Dataset Information

A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets.

ABSTRACT: Arrhythmias can pose a significant threat to cardiac health, potentially leading to serious consequences such as stroke, heart failure, cardiac arrest, shock, and sudden death. In computer-aided electrocardiogram interpretation systems, the inclusion of certain classes of arrhythmias, which we term "aggressive" or "bullying," can lead to the underdiagnosis of other "vulnerable" classes. To address this issue, a method for arrhythmia diagnosis is proposed in this study. This method combines morphological-characteristic-based waveform clustering with Bayesian theory, drawing inspiration from the diagnostic reasoning of experienced cardiologists. The proposed method achieved optimal performance in macro-recall and macro-precision through hyperparameter optimization, including spliced heartbeats and clusters. In addition, with increasing bullying by aggressive arrhythmias, our model obtained the highest average recall and the lowest average drop in recall on the nine vulnerable arrhythmias. Furthermore, the maximum cluster characteristics were found to be consistent with established arrhythmia diagnostic criteria, lending interpretability to the proposed method.

SUBMITTER: Hu L

PROVIDER: S-EPMC10499877 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets.

Hu Lianting L Huang Shuai S Liu Huazhang H Du Yunmei Y Zhao Junfei J Peng Xiaoting X Li Dantong D Chen Xuanhui X Yang Huan H Kong Lingcong L Tang Jiajie J Li Xin X Liang Heng H Liang Huiying H

Patterns (New York, N.Y.) 20230712 9

Arrhythmias can pose a significant threat to cardiac health, potentially leading to serious consequences such as stroke, heart failure, cardiac arrest, shock, and sudden death. In computer-aided electrocardiogram interpretation systems, the inclusion of certain classes of arrhythmias, which we term "aggressive" or "bullying," can lead to the underdiagnosis of other "vulnerable" classes. To address this issue, a method for arrhythmia diagnosis is proposed in this study. This method combines morph ...[more]

PMID: 37720326

Similar Datasets

Project description:Food-derived nattokinase has strong thrombolytic activity and few side effects. In the field of medicine, nattokinase has been developed as an adjuvant drug for the treatment of thrombosis, and nattokinase-rich beverages and health foods have also shown great potential in the field of food development. At present, the poor thermostability of nattokinase limits its industrial production and application. In this study, we used several thermostability-prediction algorithms to predict nattokinase from Bacillus mojavensis LY-06 (AprY), and screened two variants S33T and T174V with increased thermostability and fibrinolytic activity. The t1/2 of S33T and T174V were 8.87-fold and 2.51-fold those of the wild type AprY, respectively, and their enzyme activities were also increased (1.17-fold and 1.28-fold, respectively). Although the thermostability of N218L was increased by 2.7 times, the fibrinolytic activity of N218L was only 73.3% of that of wild type AprY. The multiple-point mutation results showed that S33T-N218L and S33T-T174V-N218L variants lost their activity, and the T174V-N218L variant did not show any significant change in catalytic performance, while S33T-T174V increased its thermostability and activity by 21.3% and 24.8%, respectively. Although the S33T-T174V variant did not show the additive effect of thermostability, it combined the excellent transient thermostability of S33T with the better thrombolytic activity of T174V. Bioinformatics analysis showed that the overall structure of S33T and T174V variants tended to be stable, while the structure of S33T-T174V variant was more flexible. Local structure analysis showed that the increased rigidity of the active center region (positions 64-75) and the key loop region (positions 129-130, 155-163, 187-192, 237-241, and 268-270) determined the increased thermostability of all variants. In addition, the enhanced flexibility of S33T-T174V variant in the Ca1 binding region (positions 1-4, 75-82) and the peripheral region of the catalytic pocket (positions 210-216) may account for the inability to superpose its thermostability. We explored the effective strategy to enhance the thermostability of nattokinase, and the resulting variants have potential industrial production and application.

Project description:BackgroundAnimal models of cancer are useful to generate complementary datasets for comparison to human tumor data. Insertional mutagenesis screens, such as those utilizing the Sleeping Beauty (SB) transposon system, provide a model that recapitulates the spontaneous development and progression of human disease. This approach has been widely used to model a variety of cancers in mice. Comprehensive mutation profiles are generated for individual tumors through amplification of transposon insertion sites followed by high-throughput sequencing. Subsequent statistical analyses identify common insertion sites (CISs), which are predicted to be functionally involved in tumorigenesis. Current methods utilized for SB insertion site analysis have some significant limitations. For one, they do not account for transposon footprints - a class of mutation generated following transposon remobilization. Existing methods also discard quantitative sequence data due to uncertainty regarding the extent to which it accurately reflects mutation abundance within a heterogeneous tumor. Additionally, computational analyses generally assume that all potential insertion sites have an equal probability of being detected under non-selective conditions, an assumption without sufficient relevant data. The goal of our study was to address these potential confounding factors in order to enhance functional interpretation of insertion site data from tumors.ResultsWe describe here a novel method to detect footprints generated by transposon remobilization, which revealed minimal evidence of positive selection in tumors. We also present extensive characterization data demonstrating an ability to reproducibly assign semi-quantitative information to individual insertion sites within a tumor sample. Finally, we identify apparent biases for detection of inserted transposons in several genomic regions that may lead to the identification of false positive CISs.ConclusionThe information we provide can be used to refine analyses of data from insertional mutagenesis screens, improving functional interpretation of results and facilitating the identification of genes important in cancer development and progression.

Dataset Information

A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets.

Publications

A cardiologist-like computer-aided interpretation framework to improve arrhythmia diagnosis from imbalanced training datasets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets