Dataset Information

Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding.

ABSTRACT: Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large number of possible label combinations and the imbalance among categories. Furthermore, the task of multi-label ECG classification is cost-sensitive, a fact that has usually been ignored in previous studies on the development of the model. To address these problems, in this work, we propose a novel deep learning model-based learning framework and a thresholding method, namely category imbalance and cost-sensitive thresholding (CICST), to incorporate prior knowledge about classification costs and the characteristic of category imbalance in designing a multi-label ECG classifier. The learning framework combines a residual convolutional network with a class-wise attention mechanism. We evaluate our method with a cost-sensitive metric on multiple realistic datasets. The results show that CICST achieved a cost-sensitive metric score of 0.641 ± 0.009 in a 5-fold cross-validation, outperforming other commonly used thresholding methods, including rank-based thresholding, proportion-based thresholding, and fixed thresholding. This demonstrates that, by taking into account the category imbalance and predefined cost information, our approach is effective in improving the performance and practicability of multi-label ECG classification models.

SUBMITTER: Liu Y

PROVIDER: S-EPMC8615597 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Lesion overlap difference maps have been used in studies designed to test anatomical hypotheses regarding brain systems critical for various cognitive and behavioral tasks, including naming and recognition of concrete entities [Damasio, H., Tranel, D., Grabowski, T., Adolphs, R., Damasio, A., 2004. Neural systems behind word and concept retrieval. Cognition 92, 179-229]. To date, the interpretation of these results has focused on areas of maximum lesion overlap differences. Here we explore formal methods for statistical thresholding and power analysis. We derive exact voxel-wise statistics describing the behavior of lesion overlap difference maps and lesion proportion difference maps under the null hypothesis of no association between lesion and deficit, and we apply the statistics to a large subset of the subjects previously reported in [Damasio, H., Tranel, D., Grabowski, T., Adolphs, R., Damasio, A., 2004. Neural systems behind word and concept retrieval. Cognition 92, 179-229], in order to reassess the lesion correlates of deficits in naming and recognition for five categories of concrete entities. The thresholded maps confirmed many of the results reported previously, but also revealed some differences. Differences in spatial distribution of the lesion correlates of impaired naming of unique versus nonunique entities were confirmed in the inferotemporal region (IT), although overlapping components across categories became apparent in left IT. Additionally, the left inferior frontal gyrus (IFG) was implicated in naming both categories of nonunique natural entities (animals and fruits/vegetables). In corresponding power analyses, we estimated where significant effects could be found under an assumption of maximal effect size given the observed spatial distribution of lesions. Such "effective coverage maps" are valuable for the interpretation of the results, notably because of heterogeneity in lesion coverage encountered in lesion studies. We strongly suggest that when inferential statistics are used in voxel-wise lesion-deficit statistical mapping, these or other power maps be included in the reports.

Project description:Data classification is a fundamental task in data mining. Within this field, the classification of multi-labeled data has been seriously considered in recent years. In such problems, each data entity can simultaneously belong to several categories. Multi-label classification is important because of many recent real-world applications in which each entity has more than one label. To improve the performance of multi-label classification, feature selection plays an important role. It involves identifying and removing irrelevant and redundant features that unnecessarily increase the dimensions of the search space for the classification problems. However, classification may fail with an extreme decrease in the number of relevant features. Thus, minimizing the number of features and maximizing the classification accuracy are two desirable but conflicting objectives in multi-label feature selection. In this article, we introduce a multi-objective optimization algorithm customized for selecting the features of multi-label data. The proposed algorithm is an enhanced variant of a decomposition-based multi-objective optimization approach, in which the multi-label feature selection problem is divided into single-objective subproblems that can be simultaneously solved using an evolutionary algorithm. This approach leads to accelerating the optimization process and finding more diverse feature subsets. The proposed method benefits from a local search operator to find better solutions for each subproblem. We also define a pool of genetic operators to generate new feature subsets based on old generation. To evaluate the performance of the proposed algorithm, we compare it with two other multi-objective feature selection approaches on eight real-world benchmark datasets that are commonly used for multi-label classification. The reported results of multi-objective method evaluation measures, such as hypervolume indicator and set coverage, illustrate an improvement in the results obtained by the proposed method. Moreover, the proposed method achieved better results in terms of classification accuracy with fewer features compared with state-of-the-art methods.

Dataset Information

Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets