Journal of Computer Applications ›› 0, Vol. ›› Issue (): 357-363.DOI: 10.11772/j.issn.1001-9081.2024020172
• Frontier and comprehensive applications • Previous Articles Next Articles
					
						                                                                                                                                                                                                                                                                                    Kunhua ZHONG1, Yuwen CHEN1(
), Xiaolin QIN2, Qilong SUN1, Bin YI3
												  
						
						
						
					
				
Received:2024-02-22
															
							
																	Revised:2024-05-17
															
							
																	Accepted:2024-05-27
															
							
							
																	Online:2025-01-24
															
							
																	Published:2024-12-31
															
							
						Contact:
								Yuwen CHEN   
													通讯作者:
					陈芋文
							作者简介:钟坤华(1984—),男,重庆人,高级工程师,博士,主要研究方向:大数据分析、人工智能医疗应用基金资助:CLC Number:
Kunhua ZHONG, Yuwen CHEN, Xiaolin QIN, Qilong SUN, Bin YI. Review of machine learning-based sepsis prediction and intervention decision-making research[J]. Journal of Computer Applications, 0, (): 357-363.
钟坤华, 陈芋文, 秦小林, 孙启龙, 易斌. 基于机器学习的脓毒症预测与干预决策研究综述[J]. 《计算机应用》唯一官方网站, 0, (): 357-363.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2024020172
| 文献 | 问题 | 方法描述 | 性能 | 对比算法 | 
|---|---|---|---|---|
| 文献[ | 脓毒症患者 住院死亡率 预测  | 仅使用患者生命体征的动态变化,采用CNN、LSTM和RF这3种算法,预测败血症患者6~48 h内住院死亡的 风险。该回顾性研究基于台湾的医院数据,缺乏普适性  | 6 h: Accuracy:CNN 90.5%, LSTM 81.7%, RF 83.5% AUROC: CNN 0.840, LSTM 0.761,RF 0.770  | 无 | 
| 文献[ | 脓毒症预测 | 采用CNN算法验证脓毒症预测 | AUROC: 0.90,AUPRC: 0.62 | 无 | 
| 文献[ | 脓毒症 早期检测  | 采用9种机器学习方法对299例新生儿late-onset脓毒症早期检测,包括SVM、NB、TAN、AODE(Averaged One Dependence Estimator)、KNN、CART、RF、LR和LBR(Lazy Bayesian Rule)。所用数据均为无创指标 | 敏感性、特异性高于医生。 9种机器学习方法中,AUROC最高为0.78  | 医生诊断 | 
| 文献[ | 死亡风险 预后预测  | 采用随机生存森林构建模型,并对特征的重要性进行排名。单中心研究,缺乏外部验证 | C-index: 0.731 | SOFA评分, SAPS(Simplified Acute Physiology Score)-Ⅱ和APS-Ⅲ评分 | 
| 文献[ | 脓毒症早期 检测  | 提出MGP-RNN方法。从已有数据中学习连续特征的分布来处理缺失值。单中心研究,数据来自同一家医院。阳性预测值(Positive Predictive Value, PPV)较低 | C-statistic:0.88 | RF,Cox回归,PLR,clinical scores | 
| 文献[ | 脓毒症患者 住院死亡率 预测  | 基于MIMIC-Ⅲ开源数据集,采用LASSO回归、RF、GBM和LR构建预测模型。基于患者入ICU的前24h数据,无法提供动态预测 | AUROC:LASSO 0.829,RF 0.829, GBM 0.845,LR 0.833  | SAPS-Ⅱ | 
| 文献[ | 脓毒症预测 | 提出的模型分为2个完全无监督的阶段:表示学习和异常检测。采用递归自编码进行表示学习,采用聚类方法进行异常检测,属于无监督方法。对数据质量要求高,算法复杂度较高,可解释性低 | AUROC:0.82,F1-score:0.65, Accuracy:93%  | supervised LSTM | 
