基于贝叶斯网络与蒙特卡洛模拟的院内感染传播风险预测算法

Risk Prediction Algorithm of Nosocomial Infection Transmission Based on Bayesian Network and Monte Carlo Simulation

摘要

由于研究医院患者本身具有高度异质性, 以及外部干预措施的时空波动性, 院内感染传播呈现非线性和随机性的特征, 增加了风险预测的难度, 为此, 提出了基于贝叶斯网络与蒙特卡洛模拟的院内感染传播风险预测算法。从患者、医疗操作、环境和管理4个维度筛选影响院内感染传播风险的因素, 并将分类变量转换为连续变量以统一变量维度。同时引入客观赋权法求取单因素权重, 并整合主观权重获取影响因素的综合权重, 对影响因素的重要程度进行排序。采用贝叶斯网络通过计算高权重影响因子的联合概率分布和最大似然估计, 构建感染传播风险预测模型。利用蒙特卡洛模拟算法对模型中的不确定性变量进行随机抽样, 生成模拟场景, 根据统计模拟结果计算感染传播风险概率, 确定风险情况。实验结果表明, 应用所提方法进行院内感染传播风险预测, 预测结果的特异度高于90%, 减少了误报, 预测准确性更高。

Abstract

Due to the high heterogeneity of hospital patients and the spatiotemporal fluctuations of external intervention measures, the transmission of nosocomial infections presents non-linear and stochastic characteristics, which increases the difficulty of risk prediction. Therefore, a risk prediction algorithm for nosocomial infection transmission based on Bayesian networks and Monte Carlo simulations is proposed. The factors influencing the risk of nosocomial infection transmission are screened from four dimensions: patients, medical operations, environment and management. The categorical variables are converted into continuous variables to unify the variable dimensions, which is convenient for subsequent calculations. The objective weighting method is introduced to obtain the weight of a single factor, and the subjective weights are integrated to obtain the comprehensive weight of the influencing factors, so as to rank the importance of the influencing factors. An infection transmission risk prediction model is constructed by using Bayesian networks to calculate the joint probability distribution of high-weight influence factors and maximum likelihood estimation. The Monte Carlo simulation algorithm is utilized to randomly sample the uncertain variables in the model, generating simulation scenarios. Based on the statistical simulation results, the probability of infection transmission risk is calculated to determine the risk situation. The experimental results show that when the proposed method is applied to predict the risk of nosocomial infection transmission, the specificity of the prediction results is higher than 90%, false alarms are reduced, and the prediction accuracy is higher.

关键词

贝叶斯网络 / 蒙特卡洛模拟 / 院内感染传播风险 / 预测模型 / 影响因素

Key words

bayesian network / Monte Carlo simulation / risk of nosocomial infection transmission / prediction model / Influencing factors

参考文献

[1] 宋晓超, 金美娟, 丁蔚, 等. 基于机器学习的神经外科ICU患者耐碳青霉烯革兰阴性菌感染风险预测模型构建及验证[J]. 中华医院感染学杂志, 2025, 35(11): 1690-1696.

[2] SONG X C, JIN M J, DING W, et al. Construction and Validation of a Machine Learning-Based Model for Predicting the Risk of Carbapenem-Resistant Gram-Negative Bacteria Infections in Neurosurgical ICU Patients[J]. Chinese Journal of Nosocomiology, 2025, 35(11): 1690-1696.

[3] 殷小焦, 王健翔, 高云. 基于机器学习算法构建脑卒中患者机械取栓术后肺部感染风险预测模型[J]. 介入放射学杂志, 2025, 34(6): 574-578.

[4] YIN X J, WANG J X, GAO Y. Machine-Learning Algorithm-Based Construction of a Risk Prediction Model for Pulmonary Infection in Stroke Patients after Mechanical Thrombectomy[J]. Journal of Interventional Radiology, 2025, 34(6): 574-578.

[5] 左蝶, 赵佳, 龙晓艳, 等. 多模态数据融合+动态机器学习构建ICU患者MDRO感染早期预警模型的研究[J]. 海南医科大学学报, 2025, 31(6): 421-432.

[6] ZUO D, ZHAO J, LONG X Y, et al. Study on Early Warning Model of MDRO Infection in ICU Patients Based on Multimodal Data Fusion and Dynamic Machine Learning[J]. Journal of Hainan Medical University, 2025, 31(6): 421-432.

[7] 钟志涛, 潘振宇, 唐海达. 基于近距离接触行为分析的室内感染风险评估与防控设计策略研究[J]. 建筑科学, 2024, 40(10): 211-219.

[8] ZHONG Z T, PAN Z Y, TANG H D. Research on Indoor Infection Risk Assessment and Prevention and Control Design Strategy Based on Close Contact Behavior Analysis[J]. Building Science, 2024, 40(10): 211-219.

[9] 龚利平, 李建, 陈忠英, 等. 基于决策树法构建深静脉置管并发导管相关性感染的风险预测模型及防控策略分析[J]. 军事护理, 2024, 41(6): 52-54.

[10] GONG L P, LI J, CHEN Z Y, et al. Risk Prediction Model of Deep Venous Catheterization Complicating Catheter-Associated Infection and Analysis of Prevention and Control Strategies Based on Decision Tree Method[J]. Military Nursing, 2024, 41(6): 52-54.

[11] 张仲双, 张光葭, 姚人新, 等. 四川省棘球蚴病疫点传播风险评估体系构建研究[J]. 中国寄生虫学与寄生虫病杂志, 2025, 43(1): 37-43.

