期刊文献+

基于机器学习组合优化方法的术后感染预测模型研究 被引量:3

Predicting Surgical Infections Based on Machine Learning
原文传递
导出
摘要 【目的】提高患者术后感染风险预测的准确性和有效性,探索基于机器学习组合预测方法建立术后感染预测模型。【方法】首先选择SMOTE、ADASYN和随机过采样三种采样技术以平衡数据集,然后结合5种常用机器学习模型生成多种预测组合,提出基于改进人工蜂群算法的采样技术与预测模型的混合预测方法,最后验证并比较多种组合预测方法的有效性。【结果】实证分析显示,采用人工蜂群算法组合策略方法下的混合模型的GM值和F1值分别达到0.791 2和0.669 3,相较于单一预测模型分别提升了15.15%和23.62%。【局限】模型需要在更大的SSI数据集层面进一步验证。【结论】基于人工蜂群组合优化方法的混合预测模型能够有效提高术后感染预测能力,尤其是对阳性患者的预测,为实际临床应用提供参考。 [Objective] This paper proposes a prediction model for post-operative infection based on a combined machine learning algorithm, aiming to effectively reduce surgical site infection risks. [Methods] First, we used SMOTE, ADASYN, and random oversampling to reduce the imbalance of the original data. Then, we combined five commonly used predictive models: Lasso, SVM, GBDT, ANN and RF to create a hybrid prediction method.Finally, we used the improved artificial bee colony algorithm to optimize the weight of multiple combinations.[Results] The G-mean and F1 values of the ABC combination strategy method reached 0.791 2 and 0.669 3 respectively, which were 15.15% and 23.62% higher than the existing ones. [Limitations] The sample size used in the study needs to be expanded. [Conclusions] The proposed model can effectively predict post-operative infections.
作者 苏强 侯校理 邹妮 Su Qiang;Hou Xiaoli;Zou Ni(School of Economics and Management,Tongji University,Shanghai 200092,China;Shanghai General Hospital,Shanghai 200240,China)
出处 《数据分析与知识发现》 CSSCI CSCD 北大核心 2021年第8期65-75,共11页 Data Analysis and Knowledge Discovery
基金 国家自然科学基金项目(项目编号:71972146,71974127)的研究成果之一。
关键词 手术部位感染 预测组合 人工蜂群算法 过采样 机器学习 Surgical Site Infection Forecast Combination Artificial Bee Colony Algorithm Oversampling Machine Learning
  • 相关文献

参考文献4

二级参考文献47

  • 1张建华,刘仲英.知识获取与求精RS-GA策略[J].同济大学学报(自然科学版),2004,32(6):822-826. 被引量:5
  • 2杨博,赵鹏飞.推荐算法综述[J].山西大学学报(自然科学版),2011,34(3):337-350. 被引量:87
  • 3董雷,周文萍,张沛,刘广一,李伟迪.基于动态贝叶斯网络的光伏发电短期概率预测[J].中国电机工程学报,2013,33(S1):38-45. 被引量:77
  • 4李雪峰,刘鲁,吴丽花.在线拍卖商品最终成交价格预测[J].计算机工程,2006,32(18):189-191. 被引量:6
  • 5Wood C A. What factors drive final price in Internet auctions? An empirical assessment of coin transactions on eBay[C]// Annual Convention of the Institute for Operations Research and the Management Sciences. Miami Beach, Fla, 2001.
  • 6Bryan D, Lucking-Reiley D, Prasad N, et al. Pennies from eBay: The determinants of price in online auctions[J]. Journal of Industrial Economics, 2007, 55(2): 223 233.
  • 7Kauffman J, Wood C A. The effects of shilling on final bid prices in online auctions[J]. Electronic Commerce Research and Applications, 2005(4): 21 34.
  • 8Srinivas K R, Mayukh D. Modeling on-line art auction dynamics using functional data analysis[J]. Statistical Science, 2006, 21(2): 179 193.
  • 9Wang S S, Jank W, Shmueli G. Explaining and forecasting online auction prices and their dynamics using functional data analysis[J]. Journal of Business & Economic Statistics, 2008, 26(2): 144-160.
  • 10Ghani R, Simmons H. Predicting the end-price of online auctions[C]//Proceedings of International Workshop on Data Mining and Adaptive Modelling Methods for Economics and Management Held in Conjunction with the 15th European Conference on Machine Learning. Italy: Pisa, 2004.

共引文献86

同被引文献56

引证文献3

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部