity and positive predictive value (PPV) of the ANN were 91.8, 91.2, 90.2 and 84.9% respectively. Corresponding figures us ing linear discriminant analysis were 81.0, 77.9, 82.6 and 69.7% (P < 0.01). Using a further test set from a different centre (91 cases), th e accuracy, sensitivity, specificity and PPV for the admitting physici ans were 65.1, 28.5, 76.9 and 28.6% respectively compared with 73.6, 5 2.4, 80.0 and 44.0% for the ANN. Although myoglobin at presentation wa s highly specific, it was only 38.0% sensitive, compared with 85.7% at 3 h. Simple strategies to combine clinical opinion, ANN output and my oglobin at presentation could greatly improve sensitivity and specific ity of AMI diagnosis. The ideal support for emergency room physicians may come from a combination of computer-aided analysis of clinical fac tors and biochemical markers such as myoglobin. This study demonstrate s that the two approaches could be usefully combined, the major benefi t of the decision support system being in the first 3 h before biochem ical markers have become abnormal. Copyright (C) 1997 Elsevier Science Ireland Ltd.