Skip to main content

Advertisement

Table 2 Predictive performances of the CCU physician and the ANN.

From: An artificial neural network to safely reduce the number of ambulance ECGs transmitted for physician assessment in a system with prehospital detection of ST elevation myocardial infarction

  Sens Spec PPV NPV
Predicting STEMI     
ANN 0,95 (0,82-0,99) 0,68 (0,63-0,73) 0,18 (0,13-0,23) 0,99 (0,98-1,00)
CCU physician 0,74 (0,57-0,87) 0,98 (0,97-0,99) 0,76 (0,59-0,088) 0,98 (0,97-1,00)
ANN and CCU physician* 0,74 (0,57-0,87) 0,99 (0,98-1,0) 0,80 (0,63-0,92) 0,98 (0,97-0,99)
Predicting need of acute PCI     
ANN 0,97 (0,85-1,0) 0,68 (0,63-0,72) 0,17 (0,12-0,23) 1,0 (0,98-1,00)
CCU physician 0,78 (0,61-0,90) 0,98 (0,97-0,99) 0,76 (0,59-0,89) 0,98 (0,97-0,99)
ANN and CCU physician* 0,78 (0,61-0,90) 0,99 (0,98-1,0) 0,80 (0,63-0,92) 0,98 (0,97-0,99)
  1. Sens; sensitivity, Spec; specificity, PPV; positive predictive value, NPV; negative predictive value *Theoretical diagnostic performances if only ECGs in which the ANN predicted STEMI were to be transmitted to the CCU physician.