The model gives a novel and effective automatic heartbeat classification/annotation in real-time with high accuracy, considering intar- and interpatient schemes and validated its performance using the MIT-BIH arrhythmia database by leveraging the ability of deep convolutional neural network and encoder-decoder network in which bidirectional recurrent neural network is used as its building blocks. The suggested method significantly outperforms the existing algorithms in the literature for both intar-patient paradigm and inter-patient paradigm. Furthermore, it can be applied to several biomedical applications such as sleep staging where there are strong dependencies between each stage and sufficient data are not available.
Input variables : ECG signals
Output Variables : Classified Arrhythmia
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : arxiv.org
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | March, 2019 |
| Healthcare Domain | : |
Medical Technology
Provider |
| Code | : | github.com |
| Health Risk Management |
| Disease Detection |