

浏览全部资源
扫码关注微信
1.新疆大学 软件学院,新疆 乌鲁木齐 830091
2.新疆大学 网络与信息技术中心,新疆 乌鲁木齐 830046
3.新疆医科大学 医学工程与技术学院,新疆 乌鲁木齐 830054
4.新疆大学 计算机科学与技术学院,新疆 乌鲁木齐 830017
Received:26 April 2025,
Revised:2025-11-14,
Accepted:16 November 2025,
Published:25 January 2026
移动端阅览
张雅楠,张琳琳,郭渊博,毕雪华,赵楷.一种用于心衰患者死亡率预测的数据多重插补方法[J].新疆大学学报(自然科学版中英文),2026,43(1):61-69.
Zhang Yanan,Zhang Linlin,Guo Yuanbo,Bi Xuehua,Zhao Kai. A Data Multiple Imputation Method for Mortality Prediction in Patients with Heart Failure[J]. Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(1):61-69.
张雅楠,张琳琳,郭渊博,毕雪华,赵楷.一种用于心衰患者死亡率预测的数据多重插补方法[J].新疆大学学报(自然科学版中英文),2026,43(1):61-69. DOI: 10.13568/j.cnki.651094.651316.2025.04.26.0001.
Zhang Yanan,Zhang Linlin,Guo Yuanbo,Bi Xuehua,Zhao Kai. A Data Multiple Imputation Method for Mortality Prediction in Patients with Heart Failure[J]. Journal of Xinjiang University(Natural Science Edition in Chinese and English),2026,43(1):61-69. DOI: 10.13568/j.cnki.651094.651316.2025.04.26.0001.
针对真实数据采集机制不完善致使数据缺失、现有方法对临床特征表示不足导致模型性能受限问题,本文提出一种用于心衰患者死亡率预测的数据多重插补方法(Self-attention and Generative adversarial network based Mortality Prediction, SGMP).首先,针对临床特征在变分自编码器(Variational Autoencoder, VAE)的潜在空间中结合自注意力机制动态融合多组候选估计值,并结合生成对抗网络(Generative Adversarial Network, GAN)的对抗训练策略优化表征学习能力.然后,根据掩码矩阵有效获取候选估计结果,实现缺失数据多重插补.最后,采用合成少数类过采样技术(Synthetic Minority Over-sampling Technique, SMOTE)进行数据增强,使用多层感知机(Multilayer Perceptron, MLP)实现死亡率预测.基于新疆某三甲医院心衰患者数据进行验证,结果表明:死亡率预测任务中,相比其他模型,SGMP在多个指标上有明显提升,受试者工作特征曲线下面积达到0.902.
Aiming at the problem that the imperfect data collection mechanism of diagnosis and treatment leads to data loss and the poor quality of existing network feature extraction leads to the limited performance of clinical prediction models
a data multiple imputation method (Self-attention and Generative adversarial network based Mortality Prediction
SGMP) for mortality prediction of patients with heart failure is proposed. Firstly
the self-attention mechanism is used to dynamically fuse multiple sets of candidate estimates in the potential space of the variational autoencoder (VAE)
and the adversarial training strategy of the generative adversarial network (GAN) is introduced to optimize the representation learning ability. Then
the candidate estimation results are effectively obtained according to the mask matrix
and the multiple interpolation of missing data is realized. Finally
the synthetic minority over-sampling technique (SMOTE) is used to enhance the data
and the multilayer perceptron (MLP) is used to predict the mortality rate. Based on the diagnosis and treatment data of heart failure patients in a tertiary hospital in Xinjiang
the results show that: in the mortality prediction task
SGMP has significantly improved in multiple indicators compared with other models
and the area under the receiver operating characteristic curve reaches 0.902.
Chen J T , Huang S , Zhang Y , et al . Congenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts [J]. Nature Communications , 2024 , 15 : 976 .
Chen J , Aronowitz P . Congestive heart failure [J]. Medical Clinics of North America , 2022 , 106 : 447 - 458 .
付健 . 基于MIMIC-Ⅲ数据库的心衰患者死亡率预测模型研究 [D]. 太原 : 太原理工大学 , 2021 .
Fu J . Study of model for predicting mortality for heart failure patients based on MIMIC-Ⅲ database [D]. Taiyuan : Taiyuan University of Technology , 2021 . (in Chinese)
Liu M X , Li S Q , Yuan H , et al . Handling missing values in healthcare data:A systematic review of deep learning-based imputation techniques [J]. Artificial Intelligence in Medicine , 2023 , 142 : 102587 .
Bernardini M , Doinychko A , Romeo L , et al . A novel missing data imputation approach based on clinical conditional generative adversarial networks applied to EHR datasets [J]. Computers in Biology and Medicine , 2023 , 163 : 107188 .
Austin P C , White I R , Lee D S , et al . Missing data in clinical research:A tutorial on multiple imputation [J]. Canadian Journal of Cardiology , 2021 , 37 : 1322 - 1331 .
Zhao C , Su K J , Wu C , et al . Multi-scale variational autoencoder for imputation of missing values in untargeted metabolomics using whole-genome sequencing data [J]. Computers in Biology and Medicine , 2024 , 179 : 108813 .