[12] ZHANG Z S, ZHANG G S, YAO R X, et al. Research on the Construction of Risk Assessment System for the Transmission of Echinococcosis Endemic Sites in Sichuan Province[J]. Chinese Journal of Parasitology and Parasitic Diseases, 2025, 43(1): 37-43.

[13] 周姝宏, 李凤, 阳佳家, 等. 基于控制营养状况评分的重症脑卒中病人继发肺部感染风险预测模型的构建[J]. 护理研究, 2025, 39(2): 231-236.

[14] ZHOU S H, LI F, YANG J J, et al. Construction of Risk Prediction Model for Secondary Pulmonary Infection in Patients with Severe Stroke Based on Controlling Nutritional Status Score[J]. Chinese Nursing Research, 2025, 39(2): 231-236.

[15] 白世贞, 吴文娅, 鄢章华, 等. 基于马尔可夫与传染病模型的供应链网络中断风险传播研究[J]. 管理工程学报, 2023, 37(4): 206-221.

[16] BAI S Z, WU W Y, YAN Z H, et al. Disruption Risk Propagation in Supply Chain Network Based on Markov and Epidemic Model[J]. Journal of Industrial Engineering and Engineering Management, 2023, 37(4): 206-221.

[17] 姚尧, 查筑红, 李家丽, 等. 基于AHP-风险矩阵构建手术后肺炎风险评估模型研究[J]. 中国感染控制杂志, 2023, 22(11): 1312-1318.

[18] YAO Y, CHA Z H, LI J L, et al. Risk Assessment System of Postoperative Pneumonia Based on AHP and Risk Matrix[J]. Chinese Journal of Infection Control, 2023, 22(11): 1312-1318.

[19] 冯新元, 赵佳雪, 龙金照, 等. 基于CRISPR序列的致泻性大肠埃希菌跨种传播风险机器学习模型构建[J]. 中国畜牧兽医, 2024, 51(9): 4060-4065.

[20] FENG X Y, ZHAO J X, LONG J Z, et al. Construction of Machine Learning Models to Predict the Cross-Host Infection Risk of Diarrheagenic Escherichia Coli Based on CRISPR Sequence[J]. China Animal Husbandry & Veterinary Medicine, 2024, 51(9): 4060-4065.

[21] 夏禹, 王磊. 基于反向传播神经网络的海洋工程项目投标风险评价方法[J]. 上海交通大学学报, 2023, 57(S1): 46-53.

[22] XIA Y, WANG L. Risk Assessment Method for Marine Engineering Project Bidding Based on Back Propagation Neural Network[J]. Journal of Shanghai Jiaotong University, 2023, 57(S1): 46-53.

[23] 张梦真, 任周鹏, 范俊甫, 等. 基于多源地理数据的广州市精细尺度登革热传播风险预测[J]. 中国媒介生物学及控制杂志, 2023, 34(5): 654-663.

[24] ZHANG M Z, REN Z P, FAN J F, et al. Fine-Scale Dengue Transmission Risk Prediction Based on Multi-Source Geographic Data in Guangzhou, China[J]. Chinese Journal of Vector Biology and Control, 2023, 34(5): 654-663.

[25] 黄国惠, 李娇, 倪萍, 等. 运用决策树算法构建天疱疮并发感染的风险预测模型[J]. 中国皮肤性病学杂志, 2023, 37(11): 1269-1276.

[26] HUANG G H, LI J, NI P, et al. The Risk Prediction Model of Pemphigus Co-Infection Constructed Based on Decision Tree Algorithm[J]. The Chinese Journal of Dermatovenereology, 2023, 37(11): 1269-1276.

[27] MIAO R Q, QIAO R P, CLEMENT YAW EFFAH, et al. Application of Data Mining Technology in Prevalence Risk Model for Com-Munity-Acquired Pneumonia[J]. Journal of Zhengzhou University (Medical Sciences), 2023, 58(3): 306-310.

[28] 李宇行, 何继玮, 钱敏, 等. 市售发酵食品中乳酸菌的耐药性评估及传播风险研究[J]. 食品与生物技术学报, 2024, 43(6): 21-30.

[29] LI Y X, HE J W, QIAN M, et al. Antibiotics Resistance Evaluation and Transmission Risk of Lactic Acid Bacteria in Commercial Fermented Foods[J]. Journal of Food Science and Biotechnology, 2024, 43(6): 21-30.

[30] 左玉婷, 徐明星, 李洋, 等. 基于层次分析法构建武汉市血吸虫病传播风险评估体系[J]. 中国血吸虫病防治杂志, 2023, 35(4): 374-378.

[31] ZUO Y T, XU M X, LI Y, et al. Construction of a Schistosomiasis Transmission Risk Assessment System in Wuhan City Based on Analytic Hierarchy Process[J]. Chinese Journal of Schistosomiasis Control, 2023, 35(4): 374-378.

[32] 涂金豆, 林忠伟, 孙辰. 基于LEC的新冠病毒环境传染人风险评估模型[J]. 计算机仿真, 2023, 40(3): 346-353.

[33] TU J D, LIN Z W, SUN C. Risk Assessment Model for Environmental Contagion of COVID-19 Based on LEC Method[J]. Computer Simulation, 2023, 40(3): 346-353.

基金资助

北京市数字教育研究课题基金资助项目(BDEC2024ZD02)