Diagnostic performance of 18-leads electrocardiography to distinguish takotsubo syndrome and acute anterior myocardial infarction

Background Electrocardiographic (ECG) features on acute phase of Takotsubo syndrome (TTS) is recognized to mimic that of acute anterior myocardial infarction (ant AMI). However, the difference of synthesized 18-leads ECG of both diseases was not elucidated. Purpose To elucidate diagnostic performance of 18-leads ECG to distinguish TTS and acute anterior AMI. Methods We firstly enrolled consecutive 40 patients of TTS, and among 500 ant AMI patients, one to two matching was done by their age and gender. Finally, 40+80 patients (74.5±11.2 years, 87 females) were enrolled, and ECG at onset of both group was estimated. Because of multicollinearity, all significant differences were compared by machine learning (Random Forest method). Results Prevalence of Q wave had no difference. Conversely, ST depression in TTS and ST elevation in ant AMI were significant differences in V7–9 leads. T-wave polarity of V3R-V9 leads were significantly different (flat T-wave in TTS and positive in ant AMI). Machine learning revealed T wave polarity in V7 lead had the highest feature importance. Conclusion 18-leads ECG at onset had powerful diagnostic performance to distinguish the two diseases. Funding Acknowledgement Type of funding source: None