• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

脓毒症患者预测分析解决方案综述

A Review of Predictive Analytics Solutions for Sepsis Patients.

机构信息

Biomedical Informatics and Medical Education, School of Medicine, University of Washington, Seattle, Washington, United States.

出版信息

Appl Clin Inform. 2020 May;11(3):387-398. doi: 10.1055/s-0040-1710525. Epub 2020 May 27.

DOI:10.1055/s-0040-1710525
PMID:32462640
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7253313/
Abstract

BACKGROUND

Early detection and efficient management of sepsis are important for improving health care quality, effectiveness, and costs. Due to its high cost and prevalence, sepsis is a major focus area across institutions and many studies have emerged over the past years with different models or novel machine learning techniques in early detection of sepsis or potential mortality associated with sepsis.

OBJECTIVE

To understand predictive analytics solutions for sepsis patients, either in early detection of onset or mortality.

METHODS AND RESULTS

We performed a systematized narrative review and identified common and unique characteristics between their approaches and results in studies that used predictive analytics solutions for sepsis patients. After reviewing 148 retrieved papers, a total of 31 qualifying papers were analyzed with variances in model, including linear regression ( = 2), logistic regression ( = 5), support vector machines ( = 4), and Markov models ( = 4), as well as population (range: 24-198,833) and feature size (range: 2-285). Many of the studies used local data sets of varying sizes and locations while others used the publicly available Medical Information Mart for Intensive Care data. Additionally, vital signs or laboratory test results were commonly used as features for training and testing purposes; however, a few used more unique features including gene expression data from blood plasma and unstructured text and data from clinician notes.

CONCLUSION

Overall, we found variation in the domain of predictive analytics tools for septic patients, from feature and population size to choice of method or algorithm. There are still limitations in transferability and generalizability of the algorithms or methods used. However, it is evident that implementing predictive analytics tools are beneficial in the early detection of sepsis or death related to sepsis. Since most of these studies were retrospective, the translational value in the real-world setting in different wards should be further investigated.

摘要

背景

早期发现和有效管理脓毒症对于提高医疗质量、效果和成本至关重要。由于脓毒症成本高、发病率高,因此它是各机构的重点关注领域,近年来出现了许多使用不同模型或新型机器学习技术来早期检测脓毒症或与脓毒症相关的潜在死亡率的研究。

目的

了解脓毒症患者的预测分析解决方案,无论是在早期发现发病还是死亡率方面。

方法和结果

我们进行了系统的叙述性综述,并在使用预测分析解决方案的脓毒症患者研究中,确定了他们的方法和结果之间的共同和独特特征。在回顾了 148 篇检索到的论文后,总共分析了 31 篇合格论文,这些论文的模型存在差异,包括线性回归(=2)、逻辑回归(=5)、支持向量机(=4)和马尔可夫模型(=4),以及人群(范围:24-198833)和特征大小(范围:2-285)。许多研究使用了不同大小和位置的本地数据集,而其他研究则使用了公开的医疗信息集市重症监护数据。此外,生命体征或实验室测试结果通常用作训练和测试目的的特征;然而,有一些研究使用了更独特的特征,包括来自血浆的基因表达数据以及非结构化文本和来自临床医生笔记的数据。

结论

总体而言,我们发现脓毒症患者预测分析工具的领域存在差异,从特征和人群规模到方法或算法的选择。所使用的算法或方法的可转移性和通用性仍然存在限制。然而,实施预测分析工具显然有助于早期发现脓毒症或与脓毒症相关的死亡。由于这些研究大多是回顾性的,因此应该进一步研究在不同病房的真实环境中的转化价值。