| 文献[ | 脓毒症检测 | 开源数据集上采用XGBoost方法检测脓毒症 | Accuracy: 92% | 无 | 
| 文献[ | 脓毒症患者 住院死亡率 预测  | 采用9种机器学习方法预测脓毒症患者住院死亡率,并提供SHAP(SHapley Additive exPlanations)和LIME(Local Interpretable Model-agnostic Explanations)解释;但缺乏外部验证和因果推断,影响模型的可信度 | RF 性能最好 AUROC: 0.81,Accuracy: 85%, Precision: 62%  | OASIS(Oxford Acute Severity of Illness Score)评分,SOFA评分 | 
| 文献[ | 脓毒症早期 预测  | 采用4种算法(RF、LR、GBM、决策树)预测ICU患者脓毒症。引入一种新的基于异常值的平均中值数据插补技术。仅使用了结构化数据;缺乏外部和独立评估 | RF结果最优: Accuracy: 99.01%,F1-Score: 0.99, AUROC: 0.999 9  | 无 | 
| 文献[ | 脓毒症早期 预测  | 采用梯度增强树算法对ICU患者脓毒症进行早期预测 | 梯度增强树的AUROC最好:发病前15 h为0.777,发病前10 h为0.769 | 决策树,随机森林, AdaBoost,MLP  | 
| 文献[ | 脓毒症早期 诊断  | 针对已有方法敏感性低,采用时间序列数据的独特分割方法。采用4种算法:KNN,RF,MLP, XGBoost | XGBoost算法最优: Recall: 98%,AUROC: 0.98  | 无 | 
| 文献[ | 脓毒症预测 | 采用广义线性模型(Generalized Linear Model, GLM)进行特征选择,构建ANN和RF脓毒症预测模型 | 优于临床评分系统 | SOFA评分, qSOFA评分,SIRS评分  | 
| 文献[ | 脓毒症早期 预测  | 基于患者生理数据,提出一种基于SVM和LSTM的脓毒症预测模型 | AUROC: 0.696 | 无 | 
| 文献[ | 脓毒症早期 识别  | 提出一种以医学知识为指导的新的跨中心协作学习框架SofaNet,采用多通道GRU结构预测不同系统的SOFA值。通过明确考虑领域知识(即多系统SOFA评分)设计早期败血症识别的隐私保护跨中心协作机制 | AUROC: 0.9216, AUPRC: 0.7197 | 逻辑回归,NN, XGBoost,GRU  | 
| 文献[ | 脓毒症早期 预测  | 提出一种使用各种机器学习和深度学习模型提前6 h预测败血症发病的方法 | AUROC: 0.888 | RF,XGBoost | 
| 文献[ | 脓毒症早期 预测  | 针对类别不平衡数据,提出SPMPH(Sepsis Prediction Model for Peripheral Hospitals)模型预测脓毒症的发生 | Accuracy: 95%,Precision: 98%, Recall: 91%,AUROC: 0.978  | LR, KNN, RF, AdaBoost, XGBoost | 
| 文献[ | 脓毒症早期 预测  | 将败血症的预测视为一个时间序列预测问题,融合基于脓毒症临床先验知识的人工特征与长短期记忆神经网络自动提取的深度特征,构建XGBoost和GBDT(Gradient Boosting Decision Tree)模型 | normalized utility score: 0.313 | 无 | 
| 文献[ | 脓毒症早期 预测  | 采用自然语言处理模型表示临床文本数据,构建脓毒症预测模型 | 标准效用得分提升6.07, AUROC提升2.89%  | qSOFA | 
| 文献[ | 脓毒症早期 预测  | 提出一种双重融合模型(DFSP) 早期融合:首先采用CNN和GRU提取深度特征,然后与手工特征相融合构建联合特征,最后采用GBDT构建多个预测模型 晚期融合:以早期融合的多个GBDT的输出为输入,采用端到端的神经网络(只有1个隐藏层)进行融合,得到最终的脓毒症风险  | 提前6 h脓毒症预测: AUROC: 0.92,Accuracy: 87%, Specificity: 0.87,Sensitivity: 0.80  | SIRS,qSOFA,DSPA(Deep SOFA-Sepsis Prediction Algorithm), ResNet,Time-phAsed | 
| 文献[ | 脓毒症干预 治疗策略  | 基于强化学习开发一种“AI临床医生”,用于静脉输液和血管升压药给药方式的脓毒症干预治疗辅助策略制定 | 接受与“AI临床医生”建议剂量相似患者的死亡率更低 | 人类临床医生 | 
| 文献[ | 脓毒症 个性化 治疗策略  | 提出了一种深度强化计算模型,用于制定脓毒症患者个体动态治疗策略,将堆叠张量自动编码器与Q学习相结合,以改进高维异构数据学习 | 能够达到脓毒症专家水平 | 脓毒症专家的治疗策略 | 
| 文献[ | 脓毒症治疗 策略  | 提出使用Mixture-of-Experts技术将监督学习和强化学习相结合的脓毒症治疗策略方法 | 所提出的模型中得出的策略优于医生的策略,并限制了危险行为的数量 | 医生的治疗策略、DDQN(Dueling Deep Q Network) | 
| 文献 | 问题 | 方法描述 | 性能 | 对比算法 | 
|---|---|---|---|---|
| 文献[ | 脓毒症患者 住院死亡率 预测  | 仅使用患者生命体征的动态变化,采用CNN、LSTM和RF这3种算法,预测败血症患者6~48 h内住院死亡的 风险。该回顾性研究基于台湾的医院数据,缺乏普适性  | 6 h: Accuracy:CNN 90.5%, LSTM 81.7%, RF 83.5% AUROC: CNN 0.840, LSTM 0.761,RF 0.770  | 无 | 
