Decision tree-based learning to predict patient controlled analgesia consumption and readjustment.
Decision tree-based learning to predict patient controlled analgesia consumption and readjustment.
复制标题
DOI：
10.1186/1472-6947-12-131
复制
发表时间：
2012-11-14
影响因子：
3.5
通讯作者：
Yang SF
中科院分区：
文献类型：
--
作者：
Hu YJ;Ku TH;Jan RH;Wang K;Tseng YC;Yang SF
适当的术后疼痛管理有助于尽早活动、缩短住院时间并降低费用。疼痛治疗不足可能会阻碍短期康复，并对健康产生长期有害影响。本研究重点关注患者自控镇痛 (PCA)，这是一种止痛药物输送系统。本研究提出并演示了如何使用机器学习和数据挖掘技术来预测镇痛需求和 PCA 重新调整。本研究的样本包括 1099 名患者。每个患者都由 280 个属性描述，其中包括类别属性。除了普遍研究的人口和生理因素外，本研究还强调与 PCA 相关的属性。我们使用基于决策树的学习算法来根据 PCA 药物治疗的前几个小时来预测镇痛药用量和 PCA 控制调整。我们还开发了一种基于最近邻的数据清理方法来缓解 PCA 设置重新调整预测中的类不平衡问题。决策树集合对总镇痛药消耗量（连续剂量和 PCA 剂量）和 PCA 镇痛需求量（仅 PCA 剂量）的预测准确度分别为 80.9% 和 73.1%。基于决策树的学习在镇痛药用量预测方面优于人工神经网络、支持向量机、随机森林、旋转森林和朴素贝叶斯分类器。所提出的数据清理方法提高了 PCA 设置重新调整预测研究中每种学习方法的性能。比较分析确定了数据挖掘模型中的信息属性，并将其与先前工作中报告的镇痛需求的相关性进行比较。本研究展示了数据挖掘在麻醉学中的实际应用。与之前的研究不同，本研究考虑了更广泛的预测因素，包括随时间变化的 PCA 需求。我们分析了 PCA 患者数据并进行了多项实验，以评估应用机器学习算法协助麻醉师进行 PCA 管理的潜力。结果证明了所提出的术后疼痛管理整体方法的可行性。
Appropriate postoperative pain management contributes to earlier mobilization, shorter hospitalization, and reduced cost. The under treatment of pain may impede short-term recovery and have a detrimental long-term effect on health. This study focuses on Patient Controlled Analgesia (PCA), which is a delivery system for pain medication. This study proposes and demonstrates how to use machine learning and data mining techniques to predict analgesic requirements and PCA readjustment. The sample in this study included 1099 patients. Every patient was described by 280 attributes, including the class attribute. In addition to commonly studied demographic and physiological factors, this study emphasizes attributes related to PCA. We used decision tree-based learning algorithms to predict analgesic consumption and PCA control readjustment based on the first few hours of PCA medications. We also developed a nearest neighbor-based data cleaning method to alleviate the class-imbalance problem in PCA setting readjustment prediction. The prediction accuracies of total analgesic consumption (continuous dose and PCA dose) and PCA analgesic requirement (PCA dose only) by an ensemble of decision trees were 80.9% and 73.1%, respectively. Decision tree-based learning outperformed Artificial Neural Network, Support Vector Machine, Random Forest, Rotation Forest, and Naïve Bayesian classifiers in analgesic consumption prediction. The proposed data cleaning method improved the performance of every learning method in this study of PCA setting readjustment prediction. Comparative analysis identified the informative attributes from the data mining models and compared them with the correlates of analgesic requirement reported in previous works. This study presents a real-world application of data mining to anesthesiology. Unlike previous research, this study considers a wider variety of predictive factors, including PCA demands over time. We analyzed PCA patient data and conducted several experiments to evaluate the potential of applying machine-learning algorithms to assist anesthesiologists in PCA administration. Results demonstrate the feasibility of the proposed ensemble approach to postoperative pain management.
登录
查看更多内容
影响因子：
--
作者：
BELLVILL.JW;FORREST, WH;BROWEN, BW
通讯作者：
BROWEN, BW
影响因子：
7.4
作者：
Macintyre, PE;Jarvis, DA
通讯作者：
Jarvis, DA
影响因子：
7.4
作者：
Bisgaard, T;Klarskov, B;Kehlet, H
通讯作者：
Kehlet, H
DOI：
10.1007/bf03011838
发表时间：
1996-11-01
期刊：
CANADIAN JOURNAL OF ANAESTHESIA-JOURNAL CANADIEN D ANESTHESIE
影响因子：
--
作者：
Chung, F;Un, V;Su, J
通讯作者：
Su, J
影响因子：
3.5
作者：
Khalilia, Mohammed;Chakraborty, Sounak;Popescu, Mihail
通讯作者：
Popescu, Mihail