相似文献

1
A Review of Predictive Analytics Solutions for Sepsis Patients.脓毒症患者预测分析解决方案综述
Appl Clin Inform. 2020 May;11(3):387-398. doi: 10.1055/s-0040-1710525. Epub 2020 May 27.
2
Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach.急诊科脓毒症患者院内死亡率的预测:一种基于本地大数据驱动的机器学习方法。
Acad Emerg Med. 2016 Mar;23(3):269-78. doi: 10.1111/acem.12876. Epub 2016 Feb 13.
3
[Constructing a predictive model for the death risk of patients with septic shock based on supervised machine learning algorithms].基于监督机器学习算法构建脓毒症休克患者死亡风险预测模型
Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2024 Apr;36(4):345-352. doi: 10.3760/cma.j.cn121430-20230930-00832.
4
An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU.一种用于 ICU 中脓毒症准确预测的可解释机器学习模型。
Crit Care Med. 2018 Apr;46(4):547-553. doi: 10.1097/CCM.0000000000002936.
5
Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.一种用于早期严重脓毒症预测的机器学习算法的验证:一项回顾性研究,使用来自 461 家美国医院的多样化数据集提前 48 小时预测严重脓毒症。
BMC Med Inform Decis Mak. 2020 Oct 27;20(1):276. doi: 10.1186/s12911-020-01284-x.
6
Folic acid supplementation and malaria susceptibility and severity among people taking antifolate antimalarial drugs in endemic areas.在流行地区,服用抗叶酸抗疟药物的人群中,叶酸补充剂与疟疾易感性和严重程度的关系。
Cochrane Database Syst Rev. 2022 Feb 1;2(2022):CD014217. doi: 10.1002/14651858.CD014217.
7
Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies.利用常规电子健康记录进行感染管理的机器学习:未来技术的工具、技术和报告。
Clin Microbiol Infect. 2020 Oct;26(10):1291-1299. doi: 10.1016/j.cmi.2020.02.003. Epub 2020 Feb 13.
8
Clinical Decision-Support Systems for Detection of Systemic Inflammatory Response Syndrome, Sepsis, and Septic Shock in Critically Ill Patients: A Systematic Review.用于检测重症患者全身炎症反应综合征、脓毒症和脓毒性休克的临床决策支持系统:一项系统评价
Methods Inf Med. 2019 Dec;58(S 02):e43-e57. doi: 10.1055/s-0039-1695717. Epub 2019 Sep 9.
9
Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review.使用临床文本进行机器学习的脓毒症预测、早期检测和识别:系统评价。
J Am Med Inform Assoc. 2022 Jan 29;29(3):559-575. doi: 10.1093/jamia/ocab236.
10
Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.仅使用生命体征数据在急诊科、普通病房和重症监护病房对脓毒症预测算法进行多中心验证。
BMJ Open. 2018 Jan 26;8(1):e017833. doi: 10.1136/bmjopen-2017-017833.

引用本文的文献

1
A scoping review on pediatric sepsis prediction technologies in healthcare.一项关于医疗保健中儿童脓毒症预测技术的范围综述。
NPJ Digit Med. 2024 Dec 4;7(1):353. doi: 10.1038/s41746-024-01361-9.
2
TCKAN: a novel integrated network model for predicting mortality risk in sepsis patients.TCKAN:一种用于预测脓毒症患者死亡风险的新型综合网络模型。
Med Biol Eng Comput. 2025 Apr;63(4):1013-1025. doi: 10.1007/s11517-024-03245-2. Epub 2024 Nov 19.
3
Analysis of the Relevant Vital Signs and Infection of Sepsis Patients and to Explore the Influencing Factors of Acute Lung Injury/Acute Respiratory Distress Syndrome.脓毒症患者相关生命体征及感染情况分析并探讨急性肺损伤/急性呼吸窘迫综合征的影响因素
Contrast Media Mol Imaging. 2022 Sep 2;2022:7718248. doi: 10.1155/2022/7718248. eCollection 2022.
4
Assessing the Predictive and Analytics Capability of Electronic Clinical Data for High-Cost Patients.评估电子临床数据对高成本患者的预测及分析能力。
AMIA Jt Summits Transl Sci Proc. 2023 Jun 16;2023:101-107. eCollection 2023.
5
Online Critical-State Detection of Sepsis Among ICU Patients using Jensen-Shannon Divergence.利用 Jensen-Shannon 散度对 ICU 患者脓毒症进行在线临界状态检测。
AMIA Annu Symp Proc. 2023 Apr 29;2022:982-991. eCollection 2022.
6
SEPRES: Intensive Care Unit Clinical Data Integration System to Predict Sepsis.SEPRES:用于预测脓毒症的重症监护病房临床数据集成系统。
Appl Clin Inform. 2023 Jan;14(1):65-75. doi: 10.1055/a-1990-3037. Epub 2022 Nov 30.
7
Automated digital technologies for supporting sepsis prediction in children: a scoping review protocol.用于支持儿童脓毒症预测的自动化数字技术:范围综述方案。
BMJ Open. 2022 Nov 22;12(11):e065429. doi: 10.1136/bmjopen-2022-065429.
8
Application of a Machine Learning-Based Decision Support Tool to Improve an Injury Surveillance System Workflow.基于机器学习的决策支持工具在改进伤害监测系统工作流程中的应用。
Appl Clin Inform. 2022 May;13(3):700-710. doi: 10.1055/a-1863-7176. Epub 2022 May 29.
9
Predicting Major Adverse Cardiovascular Events in Acute Coronary Syndrome: A Scoping Review of Machine Learning Approaches.预测急性冠状动脉综合征中的主要不良心血管事件:机器学习方法的范围综述。
Appl Clin Inform. 2022 May;13(3):720-740. doi: 10.1055/a-1863-1589. Epub 2022 May 26.
10
A Graphical Toolkit for Longitudinal Dataset Maintenance and Predictive Model Training in Health Care.用于医疗保健中纵向数据集维护和预测模型训练的图形工具包。
Appl Clin Inform. 2022 Jan;13(1):56-66. doi: 10.1055/s-0041-1740923. Epub 2022 Feb 16.