| 文献[ | 脓毒症预测 | 采用CNN算法验证脓毒症预测 | AUROC: 0.90,AUPRC: 0.62 | 无 | 
| 文献[ | 脓毒症 早期检测  | 采用9种机器学习方法对299例新生儿late-onset脓毒症早期检测,包括SVM、NB、TAN、AODE(Averaged One Dependence Estimator)、KNN、CART、RF、LR和LBR(Lazy Bayesian Rule)。所用数据均为无创指标 | 敏感性、特异性高于医生。 9种机器学习方法中,AUROC最高为0.78  | 医生诊断 | 
| 文献[ | 死亡风险 预后预测  | 采用随机生存森林构建模型,并对特征的重要性进行排名。单中心研究,缺乏外部验证 | C-index: 0.731 | SOFA评分, SAPS(Simplified Acute Physiology Score)-Ⅱ和APS-Ⅲ评分 | 
| 文献[ | 脓毒症早期 检测  | 提出MGP-RNN方法。从已有数据中学习连续特征的分布来处理缺失值。单中心研究,数据来自同一家医院。阳性预测值(Positive Predictive Value, PPV)较低 | C-statistic:0.88 | RF,Cox回归,PLR,clinical scores | 
| 文献[ | 脓毒症患者 住院死亡率 预测  | 基于MIMIC-Ⅲ开源数据集,采用LASSO回归、RF、GBM和LR构建预测模型。基于患者入ICU的前24h数据,无法提供动态预测 | AUROC:LASSO 0.829,RF 0.829, GBM 0.845,LR 0.833  | SAPS-Ⅱ | 
| 文献[ | 脓毒症预测 | 提出的模型分为2个完全无监督的阶段:表示学习和异常检测。采用递归自编码进行表示学习,采用聚类方法进行异常检测,属于无监督方法。对数据质量要求高,算法复杂度较高,可解释性低 | AUROC:0.82,F1-score:0.65, Accuracy:93%  | supervised LSTM | 
| 文献[ | 脓毒症检测 | 开源数据集上采用XGBoost方法检测脓毒症 | Accuracy: 92% | 无 | 
| 文献[ | 脓毒症患者 住院死亡率 预测  | 采用9种机器学习方法预测脓毒症患者住院死亡率,并提供SHAP(SHapley Additive exPlanations)和LIME(Local Interpretable Model-agnostic Explanations)解释;但缺乏外部验证和因果推断,影响模型的可信度 | RF 性能最好 AUROC: 0.81,Accuracy: 85%, Precision: 62%  | OASIS(Oxford Acute Severity of Illness Score)评分,SOFA评分 | 
| 文献[ | 脓毒症早期 预测  | 采用4种算法(RF、LR、GBM、决策树)预测ICU患者脓毒症。引入一种新的基于异常值的平均中值数据插补技术。仅使用了结构化数据;缺乏外部和独立评估 | RF结果最优: Accuracy: 99.01%,F1-Score: 0.99, AUROC: 0.999 9  | 无 | 
| 文献[ | 脓毒症早期 预测  | 采用梯度增强树算法对ICU患者脓毒症进行早期预测 | 梯度增强树的AUROC最好:发病前15 h为0.777,发病前10 h为0.769 | 决策树,随机森林, AdaBoost,MLP  | 
| 文献[ | 脓毒症早期 诊断  | 针对已有方法敏感性低,采用时间序列数据的独特分割方法。采用4种算法:KNN,RF,MLP, XGBoost | XGBoost算法最优: Recall: 98%,AUROC: 0.98  | 无 | 
| 文献[ | 脓毒症预测 | 采用广义线性模型(Generalized Linear Model, GLM)进行特征选择,构建ANN和RF脓毒症预测模型 | 优于临床评分系统 | SOFA评分, qSOFA评分,SIRS评分  | 
| 文献[ | 脓毒症早期 预测  | 基于患者生理数据,提出一种基于SVM和LSTM的脓毒症预测模型 | AUROC: 0.696 | 无 | 
| 文献[ | 脓毒症早期 识别  | 提出一种以医学知识为指导的新的跨中心协作学习框架SofaNet,采用多通道GRU结构预测不同系统的SOFA值。通过明确考虑领域知识(即多系统SOFA评分)设计早期败血症识别的隐私保护跨中心协作机制 | AUROC: 0.9216, AUPRC: 0.7197 | 逻辑回归,NN, XGBoost,GRU  | 
| 文献[ | 脓毒症早期 预测  | 提出一种使用各种机器学习和深度学习模型提前6 h预测败血症发病的方法 | AUROC: 0.888 | RF,XGBoost | 
| 文献[ | 脓毒症早期 预测  | 针对类别不平衡数据,提出SPMPH(Sepsis Prediction Model for Peripheral Hospitals)模型预测脓毒症的发生 | Accuracy: 95%,Precision: 98%, Recall: 91%,AUROC: 0.978  | LR, KNN, RF, AdaBoost, XGBoost | 
| 文献[ | 脓毒症早期 预测  | 将败血症的预测视为一个时间序列预测问题,融合基于脓毒症临床先验知识的人工特征与长短期记忆神经网络自动提取的深度特征,构建XGBoost和GBDT(Gradient Boosting Decision Tree)模型 | normalized utility score: 0.313 | 无 | 
