文献速递重症综合管理与镇静镇痛

预测重症患者多重耐药菌感染的深度学习模型

A deep learning model for predicting multidrug-resistant organism infection in critically ill patients.
PubMed 文献 · J Intensive Care · 2023-11-09
一句话结论基于9项独立危险因素构建的BPNN模型预测ICU患者MDRO感染,训练集AUC 0.889、测试集0.919、外部验证集0.811。

本研究收集青岛大学附属医院ICU 2021年8月至2022年1月患者资料,随机分为训练集(80%)与测试集(20%),用LASSO和逐步回归确定MDRO感染的独立危险因素并构建BPNN模型,再以2022年5月至7月同中心患者外部验证。初始队列688例中109例(15.84%)发生MDRO感染,确定9项危险因素;验证集238例中31例(13.03%)感染。模型校准良好,训练集、测试集、验证集AUC分别为0.889(95%CI 0.852-0.925)、0.919(95%CI 0.856-0.983)、0.811(95%CI 0.731-0.891)。作者认为该模型表现良好,可能用于预测ICU患者MDRO感染。

要点

  • 初始队列688例ICU患者中109例(15.84%)发生MDRO感染,验证集238例中31例(13.03%)发生MDRO感染。
  • 确定的9项MDRO感染危险因素包括住院时间、ICU停留时间、长期卧床、入ICU前使用抗生素、APACHE II评分、入ICU前侵入性操作、抗生素数量、慢性肺病和低蛋白血症。
  • BPNN模型校准良好,训练集AUC 0.889(95%CI 0.852-0.925),测试集AUC 0.919(95%CI 0.856-0.983),外部验证集AUC 0.811(95%CI 0.731-0.891)。
  • 作者认为该BPNN模型表现良好,可能用于预测ICU患者MDRO感染。

适用人群与场景

  • 青岛大学附属医院ICU 2021年8月至2022年1月收治的患者(初始队列688例),以及2022年5月至7月同中心患者(验证集238例)。

研究设计与关键结果

  • 研究类型为预测模型构建与外部验证;初始队列688例,随机分为训练集(80%)和测试集(20%),MDRO感染109例(15.84%);验证集238例,MDRO感染31例(13.03%)。
  • 采用LASSO和逐步回归分析确定MDRO感染的独立危险因素,包括住院时间、ICU停留时间、长期卧床、入ICU前抗生素使用、APACHE II评分、入ICU前侵入性操作、抗生素数量、慢性肺病和低蛋白血症。
  • 基于上述因素构建BPNN模型,校准曲线显示校准良好;训练集AUC 0.889(95%CI 0.852-0.925),测试集AUC 0.919(95%CI 0.856-0.983),验证集AUC 0.811(95%CI 0.731-0.891)。

证据类型、等级与局限

  • 证据类型:预测模型构建与外部验证研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为该BPNN模型表现良好,可能用于预测ICU患者MDRO感染。

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: This study aimed to apply the backpropagation neural network (BPNN) to develop a model for predicting multidrug-resistant organism (MDRO) infection in critically ill patients.

METHODS: This study collected patient information admitted to the intensive care unit (ICU) of the Affiliated Hospital of Qingdao University from August 2021 to January 2022. All patients enrolled were divided randomly into a training set (80%) and a test set (20%). The least absolute shrinkage and selection operator and stepwise regression analysis were used to determine the independent risk factors for MDRO infection. A BPNN model was constructed based on these factors. Then, we externally validated this model in patients from May 2022 to July 2022 over the same center. The model performance was evaluated by the calibration curve, the area under the curve (AUC), sensitivity, specificity, and accuracy.

RESULTS: In the primary cohort, 688 patients were enrolled, including 109 (15.84%) MDRO infection patients. Risk factors for MDRO infection, as determined by the primary cohort, included length of hospitalization, length of ICU stay, long-term bed rest, antibiotics use before ICU, acute physiology and chronic health evaluation II, invasive operation before ICU, quantity of antibiotics, chronic lung disease, and hypoproteinemia. There were 238 patients in the validation set, including 31 (13.03%) MDRO infection patients. This BPNN model yielded good calibration. The AUC of the training set, the test set and the validation set were 0.889 (95% CI 0.852-0.925), 0.919 (95% CI 0.856-0.983), and 0.811 (95% CI 0.731-0.891), respectively.

CONCLUSIONS: This study confirmed nine independent risk factors for MDRO infection. The BPNN model performed well and was potentially used to predict MDRO infection in ICU patients.

来源:J Intensive Care,查看原文。版权归原作者所有。

参考来源

  1. Wang Y, Wang G, Zhao Y, et al. A deep learning model for predicting multidrug-resistant organism infection in critically ill patients. J Intensive Care. 2023. PMID: 37941079. doi:10.1186/s40560-023-00695-y

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。