Use of machine-learning classifiers to predict requests for preoperative acute pain service consultation.
Use of machine-learning classifiers to predict requests for preoperative acute pain service consultation.
复制标题
DOI：
10.1111/j.1526-4637.2012.01477.x
复制
发表时间：
2012-10
期刊：
影响因子：
--
通讯作者：
Bihorac A
中科院分区：
文献类型：
--
作者：
Tighe PJ;Lucas SD;Edwards DA;Boezaart AP;Aytug H;Bihorac A
该项目的目的是确定机器学习分类器是否可以预测哪些患者需要术前急性疼痛服务咨询。回顾性队列。大学教学医院。回顾了2010年1月1日至6月30日期间发布的9，860名手术患者的记录。急性疼痛服务咨询请求。根据其将手术病例分类为需要术前急性疼痛服务咨询请求的能力或能力，比较了一组机器学习分类器。分类器，然后利用集成技术进行优化。计算效率用模型训练所需的中央处理器处理时间来衡量。分类器进行了测试，使用完整的功能集，以及减少的功能集，使用基于优点的降维策略进行优化。机器学习分类器在所有手术病例中正确预测了92.3%（95%置信区间[CI]，91.8-92.8）的术前急性疼痛服务咨询请求。贝叶斯方法产生了最高的受试者工作曲线下面积（0.87，95% CI 0.84-0.89）和最低的训练时间（NaiveBayesUpdateable算法为0.0018秒，95% CI 0.0017-0.0019）。高性能机器学习分类器的集合并没有产生比其组件分类器更高的接收器操作曲线下面积。降维降低了多个分类器的计算要求，但并没有对分类性能产生不利影响。使用历史数据，机器学习分类器可以预测哪些手术病例应该提示术前急性疼痛服务咨询请求。降维提高了计算效率并保留了预测性能。
The purpose of this project was to determine whether machine-learning classifiers could predict which patients would require a preoperative acute pain service consultation. Retrospective cohort. University teaching hospital. The records of 9,860 surgical patients posted between January 1 and June 30, 2010 were reviewed. Request for acute pain service consultation. A cohort of machine-learning classifiers was compared according to its ability or inability to classify surgical cases as requiring a request for a preoperative acute pain service consultation. Classifiers were then optimized utilizing ensemble techniques. Computational efficiency was measured with the central processing unit processing times required for model training. Classifiers were tested using the full feature set, as well as the reduced feature set that was optimized using a merit-based dimensional reduction strategy. Machine-learning classifiers correctly predicted preoperative requests for acute pain service consultations in 92.3% (95% confidence intervals [CI], 91.8–92.8) of all surgical cases. Bayesian methods yielded the highest area under the receiver operating curve (0.87, 95% CI 0.84–0.89) and lowest training times (0.0018 seconds, 95% CI, 0.0017–0.0019 for the NaiveBayesUpdateable algorithm). An ensemble of high-performing machine-learning classifiers did not yield a higher area under the receiver operating curve than its component classifiers. Dimensional reduction decreased the computational requirements for multiple classifiers, but did not adversely affect classification performance. Using historical data, machine-learning classifiers can predict which surgical cases should prompt a preoperative request for an acute pain service consultation. Dimensional reduction improved computational efficiency and preserved predictive performance.