基于深度神经网络的重症监护室脓毒症患者死亡风险预测模型分析

doi:10.6040/j.issn.1671-9352.8.2024.009

摘要/Abstract

摘要： 提出基于变量选择网络(variable selection networks, VSN)和门控残差网络(gated residual networks, GRN)相结合的深度神经网络(deep neural network, DNN)模型,用于预测重症监护室(intensive care unit, ICU)脓毒症患者30 d内的死亡风险,并对模型的可解释性进行深入分析。在重症医学数据库中利用随机森林算法筛选43个重要特征,利用本文提出的模型评估死亡风险,并采用移除再训练(remove and retrain, ROAR)方法选出一种最佳的可解释性方法对结果进行解释。测试结果显示,本文提出的模型的预测性能优于其他机器学习模型,受试者工作特征曲线面积(area under receiver operating characteristic curve, AUROC)为0.967。利用ROAR方法分析中,相关性分数逐层传播(layer-wise relevance propagation, LRP)方法的AUROC从0.967下降到0.828。利用LRP方法对本文提出的模型进行可解释性分析后,确定查尔森合并症评分为最重要的特征,同时器官衰竭评分、年龄、呼吸频率也对重症监护室脓毒症患者的死亡风险有较大影响。

关键词: 脓毒症, 死亡风险预测, 深度神经网络, 移除再训练, 相关性分数逐层传播

Abstract: A deep neural network(DNN)model is proposed by integrating variable selection networks(VSN)and gated residual networks(GRN)to predict the 30-day mortality risk of sepsis patients in the intensive care unit(ICU)and to conduct an in-depth interpretability analysis. In the critical care medical database, 43 significant features are selected using a random forest algorithm, and the proposed model is employed to evaluate mortality risk. The remove and retrain(ROAR)method is utilized to determine the optimal interpretability approach for explaining the results. Testing outcomes indicate that the proposed model outperforms other machine learning models, achieving an area under the receiver operating characteristic curve(AUROC)of 0.967. In the ROAR analysis, the AUROC of the layer-wise relevance propagation(LRP)method decreases from 0.967 to 0.828. Through interpretability analysis of the proposed model using LRP, the Charlson comorbidity score is identified as the most critical feature. In contrast, the organ failure score, age, and respiratory rate also have a pronounced impact on the mortality risk of ICU sepsis patients.

Key words: sepsis, mortality risk prediction, deep neural network, remove and retrain, layer-wise relevance propagation

中图分类号:

TP391

余雷,孙懿,华金铭,李腊全. 基于深度神经网络的重症监护室脓毒症患者死亡风险预测模型分析[J]. 《山东大学学报(理学版)》, 2026, 61(1): 26-35.

YU Lei, SUN Yi, HUA Jinming, LI Laquan. Analysis of the prediction model based on deep neural networks for mortality risk prediction for sepsis patients in intensive care units[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2026, 61(1): 26-35.

