混合多机器学习的ICU病人生死预测框架
ICU病人生死预测一直都是医学界的研究热点和难点。数据挖掘的机器学习方法近年来在该领域取得了一定的进展，但依然有很大的发展空间。针对ICU时序数据的高维度和不确定间隔采样特性，提出了不确定间隔采样转化为确定间隔的空采样的思想和相应的处理策略；在此基础上将传统的时间序列聚类与机器学习方法相结合，提出了一个两阶段的混合多机器学习算法框架，使得数据集的高维和不确定性得到了约简，从而可以采用经典的机器学习方法挖掘病人生死知识。在一个公开数据集上的两组实验结果表明，基于该算法框架的ICU病人死亡预测方法对于少数样本的分类效果优于传统方法，弹性时间间隔下的预测效果更好，最优时间间隔的选取可以通过实验效果来...
Saved in:
| Published in | 计算机科学与探索 Vol. 8; no. 11; pp. 1381 - 1390 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
南昌大学 软件学院,南昌,330047%江西警察学院,南昌,330100%南昌大学 信息工程学院,南昌,330031
2014
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1673-9418 |
| DOI | 10.3778/j.issn.1673-9418.1406016 |
Cover
| Abstract | ICU病人生死预测一直都是医学界的研究热点和难点。数据挖掘的机器学习方法近年来在该领域取得了一定的进展，但依然有很大的发展空间。针对ICU时序数据的高维度和不确定间隔采样特性，提出了不确定间隔采样转化为确定间隔的空采样的思想和相应的处理策略；在此基础上将传统的时间序列聚类与机器学习方法相结合，提出了一个两阶段的混合多机器学习算法框架，使得数据集的高维和不确定性得到了约简，从而可以采用经典的机器学习方法挖掘病人生死知识。在一个公开数据集上的两组实验结果表明，基于该算法框架的ICU病人死亡预测方法对于少数样本的分类效果优于传统方法，弹性时间间隔下的预测效果更好，最优时间间隔的选取可以通过实验效果来验证。 |
|---|---|
| AbstractList | ICU病人生死预测一直都是医学界的研究热点和难点。数据挖掘的机器学习方法近年来在该领域取得了一定的进展，但依然有很大的发展空间。针对ICU时序数据的高维度和不确定间隔采样特性，提出了不确定间隔采样转化为确定间隔的空采样的思想和相应的处理策略；在此基础上将传统的时间序列聚类与机器学习方法相结合，提出了一个两阶段的混合多机器学习算法框架，使得数据集的高维和不确定性得到了约简，从而可以采用经典的机器学习方法挖掘病人生死知识。在一个公开数据集上的两组实验结果表明，基于该算法框架的ICU病人死亡预测方法对于少数样本的分类效果优于传统方法，弹性时间间隔下的预测效果更好，最优时间间隔的选取可以通过实验效果来验证。 TP391; ICU病人生死预测一直都是医学界的研究热点和难点。数据挖掘的机器学习方法近年来在该领域取得了一定的进展，但依然有很大的发展空间。针对ICU时序数据的高维度和不确定间隔采样特性，提出了不确定间隔采样转化为确定间隔的空采样的思想和相应的处理策略；在此基础上将传统的时间序列聚类与机器学习方法相结合，提出了一个两阶段的混合多机器学习算法框架，使得数据集的高维和不确定性得到了约简，从而可以采用经典的机器学习方法挖掘病人生死知识。在一个公开数据集上的两组实验结果表明，基于该算法框架的ICU病人死亡预测方法对于少数样本的分类效果优于传统方法，弹性时间间隔下的预测效果更好，最优时间间隔的选取可以通过实验效果来验证。 |
| Abstract_FL | The mortality prediction of ICU patient has been an active topic in the past decades. Machine learning algo-rithms have been proved to have preliminary effects in this domain and still have room for improvement. In order to deal with the ICU time series which is both high dimensional and uncertain sampling interval, this paper proposes the idea that the unequal sampling frequency phenomenon in time series can be transferred to the empty value under the regular sampling frequency and corresponding strategies. Then, this paper proposes a two-step hybrid framework which combines the time series clustering and machine learning algorithm. In the first step, the dimension and uncertainty are reduced;in the second step, classical machine learning algorithms are conducted for mortality prediction of ICU patient. The experiments on a public data set show that the results of classifying the minority death patients are more efficient than the traditional solutions and the elastic interval is better. The selection for best time interval is validated by the experiments meanwhile. |
| Author | 张远健 徐健锋 涂敏 黄学坚 刘清 |
| AuthorAffiliation | 南昌大学软件学院,南昌330047 江西警察学院,南昌330100 南昌大学信息工程学院,南昌330031 |
| AuthorAffiliation_xml | – name: 南昌大学 软件学院,南昌,330047%江西警察学院,南昌,330100%南昌大学 信息工程学院,南昌,330031 |
| Author_FL | XU Jianfeng ZHANG Yuanjian LIU Qing HUANG Xuejian TU Min |
