张熠, 陈均, 薛春竹, 母存富. 基于随机森林算法心胸外科术后患者急性肾损伤预测模型的价值分析[J]. 心脏杂志, 2023, 35(1): 67-71. DOI: 10.12125/j.chj.202201017
    引用本文: 张熠, 陈均, 薛春竹, 母存富. 基于随机森林算法心胸外科术后患者急性肾损伤预测模型的价值分析[J]. 心脏杂志, 2023, 35(1): 67-71. DOI: 10.12125/j.chj.202201017
    Yi ZHANG, Jun CHEN, Chun-zhu XUE, Cun-fu MU. Value analysis of predictive model of acute kidney injury in patients after cardiothoracic surgery based on random forest algorithm[J]. Chinese Heart Journal, 2023, 35(1): 67-71. DOI: 10.12125/j.chj.202201017
    Citation: Yi ZHANG, Jun CHEN, Chun-zhu XUE, Cun-fu MU. Value analysis of predictive model of acute kidney injury in patients after cardiothoracic surgery based on random forest algorithm[J]. Chinese Heart Journal, 2023, 35(1): 67-71. DOI: 10.12125/j.chj.202201017

    基于随机森林算法心胸外科术后患者急性肾损伤预测模型的价值分析

    Value analysis of predictive model of acute kidney injury in patients after cardiothoracic surgery based on random forest algorithm

    • 摘要:
        目的  构建基于随机森林算法的心胸外科术后患者急性肾损伤(acute kindey injury,AKI)的预测模型,并分析其预测价值。
        方法  选取广元市第一人民医院2018年1月~2020年12月接受心胸外科手术治疗的212例患者为研究对象,采用随机数字表法按2:1的比例建立训练集和测试集。采用随机森林算法对心胸外科患者术后AKI的预测指标的重要性进行排序。根据袋外数据误差,赤池信息量准则和贝叶斯信息量准则对排序指标进行筛选并构建预测模型,多维标度法(multidimensional scaling,MDS)观察预测模型对心胸外科术后患者AKI的预测能力;采用内部验证法验证模型对心胸外科患者术后AKI的预测能力。
        结果  212例患者中,148例未发生AKI的为未发生组,64例发生AKI为发生组;16 个指标根据平均准确度下降程度和平均基尼指数下降程度进行重要性排序。用袋外数据误差,赤池信息量准则和贝叶斯信息量准则筛选出术后中性粒细胞明胶酶相关脂质运载蛋白(NGAL)、术后金属蛋白酶组织抑制剂2(TIMP 2)、术后胰岛素样生长因子结合蛋白7(IGFBP7)及术后血浆肌酐(pCr)4个变量(P<0.01),并纳入模型。 通过 MDS 法观察到预测模型区分良好。
        结论  基于术后NGAL、术后TIMP 2、术后IGFBP7及术后pCr建立的随机森林算法预测模型可用于心胸外科术后患者AKI发生的预测。

       

      Abstract:
        AIM  To construct a predictive model of acute kidney injury (AKI) for patients undergoing cardiothoracic surgery based on the random forest algorithm and analyze its predictive value.
        METHODS  Two hundred and twelve patients in our hospital who underwent cardiothoracic surgery from January 2018 to December 2020 were selected as the research subjects. The random number table method was used to establish the training set and the test was set at a ratio of 2:1. Random forest algorithm was used to rank the importance of predictive indicators of AKI after cardiothoracic surgery. According to the out-of-bag data error, the Akaike information criterion and the Bayesian information criterion, the ranking indexes were screened and the predictive model was constructed. The multidimensional scaling method (MDS) was used to observe the predictive ability of the model after cardiothoracic surgery and internal verification method was adopted to validate the model’s ability to predict postoperative AKI in patients undergoing cardiothoracic surgery.
        RESULTS  Among the 212 patients, AKI occurred in 64 cases (occurrence group) and did not occur in 148 cases (non-occurring group). The 16 indicators were ranked in importance according to the degree of decline in average accuracy and the degree of decline in average Gini index. Using the out-of-bag data error, Akaike information criterion and Bayesian information criterion, 4 variables were screened out, namely, postoperative NGAL, postoperative TIMP 2, postoperative IGFBP7 and postoperative pCr, and they were included in the model(P<0.01). It was observed that the prediction models were well differentiated by the MDS method.
        CONCLUSION  The random forest algorithm prediction model based on postoperative NGAL, postoperative TIMP 2, postoperative IGFBP7 and postoperative pCr can be used to predict the occurrence of AKI in patients after cardiothoracic surgery.

       

    /

    返回文章
    返回