Sun Y G , Li J , Xu Y F , et al . Deep learning versus conventional methods for missing data imputation:A review and comparative study [J]. Expert Systems with Applications , 2023 , 227 : 120201 .
Ma Q , Lee W C , Fu T Y , et al . MIDIA:Exploring denoising autoencoders for missing data imputation [J]. Data Mining and Knowledge Discovery , 2020 , 34 : 1859 - 1897 .
Kabir S , Farrokhvar L . Non-linear missing data imputation for healthcare data via index-aware autoencoders [J]. Health Care Management Science , 2022 , 25 : 484 - 497 .
Chen Z , Cao B , Edwards A , et al . A deep imputation and inference framework for estimating personalized and race-specific causal effects of genomic alterations on PSA [J]. Journal of Bioinformatics and Computational Biology , 2021 , 19 ( 4 ): 2150016 .
何琨 , 陈振华 , 黄绍 , 等 . 基于变分编码器与主成分分析的电磁对抗攻击 [J]. 华中科技大学学报(自然科学版) , 2024 , 52 ( 11 ): 1 - 7 .
He K , Chen Z H , Huang S , et al . Electromagnetic adversarial attack based on variational auto-encoder and principal component analysis [J]. Journal of Huazhong University of Science and Technology(Natural Science Edition) , 2024 , 52 ( 11 ): 1 - 7 . (in Chinese)
Zhao J Q , Rong C T , Dang X , et al . QAR data imputation using generative adversarial network with self-attention mecha-nism [J]. Big Data Mining and Analytics , 2024 , 7 ( 1 ): 12 - 28 .
Dong W N , Fong D Y T , Yoon J S , et al . Generative adversarial networks for imputing missing data for big data clinical resear-ch [J]. BMC Medical Research Methodology , 2021 , 21 : 78 .
施媛波 . 变分自编码器和注意力机制的异常入侵检测方法 [J]. 重庆邮电大学学报(自然科学版) , 2022 , 34 ( 6 ): 1071 - 1078 .
Shi Y B . Anomaly intrusion detection method based on variational autoencoder and attention mechanism [J]. Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition) , 2022 , 34 ( 6 ): 1071 - 1078 . (in Chinese)
粟佳 , 于洪 . 基于条件生成对抗插补网络的双重判别器缺失值插补算法 [J]. 计算机应用 , 2024 , 44 ( 5 ): 1423 - 1427 .
Su J , Yu H . Missing value imputation algorithm using dual discriminator based on conditional generative adversarial imputation network [J]. Journal of Computer Applications , 2024 , 44 ( 5 ): 1423 - 1427 . (in Chinese)
Johnson A E W , Pollard T J , Shen L , et al . Data descriptor:MIMIC-III,a freely accessible critical care database [J]. Scientific Data , 2016 , 3 : 160035 .
Chawla N V , Bowyer K W , Hall L O , et al . SMOTE:Synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research , 2002 , 16 : 321 - 357 .
Stekhoven D J , Bühlmann P . MissForest:Non-parametric missing value imputation for mixed-type data [J]. Bioinformatics , 2012 , 28 ( 1 ): 112 - 118 .
Beretta L , Santaniello A . Nearest neighbor imputation algorithms:A critical evaluation [J]. BMC Medical Informatics and Decision Making , 2016 , 16 ( S3 ): 74 .
Kingma D P , Welling M . Auto-encoding variational Bayes [PP/OL]. V11.arXiv ( 2022-12-10 )[ 2025-01-15 ]. https://arxiv.org/pdf/1312.6114 https://arxiv.org/pdf/1312.6114 .
van Buuren S , Groothuis-Oudshoorn K . MICE:Multivariate imputation by chained equations in R [J]. Journal of Statistical Software , 2011 , 45 ( 3 ): 1 - 67 .
Mattei P A , Frellsen J . MIWAE:Deep generative modelling and imputation of incomplete data sets [PP/OL]. V2.arXiv ( 2019-02-04 )[ 2025-01-15 ]. https://arxiv.org/pdf/1812.02633 https://arxiv.org/pdf/1812.02633 .
Pereira R C , Abreu P H , Rodrigues P P . Partial multiple imputation with variational autoencoders:Tackling not at randomness in healthcare data [J]. IEEE Journal of Biomedical and Health Informatics , 2022 , 26 ( 8 ): 4218 - 4227 .
Monzo L , Girerd N , Ferreira J P , et al . High risk of stroke in patients with worsening heart failure,reduced ejection fraction,coronary heart disease and sinus rhythm:Risk prediction score analysis from the COMMANDER-HF trial [J]. Journal of Cardiac Failure , 2024 , 30 : 618 - 623 .
Fuery M A , Leifer E S , Samsky M D , et al . Prognostic impact of repeated NT-proBNP measurements in patients with heart fai-lure with reduced ejection fraction [J]. JACC:Heart Failure , 2024 , 12 ( 3 ): 479 - 487 .
Tolomeo P , Butt J H , Kondo T , et al . Independent prognostic importance of blood urea nitrogen to creatinine ratio in heart fai-lure [J]. European Journal of Heart Failure , 2024 , 26 : 245 - 256 .
0
Views
3
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621