本文引用的文献

1
Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy.机器学习在脓毒症预测中的应用:诊断试验准确性的系统评价和荟萃分析。
Intensive Care Med. 2020 Mar;46(3):383-400. doi: 10.1007/s00134-019-05872-y. Epub 2020 Jan 21.
2
Clinical applications of artificial intelligence in sepsis: A narrative review.人工智能在脓毒症中的临床应用:叙事性综述。
Comput Biol Med. 2019 Dec;115:103488. doi: 10.1016/j.compbiomed.2019.103488. Epub 2019 Oct 7.
3
Machine learning for clinical decision support in infectious diseases: a narrative review of current applications.机器学习在传染病临床决策支持中的应用:当前应用的叙述性综述。
Clin Microbiol Infect. 2020 May;26(5):584-595. doi: 10.1016/j.cmi.2019.09.009. Epub 2019 Sep 17.
4
Generalized additive models: Building evidence of air pollution, climate change and human health.广义加性模型:构建空气污染、气候变化与人类健康关联的证据。
Environ Int. 2019 Nov;132:104987. doi: 10.1016/j.envint.2019.104987. Epub 2019 Aug 6.
5
Errors in search strategies used in systematic reviews and their effects on information retrieval.系统评价中检索策略的错误及其对信息检索的影响。
J Med Libr Assoc. 2019 Apr;107(2):210-221. doi: 10.5195/jmla.2019.567. Epub 2019 Apr 1.
6
Removing Confounding Factors Associated Weights in Deep Neural Networks Improves the Prediction Accuracy for Healthcare Applications.消除深度神经网络中与权重相关的混杂因素可提高医疗保健应用的预测准确性。
Pac Symp Biocomput. 2019;24:54-65.
7
Sample size implications of mortality definitions in sepsis: a retrospective cohort study.脓毒症中死亡率定义对样本量的影响:一项回顾性队列研究。
Trials. 2018 Mar 27;19(1):198. doi: 10.1186/s13063-018-2570-2.
8
Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units.通过在急诊科、重症监护病房和医院普通病房基于机器学习的脓毒症预测来降低患者死亡率、住院时间和再入院率。
BMJ Open Qual. 2017 Oct 25;6(2):e000158. doi: 10.1136/bmjoq-2017-000158. eCollection 2017.
9
Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial.基于机器学习的严重脓毒症预测算法对患者生存率和住院时间的影响:一项随机临床试验。
BMJ Open Respir Res. 2017 Nov 9;4(1):e000234. doi: 10.1136/bmjresp-2017-000234. eCollection 2017.
10
Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.仅使用生命体征数据在急诊科、普通病房和重症监护病房对脓毒症预测算法进行多中心验证。
BMJ Open. 2018 Jan 26;8(1):e017833. doi: 10.1136/bmjopen-2017-017833.