| Author_FL_xml | – sequence: 1 fullname: ZHANG Yuanjian – sequence: 2 fullname: XU Jianfeng – sequence: 3 fullname: TU Min – sequence: 4 fullname: HUANG Xuejian – sequence: 5 fullname: LIU Qing |
| Author_xml | – sequence: 1 fullname: 张远健 徐健锋 涂敏 黄学坚 刘清 |
| BookMark | eNo9zT1LAzEcBvAMFay130HcHO7MP0mT3CjFl0LBpc5HctfUOzXVRtHuVQQXB0Es4hsiLh21WL9O74rfwkLF6YGHH8-zgAq2bZsILQH2qRByNfUT56wPXFAvYCB9YJhj4AVU_O_mUdm5ROMKYwQEl0VE8-Ewu77MXvv5_Si7e88Gb-Ovp0m_V6vuTG7Px6PR5OYxH3z_vPTyj6v8-SJ_-FxEc0btu2b5L0uosbHeqG559e3NWnWt7kUciCcwFSoOpIlprLQSmEtlqDJCg-SUGFIBHGAtIh4pThgPtME6YCRgFGOqY1pCK7PZU2WNsq0wbZ907PQwTF26d9Y9dgQDA8BApnZ5ZqPdtm0dJVN92EkOVKcbck6EpJxQ-gtYI2cl |
| ClassificationCodes | TP391 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3778/j.issn.1673-9418.1406016 |
| DatabaseName | 维普期刊资源整合服务平台 中文科技期刊数据库-CALIS站点 中文科技期刊数据库-7.0平台 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitleAlternate | Hybrid Machine Learning Based Mortality Prediction Framework of ICU Patient |
| DocumentTitle_FL | Hybrid Machine Learning Based Mortality Prediction Framework of ICU Patient |
| EndPage | 1390 |
| ExternalDocumentID | jsjkxyts201411012 662783623 |
| GrantInformation_xml | – fundername: The National Natural Science Foundation of China under Grant No.61070139 |
| GroupedDBID | 2RA 92L ALMA_UNASSIGNED_HOLDINGS CQIGP M~E W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| ID | FETCH-LOGICAL-c612-7037ad98fd3daba7068af3af7b18632f251090b7c6ca62469bf0b942943003bd3 |
| ISSN | 1673-9418 |
| IngestDate | Thu May 29 04:00:16 EDT 2025 Thu Nov 14 02:55:54 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 11 |
| Keywords | uncertain time series 不确定时间序列 机器学习 混合框架 预测 prediction ICU machine learning hybrid framework |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c612-7037ad98fd3daba7068af3af7b18632f251090b7c6ca62469bf0b942943003bd3 |
| Notes | ZHANG Yuanjian, XU Jianfeng, TU Min, HUANG Xuejian, LIU Qing（ 1. Software College, Nanchang University, Nanchang 330047, China ;2. Jiangxi Police Institute, Nanchang 330100, China ;3. Information Engineering College, Nanchang University, Nanchang 330031, China） 11-5602/TP ICU; uncertain time series; prediction; machine learning; hybrid framework The mortality prediction of ICU patient has been an active topic in the past decades. Machine learning algorithms have been proved to have preliminary effects in this domain and still have room for improvement. In order to deal with the ICU time series which is both high dimensional and uncertain sampling interval, this paper proposes the idea that the unequal sampling frequency phenomenon in time series can be transferred to the empty value under the regular sampling frequency and corresponding strategies. Then, this paper proposes a two-step hybrid framework which combines the time series clustering and machine learning algorithm. In the first step, the dimension and u |
| PageCount | 10 |
| ParticipantIDs | wanfang_journals_jsjkxyts201411012 chongqing_primary_662783623 |
| PublicationCentury | 2000 |
| PublicationDate | 2014 |
| PublicationDateYYYYMMDD | 2014-01-01 |
| PublicationDate_xml | – year: 2014 text: 2014 |