参考文献

[1] 邱海波,杜斌,刘大为,等. 全身炎症反应综合征与多器官功能障碍综合征的临床研究[J]. 中华外科杂志,1997,35(7):402-405. QIU Haibo, DU Bin, LIU Dawei, et al. Clinical study on systemic inflammatory response syndrome and multiple organ dysfunction syndrome [J]. Chinese Journal of Surgery, 1997, 35(7):402-405.
[2] GAUER R, FORBES D, BOYER N. Sepsis:diagnosis and management[J]. American Family Physician, 2020, 101(7):409-418.
[3] WANG Yuhe, SHAN Gao, LEI Hong, et al. Prognostic impact of blood urea nitrogen to albumin ratio on patients with sepsis: a retrospective cohort study[J]. Scientific Reports, 2023, 13(1):10013.
[4] COX D R. Regression models and life-tables[J]. Journal of the Royal Statistical Society(Series B: Methodological), 1972, 34(2):187-220.
[5] DIAS A, GOMEZ V C, VIOLA L R, et al. Fever is associated with earlier antibiotic onset and reduced mortality in patients with sepsis admitted to the ICU[J]. Scientific Reports, 2021, 11(1):23949.
[6] HU Jing, LÜ Chenwei, HU Xinxing, et al. Effect of hypoproteinemia on the mortality of sepsis patients in the ICU: a retrospective cohort study[J]. Scientific Reports, 2021, 11(1):24379.
[7] VINCENT J L, MENDONCA A, CANTRAINE F, et al. Use of the SOFA score to assess the incidence of organ dysfunction/failure in intensive care units: results of a multicenter, prospective study[J]. Critical Care Medicine, 1998, 26(11):1793-1800.
[8] FORD D W, GOODWIN A J, SIMPSON A N, et al. A severe sepsis mortality prediction model and score for use with administrative data[J]. Critical Care Medicine, 2016, 44(2):319-327.
[9] CARRARA M, BASELLA G, FERRARIO M. Mortality prediction model of septic shock patients based on routinely recorded data[J]. Computational and Mathematical Methods in Medicine, 2015, 2015(1):761435.
[10] KHWANNIMIT B, BHURAVANONTACHAI R, VATTANVANIT V. Validation of the sepsis severity score compared with updated severity scores in predicting hospital mortality in sepsis patients[J]. Shock, 2017, 47(6):720-725.
[11] HOU Nianzong, LI Mingzhe, HE Lu, et al. Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost[J]. Journal of Translational Medicine, 2020, 18(1):462-462.
[12] PERNG J W, KAO I H, KUNG C T, et al. Mortality prediction of septic patients in the emergency department based on machine learning[J]. Journal of Clinical Medicine, 2019, 8(11):1906.
[13] 化盈盈,张岱墀,葛仕明. 深度学习模型可解释性的研究进展[J]. 信息安全学报,2020,5(3):1-12. HUA Yingying, ZHANG Daichi, GE Shiming. Research progress in the interpretability of deep learning models[J]. Journal of Information Security, 2020, 5(3):1-12.
[14] 陈珂锐,孟小峰. 机器学习的可解释性[J]. 计算机研究与发展,2020,57(9):1971-1986. CHEN Kerui, MENG Xiaofeng. Interpretability of machine learning[J]. Journal of Computer Research and Development, 2020, 57(9):1971-1986.
[15] 曾春艳,严康,王志锋,等. 深度学习模型可解释性研究综述[J]. 计算机工程与应用,2021,57(8):1-9. ZENG Chunyan, YAN Kang, WANG Zhifeng, et al. A review of research on the interpretability of deep learning models[J]. Computer Engineering and Applications, 2021, 57(8):1-9.
[16] RAIKOMAR A, DEAN J, KOHANE I. Machine learning in medicine[J]. New England Journal of Medicine, 2019, 380(14):1347-1358.
[17] LIM B, ARIK S O, LOEFF N, et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting[J]. International Journal of Forecasting, 2021, 37(4):1748-1764.
[18] HOOKER S, ERHAN D, KINDERMANS P J, et al. A benchmark for interpretability methods in deep neural networks[C] //Advances in Neural Information Processing Systems. Vancouver: Curran Associates Incorporated, 2019.
[19] MENG C, TRINH L, XU N, et al. Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset[J]. Scientific Reports, 2022, 12:7166.
[20] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C] //2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vega: Curran Associates Incorporated, 2016:770-778.
[21] MITCHELL R, COOPER J, FRANK E, et al. Sampling permutations for Shapley value estimation[J]. Journal of Machine Learning Research, 2022, 23(43):1-46.
[22] HE Shengfeng, ZHE Huang, LIU Wenxi, et al. SuperCNN: a superpixelwise convolutional neural network for salient object detection[J]. International Journal of Computer Vision, 2015, 115(3):330-344.
[23] ZAFEIRIOU A, KALLIPOLITIS A, MAGLOGIANNIS I. Ensembling to leverage the interpretability of medical image analysis systems[J]. IEEE Access, 2023,11:76437-76447.
[24] SUNDARARAJAN M, TALY A, YAN Q. Axiomatic attribution for deep networks[C] //International Conference on Machine Learning. Sydney: PMLR, 2017:3319-3328.
[25] BACH S, BINDER A, MONTAVON G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation[J]. Public Library of Science One, 2015, 10(7):e0130140.
[26] HOCHULI J, HELBLING A, SKAIST T, et al. Visualizing convolutional neural network protein-ligand scoring[J]. Journal of Molecular Graphics & Modelling, 2018, 84:96-108.
[27] TOLLES J, MEURER W J. Logistic regression: relating patient characteristics to outcomes[J]. The Journal of the American Medical Association, 2016, 316(5):533-534.
[28] OSMAN A I A, AHMED A N, CHOW M F, et al. Extreme gradient boosting(Xgboost)model to predict the groundwater levels in selangor malaysia[J]. Ain Shams Engineering Journal, 2021, 12(2):1545-1556.
[29] MASCARO J, ASNER G P, KNAPP D E, et al. A tale of two “forests”: random forest machine learning AIDS tropical forest carbon mapping[J]. Public Library of Science One, 2014, 9(1):E85993.
[30] FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. The Annals of statistics, 2001, 29(5):1189-1232.