| 文献[ | 脓毒症早期 预测  | 采用自然语言处理模型表示临床文本数据,构建脓毒症预测模型 | 标准效用得分提升6.07, AUROC提升2.89%  | qSOFA | 
| 文献[ | 脓毒症早期 预测  | 提出一种双重融合模型(DFSP) 早期融合:首先采用CNN和GRU提取深度特征,然后与手工特征相融合构建联合特征,最后采用GBDT构建多个预测模型 晚期融合:以早期融合的多个GBDT的输出为输入,采用端到端的神经网络(只有1个隐藏层)进行融合,得到最终的脓毒症风险  | 提前6 h脓毒症预测: AUROC: 0.92,Accuracy: 87%, Specificity: 0.87,Sensitivity: 0.80  | SIRS,qSOFA,DSPA(Deep SOFA-Sepsis Prediction Algorithm), ResNet,Time-phAsed | 
| 文献[ | 脓毒症干预 治疗策略  | 基于强化学习开发一种“AI临床医生”,用于静脉输液和血管升压药给药方式的脓毒症干预治疗辅助策略制定 | 接受与“AI临床医生”建议剂量相似患者的死亡率更低 | 人类临床医生 | 
| 文献[ | 脓毒症 个性化 治疗策略  | 提出了一种深度强化计算模型,用于制定脓毒症患者个体动态治疗策略,将堆叠张量自动编码器与Q学习相结合,以改进高维异构数据学习 | 能够达到脓毒症专家水平 | 脓毒症专家的治疗策略 | 
| 文献[ | 脓毒症治疗 策略  | 提出使用Mixture-of-Experts技术将监督学习和强化学习相结合的脓毒症治疗策略方法 | 所提出的模型中得出的策略优于医生的策略,并限制了危险行为的数量 | 医生的治疗策略、DDQN(Dueling Deep Q Network) | 
| 数据集 | 样本数 | 人口统计特性 | 特征类型 | 
|---|---|---|---|
| MIMIC-Ⅲ | >40 000 | 年龄、性别、基础疾病状态、入院诊断、种族和社会经济状况、地理分析、临床特征等 | 静态患者数据、动态生理参数、实验室检查结果、药物治疗记录、临床事件、医疗文书记录 | 
| PhysioNet Challenge | 40 336 | 年龄、性别、种族、基础健康状况信息(ICU病房管理标识符、入院和ICU入院之间的时间、ICU住院时间) | 生理指标、实验室检查结果、用药记录和治疗措施、重症评分(如SOFA、qSOFA等) | 
| 数据集 | 样本数 | 人口统计特性 | 特征类型 | 
|---|---|---|---|
| MIMIC-Ⅲ | >40 000 | 年龄、性别、基础疾病状态、入院诊断、种族和社会经济状况、地理分析、临床特征等 | 静态患者数据、动态生理参数、实验室检查结果、药物治疗记录、临床事件、医疗文书记录 | 
| PhysioNet Challenge | 40 336 | 年龄、性别、种族、基础健康状况信息(ICU病房管理标识符、入院和ICU入院之间的时间、ICU住院时间) | 生理指标、实验室检查结果、用药记录和治疗措施、重症评分(如SOFA、qSOFA等) | 
| 文献 | 数据集 | 文献 | 数据集 | 
|---|---|---|---|
| 文献[ | 诊所数据 | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅲ | 文献[ | PhysioNet Challenge | 
| 文献[ | ICU数据 | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅳ | 文献[ | PhysioNet Challenge | 
| 文献[ | 院方数据 | 文献[ | MIMIC and PhysioNet Challenge | 
| 文献[ | MIMIC-Ⅲ | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅲ | 文献[ | PhysioNet Challenge | 
| 文献[ | ICU数据 | 文献[ | ICU数据 | 
| 文献[ | MIMIC-Ⅳ | 文献[ | MIMIC-Ⅲ | 
| 文献[ | PhysioNet Challenge | 
| 文献 | 数据集 | 文献 | 数据集 | 
|---|---|---|---|
| 文献[ | 诊所数据 | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅲ | 文献[ | PhysioNet Challenge | 
| 文献[ | ICU数据 | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅳ | 文献[ | PhysioNet Challenge | 
| 文献[ | 院方数据 | 文献[ | MIMIC and PhysioNet Challenge | 
| 文献[ | MIMIC-Ⅲ | 文献[ | MIMIC-Ⅲ | 
| 文献[ | MIMIC-Ⅲ | 文献[ | PhysioNet Challenge | 
| 文献[ | ICU数据 | 文献[ | ICU数据 | 
| 文献[ | MIMIC-Ⅳ | 文献[ | MIMIC-Ⅲ | 
| 文献[ | PhysioNet Challenge | 
| 1 | SINGER M, DEUTSCHMAN C S, SEYMOUR C W, et al. The third international consensus definitions for sepsis and septic shock (sepsis-3)[J]. JAMA, 2016, 315(8): 801-810. | 
| 2 | 王仲,魏捷,朱华栋,等. 中国脓毒症早期预防与阻断急诊专家共识[J]. 临床急诊杂志, 2020, 21(7): 517-529. | 
