Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events
Accurate prediction of adverse cardiac events for the emergency department (ED) chest pain patients is essential in risk stratification due to the current ambiguity in diagnosing acute coronary syndrome. While most current practices rely on human decision by measuring clinical vital signs, computeri...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/86898 http://hdl.handle.net/10220/44244 |
| _version_ | 1811679942552846336 |
|---|---|
| author | Liu, Nan Sakamoto, Jeffrey Tadashi Cao, Jiuwen Koh, Zhi Xiong Ho, Andrew Fu Wah Lin, Zhiping Ong, Marcus Eng Hock |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Liu, Nan Sakamoto, Jeffrey Tadashi Cao, Jiuwen Koh, Zhi Xiong Ho, Andrew Fu Wah Lin, Zhiping Ong, Marcus Eng Hock |
| author_sort | Liu, Nan |
| collection | NTU |
| description | Accurate prediction of adverse cardiac events for the emergency department (ED) chest pain patients is essential in risk stratification due to the current ambiguity in diagnosing acute coronary syndrome. While most current practices rely on human decision by measuring clinical vital signs, computerized solutions are gaining popularity. We have previously proposed an ensemble-based scoring system (ESS). In this paper, we aim to extend the ESS system using extreme learning machine (ELM), a fast learning algorithm for neural networks. We recruited patients from the ED of Singapore General Hospital, and extracted features such as heart rate variability, 12-lead ECG parameters, and vital signs. We also proposed a novel algorithm called ESS-ELM to predict adverse cardiac events. Different from the original ESS algorithm, ESS-ELM uses the under-sampling technique only in model training. Our proposed method was compared to the original ESS algorithm and several clinical scores in predicting patient outcome. With a cohort of 797 recruited patients, we demonstrated that ESS-ELM outperformed the original ESS algorithm and three established clinical scores, namely HEART, TIMI, and GRACE, in terms of receiver operating characteristic analysis. Furthermore, we have investigated the impact of hidden node number and ensemble size on the predictive performance. ELM has demonstrated the flexibility in its integration with the ESS algorithm. Experiments showed the value of ESS-ELM in prediction of adverse cardiac events. Future works may include the use of new ELM-based learning methods and further validation with a new cohort of patients. |
| first_indexed | 2024-10-01T03:17:10Z |
| format | Journal Article |
| id | ntu-10356/86898 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:17:10Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/868982020-03-07T13:57:30Z Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events Liu, Nan Sakamoto, Jeffrey Tadashi Cao, Jiuwen Koh, Zhi Xiong Ho, Andrew Fu Wah Lin, Zhiping Ong, Marcus Eng Hock School of Electrical and Electronic Engineering Extreme Learning Machine Ensemble Learning Accurate prediction of adverse cardiac events for the emergency department (ED) chest pain patients is essential in risk stratification due to the current ambiguity in diagnosing acute coronary syndrome. While most current practices rely on human decision by measuring clinical vital signs, computerized solutions are gaining popularity. We have previously proposed an ensemble-based scoring system (ESS). In this paper, we aim to extend the ESS system using extreme learning machine (ELM), a fast learning algorithm for neural networks. We recruited patients from the ED of Singapore General Hospital, and extracted features such as heart rate variability, 12-lead ECG parameters, and vital signs. We also proposed a novel algorithm called ESS-ELM to predict adverse cardiac events. Different from the original ESS algorithm, ESS-ELM uses the under-sampling technique only in model training. Our proposed method was compared to the original ESS algorithm and several clinical scores in predicting patient outcome. With a cohort of 797 recruited patients, we demonstrated that ESS-ELM outperformed the original ESS algorithm and three established clinical scores, namely HEART, TIMI, and GRACE, in terms of receiver operating characteristic analysis. Furthermore, we have investigated the impact of hidden node number and ensemble size on the predictive performance. ELM has demonstrated the flexibility in its integration with the ESS algorithm. Experiments showed the value of ESS-ELM in prediction of adverse cardiac events. Future works may include the use of new ELM-based learning methods and further validation with a new cohort of patients. Accepted version 2018-01-03T04:44:12Z 2019-12-06T16:31:12Z 2018-01-03T04:44:12Z 2019-12-06T16:31:12Z 2017 Journal Article Liu, N., Sakamoto, J. T., Cao, J., Koh, Z. X., Ho, A. F. W., Lin, Z., et al. (2017). Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events. Cognitive Computation, 9(4), 545-554. 1866-9956 https://hdl.handle.net/10356/86898 http://hdl.handle.net/10220/44244 10.1007/s12559-017-9455-7 en Cognitive Computation © 2017 Springer. This is the author created version of a work that has been peer reviewed and accepted for publication by Cognitive Computation, Springer. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1007/s12559-017-9455-7]. 10 p. application/pdf |
| spellingShingle | Extreme Learning Machine Ensemble Learning Liu, Nan Sakamoto, Jeffrey Tadashi Cao, Jiuwen Koh, Zhi Xiong Ho, Andrew Fu Wah Lin, Zhiping Ong, Marcus Eng Hock Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title | Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title_full | Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title_fullStr | Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title_full_unstemmed | Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title_short | Ensemble-Based Risk Scoring with Extreme Learning Machine for Prediction of Adverse Cardiac Events |
| title_sort | ensemble based risk scoring with extreme learning machine for prediction of adverse cardiac events |
| topic | Extreme Learning Machine Ensemble Learning |
| url | https://hdl.handle.net/10356/86898 http://hdl.handle.net/10220/44244 |
| work_keys_str_mv | AT liunan ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT sakamotojeffreytadashi ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT caojiuwen ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT kohzhixiong ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT hoandrewfuwah ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT linzhiping ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents AT ongmarcusenghock ensemblebasedriskscoringwithextremelearningmachineforpredictionofadversecardiacevents |