文献速递创伤与烧伤重症综合管理与镇静镇痛

统计严谨的深度神经网络方法预测创伤ICU患者死亡率

A statistically rigorous deep neural network approach to predict mortality in trauma patients admitted to the intensive care unit.
PubMed 文献 · J Trauma Acute Care Surg · 2020-01-01
一句话结论在创伤ICU成人患者中,基于FLAIM框架的Deep-FLAIM深度神经网络模型预测死亡率的测试集准确率为92.25%、AUC为0.91。

本研究使用公开数据库MIMIC-III v1.4中3,041例成人创伤ICU患者,先通过Cox回归单因素和多因素分析筛选与死亡率相关的临床和实验室变量,再将显著变量输入深度神经网络(Deep-FLAIM)及其他传统机器学习模型预测死亡率。结果血清阴离子间隙(HR 2.46)、钠(HR 2.11)、氯(HR 2.11)异常及脓毒症诊断(HR 2.03)、qSOFA评分(HR 1.52)、SIRS标准(HR 1.41)为显著变量;Deep-FLAIM模型测试集准确率92.25%、敏感度79.13%、特异度94.16%、阳性预测值66.42%、阴性预测值96.87%、AUC 0.91,优于所有其他机器学习模型。作者认为该模型易于实施且准确率高。

要点

  • 在3,041例创伤ICU成人患者中,Deep-FLAIM深度神经网络预测死亡率的测试集准确率为92.25%,AUC为0.91。
  • 该模型测试集敏感度79.13%、特异度94.16%、阳性预测值66.42%、阴性预测值96.87%。
  • 多因素分析中血清阴离子间隙异常与死亡率相关(HR 2.46,95%CI 1.94-3.11),钠和氯异常HR均为2.11。
  • 脓毒症诊断(HR 2.03,95%CI 1.23-3.37)、qSOFA评分(HR 1.52,95%CI 1.32-3.76)、SIRS标准(HR 1.41,95%CI 1.24-1.26)与死亡率相关。
  • 作者认为Deep-FLAIM模型优于其他机器学习模型,易于实施且用户友好。

适用人群与场景

  • 年龄≥18岁、收入创伤ICU的成人创伤患者,数据来自公开数据库Medical Information Mart for Intensive Care III version 1.4。

研究设计与关键结果

  • 研究类型为预后预测模型开发,使用MIMIC-III v1.4公开数据库,共纳入3,041例收入创伤外科ICU的创伤患者。
  • 第一阶段用Cox回归单因素和多因素分析筛选显著变量,第二阶段将显著变量输入深度神经网络及线性判别分析、高斯朴素贝叶斯、决策树、k近邻等传统机器学习模型。
  • 多因素分析中血清阴离子间隙异常HR 2.46(95%CI 1.94-3.11)、钠异常HR 2.11(95%CI 1.61-2.77)、氯异常HR 2.11(95%CI 1.69-2.64)、脓毒症诊断HR 2.03(95%CI 1.23-3.37)、qSOFA评分HR 1.52(95%CI 1.32-3.76)、SIRS标准HR 1.41(95%CI 1.24-1.26)。
  • Deep-FLAIM模型测试集准确率92.25%、敏感度79.13%、特异度94.16%、阳性预测值66.42%、阴性预测值96.87%、AUC 0.91(原文写作1.45-1.29)。
  • Deep-FLAIM模型优于所有其他机器学习模型。

证据类型、等级与局限

  • 证据类型为预后研究,原文标注证据等级为level II。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为Deep-FLAIM模型优于所有其他机器学习模型,易于实施、用户友好且准确率高。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

BACKGROUND: Trauma patients admitted to critical care are at high risk of mortality because of their injuries. Our aim was to develop a machine learning-based model to predict mortality using Fahad-Liaqat-Ahmad Intensive Machine (FLAIM) framework. We hypothesized machine learning could be applied to critically ill patients and would outperform currently used mortality scores.

METHODS: The current Deep-FLAIM model evaluates the statistically significant risk factors and then supply these risk factors to deep neural network to predict mortality in trauma patients admitted to the intensive care unit (ICU). We analyzed adult patients (≥18 years) admitted to the trauma ICU in the publicly available database Medical Information Mart for Intensive Care III version 1.4. The first phase selection of risk factor was done using Cox-regression univariate and multivariate analyses. In the second phase, we applied deep neural network and other traditional machine learning models like Linear Discriminant Analysis, Gaussian Naïve Bayes, Decision Tree Model, and k-nearest neighbor models.

RESULTS: We identified a total of 3,041 trauma patients admitted to the trauma surgery ICU. We observed that several clinical and laboratory-based variables were statistically significant for both univariate and multivariate analyses while others were not. With most significant being serum anion gap (hazard ratio [HR], 2.46; 95% confidence interval [CI], 1.94-3.11), sodium (HR, 2.11; 95% CI, 1.61-2.77), and chloride (HR, 2.11; 95% CI, 1.69-2.64) abnormalities on laboratories, while clinical variables included the diagnosis of sepsis (HR, 2.03; 95% CI, 1.23-3.37), Quick Sequential Organ Failure Assessment score (HR, 1.52; 95% CI, 1.32-3.76). And Systemic Inflammatory Response Syndrome criteria (HR. 1.41; 95% CI, 1.24-1.26). After we used these clinically significant variables and applied various machine learning models to the data, we found out that our proposed DNN outperformed all the other methods with test set accuracy of 92.25%, sensitivity of 79.13%, and specificity of 94.16%; positive predictive value, 66.42%; negative predictive value, 96.87%; and area under the curve of the receiver-operator curve of 0.91 (1.45-1.29).

CONCLUSION: Our novel Deep-FLAIM model outperformed all other machine learning models. The model is easy to implement, user friendly and with high accuracy.

LEVEL OF EVIDENCE: Prognostic study, level II.

来源:J Trauma Acute Care Surg,查看原文。版权归原作者所有。

参考来源

  1. Ahmed FS, Ali L, Joseph BA, et al. A statistically rigorous deep neural network approach to predict mortality in trauma patients admitted to the intensive care unit. J Trauma Acute Care Surg. 2020. PMID: 32773672. doi:10.1097/TA.0000000000002888

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。