| 3 | RUDD K E, JOHNSON S C, AGESA K M, et al. Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study[J]. The Lancet, 395(10219): 200-211. | 
| 4 | CHENG C Y, KUNG C T, CHEN F C, et al. Machine learning models for predicting in-hospital mortality in patient with sepsis: analysis of vital sign dynamics[J]. Frontiers in Medicine, 2022, 9: No.964667. | 
| 5 | PERSSON I, ÖSTLING A, ARLBRANDT M, et al. A machine learning sepsis prediction algorithm for intended intensive care unit use (NAVOY sepsis): proof-of-concept study[J]. JMIR Formative Research, 2021, 5(9): No.e28000. | 
| 6 | MANI S, OZDAS A, ALIFERIS C, et al. Medical decision support using machine learning for early detection of late-onset neonatal sepsis[J]. Journal of the American Medical Informatics Association, 2014, 21(2): 326-336. | 
| 7 | BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1):5-32. | 
| 8 | PAUL A, MUKHERJEE D P, DAS P, et al. Improved random forest for classification[J]. IEEE Transactions on Image Processing, 2018, 27(8): 4012-4024. | 
| 9 | HU C, LI L, LI Y, et al. Explainable machine-learning model for prediction of in-hospital mortality in septic patients requiring intensive care unit readmission[J]. Infectious Diseases and Therapy, 2022, 11(4): 1695-1713. | 
| 10 | RAHMAN M A, IBRAHIM A A, TUMIAN A. Feature selection using generalized linear model for machine learning-based sepsis prediction[C]// Proceedings of the 2023 International Conference on Advances in Intelligent Computing and Applications. Piscataway: IEEE, 2023:1-6. | 
| 11 | ROUT S K, SAHU B, REGULWAR G B, et al. Deep learning in early prediction of sepsis and diagnosis[C]// Proceedings of the 2023 International Conference for Advancement in Technology. Piscataway: IEEE, 2023: 1-5. | 
| 12 | ULLAH A, QAYYUM H, KHAN M K, et al. Sepsis detection using Extreme Gradient Boost (XGB): a supervised learning approach[C]// Proceedings of the 2021 Mohammad Ali Jinnah University International Conference on Computing. Piscataway: IEEE, 2021: 1-6. | 
| 13 | AREF S, FERNANDO L, GHANTA S. A time series clinical data-driven preprocessing approach to early sepsis diagnosis[C]// Proceedings of the 2023 IEEE Conference on Artificial Intelligence. Piscataway: IEEE, 2023: 145-147. | 
| 14 | KONG G, LIN K, HU Y. Using machine learning methods to predict in-hospital mortality of sepsis patients in the ICU[J]. BMC Medical Informatics and Decision Making, 2020, 20: No.251. | 
