Continuous-Valued Annotations Aggregation for Heart Rate Detection
In the medical field, experts usually annotate the bio-signals manually, and this is regarded as the gold standard. The manual annotating mode is time-consuming so widely replaced by an automated annotating algorithm. To address the low precision and low robustness of algorithm, we used a probabilis...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8657692/ |
| _version_ | 1819073677350666240 |
|---|---|
| author | Yuting Xie Jianqing Li Tingting Zhu Chengyu Liu |
| author_facet | Yuting Xie Jianqing Li Tingting Zhu Chengyu Liu |
| author_sort | Yuting Xie |
| collection | DOAJ |
| description | In the medical field, experts usually annotate the bio-signals manually, and this is regarded as the gold standard. The manual annotating mode is time-consuming so widely replaced by an automated annotating algorithm. To address the low precision and low robustness of algorithm, we used a probabilistic model to synthesize the heart rate (HR) annotations from multiple annotators for electrocardiograph (ECG) signals and inferred the underlying true annotations and the precision of each annotator when the ground truth was not available. We further introduced signal quality indices in the model to improve our estimation. The 100 noisy ECG recordings in 2014 PhysioNet/computing in cardiology challenge database were divided into two parts, and various annotations for HR were generated by six available annotators. By employing the expectation maximization algorithm, we obtained the estimated true annotations for 80 recordings, and this result had an improvement not only over the best single annotator (17.46%) used in this paper but also to the mean and median strategies (the highest of 23.12% and 42.23%). Furthermore, the estimated precision of the single annotator from the proposed model served as the weight of the test data. In independent test, the weighted average of multiple annotations was superior to the single annotator and the mean strategy on 20 recordings, and its root mean square error (14.22 bpm) was close to that (13.96 bpm) of the proposed model on 80 recordings, demonstrating the robustness of the proposed continuous-valued annotation aggregation model. |
| first_indexed | 2024-12-21T17:57:25Z |
| format | Article |
| id | doaj.art-9327f4b8283a4d539396b20a8aec6279 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T17:57:25Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9327f4b8283a4d539396b20a8aec62792022-12-21T18:55:10ZengIEEEIEEE Access2169-35362019-01-017376643767110.1109/ACCESS.2019.29026198657692Continuous-Valued Annotations Aggregation for Heart Rate DetectionYuting Xie0Jianqing Li1Tingting Zhu2https://orcid.org/0000-0002-1552-5630Chengyu Liu3https://orcid.org/0000-0003-1965-3020The State Key Laboratory of Bioelectronics, Jiangsu Key Laboratory of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaThe State Key Laboratory of Bioelectronics, Jiangsu Key Laboratory of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaDepartment of Engineering Science, University of Oxford, Oxford, U.K.The State Key Laboratory of Bioelectronics, Jiangsu Key Laboratory of Remote Measurement and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, ChinaIn the medical field, experts usually annotate the bio-signals manually, and this is regarded as the gold standard. The manual annotating mode is time-consuming so widely replaced by an automated annotating algorithm. To address the low precision and low robustness of algorithm, we used a probabilistic model to synthesize the heart rate (HR) annotations from multiple annotators for electrocardiograph (ECG) signals and inferred the underlying true annotations and the precision of each annotator when the ground truth was not available. We further introduced signal quality indices in the model to improve our estimation. The 100 noisy ECG recordings in 2014 PhysioNet/computing in cardiology challenge database were divided into two parts, and various annotations for HR were generated by six available annotators. By employing the expectation maximization algorithm, we obtained the estimated true annotations for 80 recordings, and this result had an improvement not only over the best single annotator (17.46%) used in this paper but also to the mean and median strategies (the highest of 23.12% and 42.23%). Furthermore, the estimated precision of the single annotator from the proposed model served as the weight of the test data. In independent test, the weighted average of multiple annotations was superior to the single annotator and the mean strategy on 20 recordings, and its root mean square error (14.22 bpm) was close to that (13.96 bpm) of the proposed model on 80 recordings, demonstrating the robustness of the proposed continuous-valued annotation aggregation model.https://ieeexplore.ieee.org/document/8657692/Annotation aggregationelectrocardiographheart rateground truthprobabilistic model |
| spellingShingle | Yuting Xie Jianqing Li Tingting Zhu Chengyu Liu Continuous-Valued Annotations Aggregation for Heart Rate Detection IEEE Access Annotation aggregation electrocardiograph heart rate ground truth probabilistic model |
| title | Continuous-Valued Annotations Aggregation for Heart Rate Detection |
| title_full | Continuous-Valued Annotations Aggregation for Heart Rate Detection |
| title_fullStr | Continuous-Valued Annotations Aggregation for Heart Rate Detection |
| title_full_unstemmed | Continuous-Valued Annotations Aggregation for Heart Rate Detection |
| title_short | Continuous-Valued Annotations Aggregation for Heart Rate Detection |
| title_sort | continuous valued annotations aggregation for heart rate detection |
| topic | Annotation aggregation electrocardiograph heart rate ground truth probabilistic model |
| url | https://ieeexplore.ieee.org/document/8657692/ |
| work_keys_str_mv | AT yutingxie continuousvaluedannotationsaggregationforheartratedetection AT jianqingli continuousvaluedannotationsaggregationforheartratedetection AT tingtingzhu continuousvaluedannotationsaggregationforheartratedetection AT chengyuliu continuousvaluedannotationsaggregationforheartratedetection |