相关文章 15

[1]	梁霞,郭洁. 基于在线评论的线上教学平台选择方法[J]. 《山东大学学报(理学版)》, 2024, 59(9): 108-118.
[2]	黎超,廖薇. 基于医疗知识驱动的中文疾病文本分类模型[J]. 《山东大学学报(理学版)》, 2024, 59(7): 122-130.
[3]	纪杰,孙承杰,单丽莉,尚伯乐,林磊. 基于提示学习的电信网络诈骗案件分类方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 113-121.
[4]	罗奇,苟刚. 基于聚类和群组归一化的多模态对话情绪识别[J]. 《山东大学学报(理学版)》, 2024, 59(7): 105-112.
[5]	赵峰叙,王健,林原,林鸿飞. 面向排序学习的概率分布优化模型[J]. 《山东大学学报(理学版)》, 2024, 59(7): 95-104.
[6]	黄兴宇,赵明宇,吕子钰. 面向图神经网络表征学习的类别知识探针[J]. 《山东大学学报(理学版)》, 2024, 59(7): 85-94.
[7]	桂梁,徐遥,何世柱,张元哲,刘康,赵军. 基于动态邻居选择的知识图谱事实错误检测方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 76-84.
[8]	咸宁,范意兴,廉涛,郭嘉丰. 融合多重特征的噪声网络对齐方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 64-75.
[9]	孙承杰,李宗蔚,单丽莉,林磊. 一种基于核心论元的篇章级事件抽取方法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 53-63.
[10]	刘沛羽,姚博文,高泽峰,赵鑫. 基于矩阵乘积算符表示的序列化推荐模型[J]. 《山东大学学报(理学版)》, 2024, 59(7): 44-52, 104.
[11]	邵伟,朱高宇,于雷,郭嘉丰. 高维数据的降维与检索算法[J]. 《山东大学学报(理学版)》, 2024, 59(7): 27-43.
[12]	杨纪元,马沐阳,任鹏杰,陈竹敏,任昭春,辛鑫,蔡飞,马军. 基于自监督的预训练在推荐系统中的研究[J]. 《山东大学学报(理学版)》, 2024, 59(7): 1-26.
[13]	陈海粟,廖佳纯,姚思诚. 政府开放数据中个人信息披露识别与统计方法[J]. 《山东大学学报(理学版)》, 2024, 59(3): 95-106.
[14]	温欣,李德玉. 基于属性加权的ML-KNN方法[J]. 《山东大学学报(理学版)》, 2024, 59(3): 107-117.
[15]	曾雪强,孙雨,刘烨,万中英,左家莉,王明文. 基于情感分布的emoji嵌入式表示[J]. 《山东大学学报(理学版)》, 2024, 59(3): 81-94.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed