Lin Wei-Chun, Huang Chien-Hsiung, Chien Liang-Tien, Tseng Hsiao-Jung, Ng Chip-Jin, Hsu Kuang-Hung, Lin Chi-Chun, Chien Cheng-Yu
Department of Emergency Medicine, New Taipei Municipal TuCheng Hospital and Chang Gung University, New Taipei City, Taiwan.
Department of Emergency Medicine, Chang Gung Memorial Hospital, Linkou and College of Medicine, Chang Gung University, Taoyuan, Taiwan.
Int J Gen Med. 2022 Sep 19;15:7395-7405. doi: 10.2147/IJGM.S384959. eCollection 2022.
The authors performed several tree-based algorithms and an association rules mining as data mining tools to find useful determinants for neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients as well as to assess the effect of the first-aid and basic characteristics in the EMS system.
This was a retrospective cohort study. The outcome was Cerebral Performance Categories grading on OHCA patients at hospital discharge. Decision tree-based models inclusive of C4.5 algorithm, classification and regression tree and random forest were built to determine an OHCA patient's prognosis. Association rules mining was another data mining method which we used to find the combination of prognostic factors linked to the outcome.
The total of 3520 patients were included in the final analysis. The mean age was 67.53 (±18.4) year-old and 63.4% were men. To overcome the imbalance outcome issue in machine learning, the random forest has a better predictive ability for OHCA patients in overall accuracy (91.19%), weighted precision (88.76%), weighted recall (91.20%) and F1 score (0.9) by oversampling adjustment. Under association rules mining, patients who had any witness on the spot when encountering OHCA or who had ever ROSC during first-aid would be highly correlated with good CPC prognosis.
The random forest has a better predictive ability for OHCA patients. This paper provides a role model applying several machine learning algorithms to the first-aid clinical assessment that will be promising combining with Artificial Intelligence for applying to emergency medical services.
作者运用几种基于树的算法和关联规则挖掘作为数据挖掘工具，以找出院外心脏骤停（OHCA）患者神经学预后的有用决定因素，并评估急救和急救医疗服务（EMS）系统中的基本特征的影响。
这是一项回顾性队列研究。结局指标是OHCA患者出院时的脑功能分类分级。构建了基于决策树的模型，包括C4.5算法、分类与回归树以及随机森林，以确定OHCA患者的预后。关联规则挖掘是我们用于找出与结局相关的预后因素组合的另一种数据挖掘方法。
最终分析纳入了3520例患者。平均年龄为67.53（±18.4）岁，男性占63.4%。为克服机器学习中的结局不平衡问题，通过过采样调整，随机森林在总体准确率（91.19%）、加权精确率（88.76%）、加权召回率（91.20%）和F1分数（0.9）方面对OHCA患者具有更好的预测能力。在关联规则挖掘中，OHCA发生时现场有目击者或急救过程中有过自主循环恢复（ROSC）的患者与良好的脑功能分类（CPC）预后高度相关。
随机森林对OHCA患者具有更好的预测能力。本文提供了一个将几种机器学习算法应用于急救临床评估的范例，与人工智能相结合应用于紧急医疗服务具有广阔前景。