| 15 | BOTALB A, MOINUDDIN M, AL-SAGGAF U M, et al. Contrasting Convolutional Neural Network (CNN) with Multi-Layer Perceptron (MLP) for big data analysis[C]// Proceedings of the 2018 International Conference on Intelligent and Advanced Systems. Piscataway: IEEE, 2018: 1-5. | 
| 16 | YING T X, ABU-SAMAH A. Early prediction of sepsis for ICU patients using gradient boosted tree[C]// Proceedings of the 2022 IEEE International Conference on Automatic Control and Intelligent Systems. Piscataway: IEEE, 2022: 78-83. | 
| 17 | POPESCU M C, BALAS V E, PERESCU-POPESCU L, et al. Multilayer perceptron and neural networks[J]. WSEAS Transactions on Circuits and Systems, 2009, 8(7): 579-588. | 
| 18 | BEDOYA A D, FUTOMA J, CLEMENT M E, et al. Machine learning for early detection of sepsis: an internal and temporal validation study[J]. JAMIA Open, 2020, 3(2): 252-260. | 
| 19 | HE Z, DU L, ZHANG P, et al. Early sepsis prediction using ensemble learning with deep features and artificial features extracted from clinical electronic health records[J]. Critical Care Medicine, 2020, 48(12):e1337-e1342. | 
| 20 | QIN F, MADAN V, RATAN U, et al. Improving early sepsis prediction with multi modal learning[EB/OL]. [2023-07-21].. | 
| 21 | DUAN Y, HUO J, CHEN M, et al. Early prediction of sepsis using double fusion of deep features and handcrafted features[J]. Applied Intelligence, 2023, 53(14): 17903-17919. | 
| 22 | KOMOROWSKI M, CELI L A, BADAWI O, et al. The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care[J]. Nature Medicine, 2018, 24(11): 1716-1720. | 
| 23 | YU H, ZHANG Q. A deep reinforcement computation model for sepsis treatment[C]// Proceedings of the 2022 IEEE International Conference on Bioinformatics and Biomedicine. Piscataway: IEEE, 2022: 3217-3222. | 
| 24 | DO T C, YANG H J, YOO S B, et al. Combining reinforcement learning with supervised learning for sepsis treatment[C]// Proceedings of the 9th International Conference on Smart Media and Applications. New York: ACM, 2020: 219-223. | 
| 25 | ZHANG L, HUANG T, XU F, et al. Prediction of prognosis in elderly patients with sepsis based on machine learning (random survival forest)[J]. BMC Emergency Medicine, 2022, 22: No.26. | 
| 26 | RAMOS G, GJINI E, COELHO L, et al. Unsupervised learning approach for predicting sepsis onset in ICU patients[C]// Proceedings of the 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway: IEEE, 2021: 1916-1919. | 
| 27 | SRIMEDHA B C, RAJ R N, MAYYA V. A comprehensive machine learning based pipeline for an accurate early prediction of sepsis in ICU[J]. IEEE Access, 2022, 10: 105120-105132. | 
