ECG criteria to distinguish hypertrophic cardiomyopathy featured with "Pseudo-STEMI" from acute ST-elevation myocardial infarction.

BACKGROUD: The ECG profile of Hypertrophic Cardiomyopathy (HCM) includes ST-segment elevation (STE) that may lead to misdiagnosis of acute ST-segment elevation myocardial infarction (STEMI). This pseudo-STEMI may bring non-essential treatment. We aimed to confirm the ECG differences between HCM featured with pseudo-STEMI and acute STEMI. MATERIAL AND METHODS: We retrospectively enrolled 59 HCM cases (Group A) and 56 acute STEMI cases (Group B). Based on the locations of STE, all the patients were divided into four subgroups, including HCM with STE in anterior leads (Group A1), anterior STEMI (Group B1), HCM with STE in inferior leads (Group A2) and inferior STEMI (Group B2). Several ECG parameters were compared between these subgroups. RESULTS: ECG parameters significantly differed between these groups, especially the number of leads with TWI. We evaluated the diagnostic value of ECG profiles for those groups. ROC analysis showed that for Group A vs. Group B, number of leads with TWI showed the highest AUC value of 0.805 and its cutoff of 2.5, with 76.3% sensitivity and 76.8% specificity. For Group A1 vs. Group B1, it showed the highest AUC value of 0.801 and its cut-off point was 2.5, with 77.1% sensitivity and 79.1% specificity. For Group A2 vs. Group B2, it showed the highest AUC value of 0.822 and the cut-off value was 4.5, with 54.5% sensitivity and 92.3% specificity. CONCLUSION: ECG plays a valid tool to distinguish "Pseudo-STEMI" HCM from acute STEMI, especially number of leads with TWI.

A Robust and High-Dimensional Clustering Algorithm Based on Feature Weight and Entropy.

Since the Fuzzy C-Means algorithm is incapable of considering the influence of different features and exponential constraints on high-dimensional and complex data, a fuzzy clustering algorithm based on non-Euclidean distance combining feature weights and entropy weights is proposed. The proposed algorithm is based on the Fuzzy C-Means soft clustering algorithm to deal with high-dimensional and complex data. The objective function of the new algorithm is modified with the help of two different entropy terms and a non-Euclidean way of computing the distance. The distance calculation formula enhances the efficiency of extracting the contribution of different features. The first entropy term helps to minimize the clusters' dispersion and maximize the negative entropy to control the clustering process, which also promotes the association between the samples. The second entropy term helps to control the weights of features since different features have different weights in the clustering process. Experiments on real-world datasets indicate that the proposed algorithm gives better clustering results than other algorithms. The experiments demonstrate the proposed algorithm's robustness by analyzing the parameters' sensitivity and comparing the computational distance formulas. In summary, the improved algorithm improves classification performance under noisy interference and high-dimensional datasets, increases computational efficiency, performs well in real-world high-dimensional datasets, and encourages the development of robust noise-resistant high-dimensional fuzzy clustering algorithms.