| PublicationDecade | 2010 |
| PublicationTitle | 计算机科学与探索 |
| PublicationTitleAlternate | Egamer |
| PublicationTitle_FL | Journal of Frontiers of Computer Science & Technology |
| PublicationYear | 2014 |
| Publisher | 南昌大学 软件学院,南昌,330047%江西警察学院,南昌,330100%南昌大学 信息工程学院,南昌,330031 |
| Publisher_xml | – name: 南昌大学 软件学院,南昌,330047%江西警察学院,南昌,330100%南昌大学 信息工程学院,南昌,330031 |
| SSID | ssib054421768 ssib002040941 ssib002423894 ssib051375751 ssib023646573 ssib036438069 ssib002040926 |
| Score | 1.9411334 |
| Snippet | ... TP391;... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 1381 |
| SubjectTerms | ICU 不确定时间序列 机器学习 混合框架 预测 |
| Title | 混合多机器学习的ICU病人生死预测框架 |
| URI | http://lib.cqvip.com/qk/93336B/201411/662783623.html https://d.wanfangdata.com.cn/periodical/jsjkxyts201411012 |
| Volume | 8 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9RAdKj14kUUFWv9KOKcJDWTmczHMdnNUoV6aqG3JR-blgrbaregPXiqInjxIIhF_ELES49aXP9Od4v_wvcm2WSLFVphCS_zXt7HvGHee9nMDCG3klilHDJpRwgvd4TXEU4c51C15rmMdRoLyXCB8_x9Obco7i35SxOTN8a-WtrsJbPp1pHrSv7Hq9AGfsVVsifwbMUUGgAG_8IVPAzXY_mYRpKGCn-RT41LtUYgENQEiDINGgYWZWhQoJo0kDQSNIQWl0YKKbW421i0sKLat9jAPggtwKqFrODBMKQRPOUBvZXrUx1aFKNaWnERDeV4sksjTYMICYAVAMC_1gpagD87rJWmOkIauIIgoAkFAKNBgbRhwyquadhCTtCiGQ38QyQR9sUIg0qDGTqsSUB5EOFZZYCqVWMMWon2VUpB5zWhk8ZfjrD6taiV0hwZBto3SgcEquJx22oLUMuaGKLwmr-xzvFgpB_By2tw3KpMUc-3WjPrDY1WhQUwUhKYI-oEbBkez-0f0wCB8tCP0naqlQSjDntX4dDCkXASk8qQXARDqbhjRB0fN0drhMpox3hx3E6ZOUEx4R4VlblS2kZl5DpbcYUgbTcDqjOR6vvQ1Y3VB4-f9DbQpQx3oDtFTntKMfxmd_5pVOeXEILMeH2M9-LQQm1IyKuAg4clSL_O1-GWa1dW-bzPuML_Iat7mMCYKpbTjrQuvgZEk-78yyDcpmVlrbv8EJJPuxawm8fd5bG0deEcOVvWmzNBMXmcJxNbKxcIH-7tDV69GHzZGb7rD95-G-x-3f_58WBnGyaCgzfP9vv9g9cfhru_fn_eHn5_Ofz0fPj-x0Wy0IoWGnNOeXqKk0LV4kAkV3FmdJ7xLIYZ2ZU6znmcq4Rpyb0c6hrXuIlKZRpLT0iT5G5iIDsVOAqSjF8ik921bucymcmxjNJG5V7agepKG8j5szRjjHe0yWQyRaYre9vrxSY5bTxYQkN2zKfIzbIH2uXUudH-y79XjkM0Tc4gXLwAvUome482O9egJOgl1-2w-APM570M |
| linkProvider | ISSN International Centre |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E6%B7%B7%E5%90%88%E5%A4%9A%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E7%9A%84ICU%E7%97%85%E4%BA%BA%E7%94%9F%E6%AD%BB%E9%A2%84%E6%B5%8B%E6%A1%86%E6%9E%B6&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8E%A2%E7%B4%A2&rft.au=%E5%BC%A0%E8%BF%9C%E5%81%A5&rft.au=%E5%BE%90%E5%81%A5%E9%94%8B&rft.au=%E6%B6%82%E6%95%8F&rft.au=%E9%BB%84%E5%AD%A6%E5%9D%9A&rft.date=2014&rft.pub=%E5%8D%97%E6%98%8C%E5%A4%A7%E5%AD%A6+%E8%BD%AF%E4%BB%B6%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E6%98%8C%2C330047%25%E6%B1%9F%E8%A5%BF%E8%AD%A6%E5%AF%9F%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E6%98%8C%2C330100%25%E5%8D%97%E6%98%8C%E5%A4%A7%E5%AD%A6+%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E6%98%8C%2C330031&rft.issn=1673-9418&rft.issue=11&rft.spage=1381&rft.epage=1390&rft_id=info:doi/10.3778%2Fj.issn.1673-9418.1406016&rft.externalDocID=jsjkxyts201411012 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F93336B%2F93336B.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjkxyts%2Fjsjkxyts.jpg |