1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Proceedings
  5. Item

學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Early Detecting In-Hospital Cardiac Arrest Based on Machine Learning on Imbalanced Data
作者 邱淑怡
Chiu, Shu-i
Chang, Hsiao-Ko
Liu, Ji-Han
Lim, Wee Shin
Wang, Hui-Chih;Jang, Jyh-Shing Roger
貢獻者 資科系
關鍵詞 Cardiac arrest ; cardiopulmonary resuscitation ; imbalanced data classification ; machine learning ; prediction
日期 2019-06
上傳時間 26-Jan-2021 15:16:05 (UTC+8)
摘要 In-hospital cardiac arrest (IHCA) diminish the survival rate of patients, despite most of the IHCA cases are preventable. More than 54% IHCA patient had abnormal clinical manifestation before they suffered a cardiac arrest. If appropriate steps were taken, patients’ survival rate would be higher and medical expense would be decreased. This paper proposes a novel approach to detect IHCA before the event occurred. We construct two types of shifting windows (corresponding to two tasks) that allow machine learning to be applied for our dataset which is severely imbalanced. The results show that our approach can effectively handle the imbalanced dataset for detecting cardiac arrest. As the selection of performance index, we used the area under the receiver operating characteristic curve (AUROC) and the area under the precision–recall curve (AUPRC). In our experiments, the best classifier is random forest for task 1, with AUROC of 0.88. LSTM is the best for task 2, with AUPRC of 0.71 for the second task.
關聯 IEEE International Conference on Healthcare Informatics, China, pp.1-10
資料類型 conference
DOI http://doi.org/10.1109/ICHI.2019.8904504
dc.contributor 資科系
dc.creator (作者) 邱淑怡
dc.creator (作者) Chiu, Shu-i
dc.creator (作者) Chang, Hsiao-Ko
dc.creator (作者) Liu, Ji-Han
dc.creator (作者) Lim, Wee Shin
dc.creator (作者) Wang, Hui-Chih;Jang, Jyh-Shing Roger
dc.date (日期) 2019-06
dc.date.accessioned 26-Jan-2021 15:16:05 (UTC+8)-
dc.date.available 26-Jan-2021 15:16:05 (UTC+8)-
dc.date.issued (上傳時間) 26-Jan-2021 15:16:05 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/133774-
dc.description.abstract (摘要) In-hospital cardiac arrest (IHCA) diminish the survival rate of patients, despite most of the IHCA cases are preventable. More than 54% IHCA patient had abnormal clinical manifestation before they suffered a cardiac arrest. If appropriate steps were taken, patients’ survival rate would be higher and medical expense would be decreased. This paper proposes a novel approach to detect IHCA before the event occurred. We construct two types of shifting windows (corresponding to two tasks) that allow machine learning to be applied for our dataset which is severely imbalanced. The results show that our approach can effectively handle the imbalanced dataset for detecting cardiac arrest. As the selection of performance index, we used the area under the receiver operating characteristic curve (AUROC) and the area under the precision–recall curve (AUPRC). In our experiments, the best classifier is random forest for task 1, with AUROC of 0.88. LSTM is the best for task 2, with AUPRC of 0.71 for the second task.
dc.format.extent 1737440 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) IEEE International Conference on Healthcare Informatics, China, pp.1-10
dc.subject (關鍵詞) Cardiac arrest ; cardiopulmonary resuscitation ; imbalanced data classification ; machine learning ; prediction
dc.title (題名) Early Detecting In-Hospital Cardiac Arrest Based on Machine Learning on Imbalanced Data
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/ICHI.2019.8904504
dc.doi.uri (DOI) http://doi.org/10.1109/ICHI.2019.8904504