| 28 | DING R, RONG F, HAN X, et al. Cross-center early sepsis recognition by medical knowledge guided collaborative learning for data-scarce hospitals[C]// Proceedings of the ACM Web Conference 2023. New York: ACM, 2023: 3987-3993. | 
| 29 | SHAH N, BHATIA J, VASAVAT N, et al. Early sepsis detection using machine learning and neural networks[C]// Proceedings of the 2nd Global Conference for Advancement in Technology. Piscataway: IEEE, 2021: 1-6. | 
| 30 | SHENOY A, BABU R K. Performance analysis of class imbalance handling techniques for early sepsis prediction using machine learning algorithms[C]// Proceedings of the 8th International Conference on Smart Structures and Systems. Piscataway: IEEE, 2022: 1-6. | 
| 31 | ABBAS M, EL-MANZALAWY Y. Machine learning based refined differential gene expression analysis of pediatric sepsis[J]. BMC Medical Genomics, 2020, 13: No.122. | 
| 32 | SHASHIKUMAR S P, SHAH A J, CLIFFORD G D, et al. Detection of paroxysmal atrial fibrillation using attention-based bidirectional recurrent neural networks[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2018: 715-723. | 
| 33 | MEROUANI M, GUIGNARD B, VINCENT F, et al. Norepinephrine weaning in septic shock patients by closed loop control based on fuzzy logic[J]. Critical Care, 2008, 12(6): No.R155. | 
| 34 | RAWSON T M, HERNANDEZ B, MOORE L S P, et al. A real-world evaluation of a case-based reasoning algorithm to support antimicrobial prescribing decisions in acute care[J]. Clinical Infectious Diseases, 2021, 72(12): 2103-2111. | 
| 35 | LAL A, LI G, CUBRO E, et al. Development and verification of a digital twin patient model to predict specific treatment response during the first 24 hours of sepsis[J]. Critical Care Explorations, 2020, 2(11): No.e0249. | 
| 36 | TURNER R B, KOJIRO K, SHEPHARD E A, et al. Review and validation of Bayesian dose-optimizing software and equations for calculation of the vancomycin area under the curve in critically Ill patients[J]. Pharmacotherapy, 2018, 38(12):1174-1183. | 
| [1] | Yonghao LIANG, Jinlong LI. Novel message passing network for neural Boolean satisfiability problem solver [J]. Journal of Computer Applications, 2025, 45(9): 2934-2940. | 
| [2] | Lina GE, Mingyu WANG, Lei TIAN. Review of research on efficiency of federated learning [J]. Journal of Computer Applications, 2025, 45(8): 2387-2398. | 
| [3] | Shujian GUO, Jieyue YU, Xuesong YIN. Graph regularized elastic net subspace clustering [J]. Journal of Computer Applications, 2025, 45(5): 1464-1471. | 
