Algorithm for the automatic computation of the modified Anderson–Wilkins acuteness score of ischemia from the pre-hospital ECG in ST-segment elevation myocardial infarction

Abstract

BackgroundThe acuteness score (based on the modified Anderson–Wilkins score) estimates the acuteness of ischemia based on ST-segment, Q-wave and T-wave measurements obtained from the electrocardiogram (ECG) in patients with ST Elevation Myocardial Infarction (STEMI). The score (range 1 (least acute) to 4 (most acute)) identifies patients with substantial myocardial salvage potential regardless of patient reported symptom duration. However, due to the complexity of the score, it is not used in clinical practice. Therefore, we aimed to develop a reliable algorithm that automatically computes the acuteness score. MethodsWe scored 50 pre-hospital ECGs from STEMI patients, manually and by the automated algorithm. We assessed the reliability test between the manual and automated algorithm by interclass correlation coefficient (ICC) and Bland–Altman plot. ResultsThe ICC was 0.84 (95% CI 0.72–0.91), P<0.0001. The mean difference between manual and automated acuteness score was 0.17±0.66. In only two cases, there was a major disagreement between the two scores. There was an excellent agreement between the scores for the remaining 48 ECGs, all within the upper (1.46) and lower (−1.12) limits of agreement. ConclusionIn conclusion, we have developed an automated algorithm for measurement of the modified Anderson–Wilkins ECG acuteness score from the pre-hospital ECG in STEMI patients. This automated algorithm is highly reliable, can be applied in daily practice for research purposes and may be implemented in commercial automated ECG analysis programs to achieve practical use for decision support in the acute phase of STEMI.