| [4] | Junyi ZHU, Leilei CHANG, Xiaobin XU, Zhiyong HAO, Haiyue YU, Jiang JIANG. Self-supervised learning method using minimal prior knowledge [J]. Journal of Computer Applications, 2025, 45(4): 1035-1041. | 
| [5] | Zirong HONG, Guangqing BAO. Review of radar automatic target recognition based on ensemble learning [J]. Journal of Computer Applications, 2025, 45(2): 371-382. | 
| [6] | You SHANG, Xianghua MIAO. Bayesian membership inference attacks for generative adversarial networks [J]. Journal of Computer Applications, 2025, 45(10): 3252-3258. | 
| [7] | Yiming WANG, Shiyuan LI, Nanqing LIAO, Qingfeng CHEN. Uncertainty-aware unsupervised medical image registration model based on evidential deep learning [J]. Journal of Computer Applications, 2025, 45(10): 3371-3380. | 
| [8] | Zihao YAO, Yuanming LI, Ziqiang MA, Yang LI, Lianggen WEI. Multi-object cache side-channel attack detection model based on machine learning [J]. Journal of Computer Applications, 2024, 44(6): 1862-1871. | 
| [9] | Xuebin CHEN, Zhiqiang REN, Hongyang ZHANG. Review on security threats and defense measures in federated learning [J]. Journal of Computer Applications, 2024, 44(6): 1663-1672. | 
| [10] | Wei SHE, Yang LI, Lihong ZHONG, Defeng KONG, Zhao TIAN. Hyperparameter optimization for neural network based on improved real coding genetic algorithm [J]. Journal of Computer Applications, 2024, 44(3): 671-676. | 
| [11] | Yi ZHENG, Cunyi LIAO, Tianqian ZHANG, Ji WANG, Shouyin LIU. Image denoising-based cell-level RSRP estimation method for urban areas [J]. Journal of Computer Applications, 2024, 44(3): 855-862. | 
| [12] | Bo LI, Jianqiang HUANG, Dongqiang HUANG, Xiaoying WANG. Adaptive computing optimization of sparse matrix-vector multiplication based on heterogeneous platforms [J]. Journal of Computer Applications, 2024, 44(12): 3867-3875. | 
| [13] | Xuebin CHEN, Changsheng QU. Overview of backdoor attacks and defense in federated learning [J]. Journal of Computer Applications, 2024, 44(11): 3459-3469. | 
| [14] | Renke SUN, Zhiyu HUANGFU, Hu CHEN, Zhongnian LI, Xinzheng XU. Survey of neural architecture search [J]. Journal of Computer Applications, 2024, 44(10): 2983-2994. | 
| [15] | Wenze CHAI, Jing FAN, Shukui SUN, Yiming LIANG, Jingfeng LIU. Overview of deep metric learning [J]. Journal of Computer Applications, 2024, 44(10): 2995-3010. | 
| Viewed | ||||||
| 
										Full text | 
									
										 | 
								|||||
| 
										Abstract | 
									
										 | 
								|||||