Machine learning for the prediction of sepsis: a systematic review and meta

心肺复苏术的CPR步骤：A-B-C，即胸外按压（Aim for the center of the chest）、开放气道（Bend the victim’s neck）和人工呼吸（Check breathing） #生活技巧# #健康生活小窍门# #运动技巧# #心肺复苏术教学#

Meta-Analysis

Actions

. 2020 Mar;46(3):383-400.

doi: 10.1007/s00134-019-05872-y. Epub 2020 Jan 21.

Thomas L T Klausch  3 , Charlotte L Zwager  4 , Linda J Schoonmade  5 , Tingjie Guo  4 , Luca F Roggeveen  4   6 , Eleonora L Swart  7 , Armand R J Girbes  4 , Patrick Thoral  4 , Ari Ercole  8   9 , Mark Hoogendoorn  6 , Paul W G Elbers  4   9

Affiliations

PMID: 31965266 PMCID: PMC7067741 DOI: 10.1007/s00134-019-05872-y

Meta-Analysis

Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy

Lucas M Fleuren et al. Intensive Care Med. 2020 Mar.

Abstract

Purpose: Early clinical recognition of sepsis can be challenging. With the advancement of machine learning, promising real-time models to predict sepsis have emerged. We assessed their performance by carrying out a systematic review and meta-analysis.

Methods: A systematic search was performed in PubMed, Embase.com and Scopus. Studies targeting sepsis, severe sepsis or septic shock in any hospital setting were eligible for inclusion. The index test was any supervised machine learning model for real-time prediction of these conditions. Quality of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology, with a tailored Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklist to evaluate risk of bias. Models with a reported area under the curve of the receiver operating characteristic (AUROC) metric were meta-analyzed to identify strongest contributors to model performance.

Results: After screening, a total of 28 papers were eligible for synthesis, from which 130 models were extracted. The majority of papers were developed in the intensive care unit (ICU, n = 15; 54%), followed by hospital wards (n = 7; 25%), the emergency department (ED, n = 4; 14%) and all of these settings (n = 2; 7%). For the prediction of sepsis, diagnostic test accuracy assessed by the AUROC ranged from 0.68-0.99 in the ICU, to 0.96-0.98 in-hospital and 0.87 to 0.97 in the ED. Varying sepsis definitions limit pooling of the performance across studies. Only three papers clinically implemented models with mixed results. In the multivariate analysis, temperature, lab values, and model type contributed most to model performance.

Conclusion: This systematic review and meta-analysis show that on retrospective data, individual machine learning models can accurately predict sepsis onset ahead of time. Although they present alternatives to traditional scoring systems, between-study heterogeneity limits the assessment of pooled results. Systematic reporting and clinical implementation studies are needed to bridge the gap between bytes and bedside.

Keywords: Machine learning; Meta-analysis; Prediction; Sepsis; Septic shock; Systematic review.

PubMed Disclaimer

Conflict of interest statement

The author(s) declare that they have no conflict of interest.

Figures

Fig. 1

Left versus right alignment. Left alignment (top) versus right alignment (bottom). Cases are aligned at the alignment point, in the feature window data are collected, the prediction window is the time of the prediction ahead of sepsis onset. Red sepsis cases, green non-septic cases

Fig. 2

Flow diagram. Papers identified in databases, title/abstract screened, read full text, and included in the synthesis. Reasons for exclusion are listed

Fig. 3

Prospective versus retrospective models. Percentages specified per paper and for all models

Fig. 4

Overview of retrospective diagnostic test accuracy studies. Papers are binned per hospital setting, data are sorted in ascending order of AUROC values. AUROC ranges are displayed per paper. AUROC area under the curve of the receiver operating characteristic, SVM support vector machines, GLM generalized linear model, NB Naive Bayes, EM ensemble methods, NNM neural network model, DT decision trees, PHM proportional hazards model, LSTM long short term memory, Hrs bef. onset hours before onset * DT, EM, GLM, LSTM, NB, NNM, SVM

Fig. 5

Features used in the papers. Features are grouped by type. ESR erythrocyte sedimentation rate, HR heart rate, MAP mean arterial pressure

Fig. 6

Relative effect of hours before sepsis onset on AUROC for different models. Expected change in AUROC for three models at different prediction windows (hours before sepsis onset)

Similar articles

Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.

Mao Q, Jay M, Hoffman JL, Calvert J, Barton C, Shimabukuro D, Shieh L, Chettipally U, Fletcher G, Kerem Y, Zhou Y, Das R.Mao Q, et al.BMJ Open. 2018 Jan 26;8(1):e017833. doi: 10.1136/bmjopen-2017-017833.BMJ Open. 2018.PMID: 29374661Free PMC article.

Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review.

Moor M, Rieck B, Horn M, Jutzeler CR, Borgwardt K.Moor M, et al.Front Med (Lausanne). 2021 May 28;8:607952. doi: 10.3389/fmed.2021.607952. eCollection 2021.Front Med (Lausanne). 2021.PMID: 34124082Free PMC article.

Diagnostic performance of machine-learning algorithms for sepsis prediction: An updated meta-analysis.

Zhang H, Wang C, Yang N.Zhang H, et al.Technol Health Care. 2024;32(6):4291-4307. doi: 10.3233/THC-240087.Technol Health Care. 2024.PMID: 38968031Free PMC article.

Prediction of sepsis patients using machine learning approach: A meta-analysis.

Islam MM, Nasrin T, Walther BA, Wu CC, Yang HC, Li YC.Islam MM, et al.Comput Methods Programs Biomed. 2019 Mar;170:1-9. doi: 10.1016/j.cmpb.2018.12.027. Epub 2018 Dec 26.Comput Methods Programs Biomed. 2019.PMID: 30712598

Clinical Decision-Support Systems for Detection of Systemic Inflammatory Response Syndrome, Sepsis, and Septic Shock in Critically Ill Patients: A Systematic Review.

Wulff A, Montag S, Marschollek M, Jack T.Wulff A, et al.Methods Inf Med. 2019 Dec;58(S 02):e43-e57. doi: 10.1055/s-0039-1695717. Epub 2019 Sep 9.Methods Inf Med. 2019.PMID: 31499571

Cited by

Assessment of the timeliness and robustness for predicting adult sepsis.

Guan Y, Wang X, Chen X, Yi D, Chen L, Jiang X.Guan Y, et al.iScience. 2021 Jan 26;24(2):102106. doi: 10.1016/j.isci.2021.102106. eCollection 2021 Feb 19.iScience. 2021.PMID: 33659874Free PMC article.

Predictive value of machine learning on fracture risk in osteoporosis: a systematic review and meta-analysis.

Wu Y, Chao J, Bao M, Zhang N.Wu Y, et al.BMJ Open. 2023 Dec 9;13(12):e071430. doi: 10.1136/bmjopen-2022-071430.BMJ Open. 2023.PMID: 38070927Free PMC article.

Development and Validation of a Machine Learning Model to Estimate Bacterial Sepsis Among Immunocompromised Recipients of Stem Cell Transplant.

Lind ML, Mooney SJ, Carone M, Althouse BM, Liu C, Evans LE, Patel K, Vo PT, Pergam SA, Phipps AI.Lind ML, et al.JAMA Netw Open. 2021 Apr 1;4(4):e214514. doi: 10.1001/jamanetworkopen.2021.4514.JAMA Netw Open. 2021.PMID: 33871619Free PMC article.

Early identification and diagnosis, pathophysiology, and treatment of sepsis-related acute lung injury: a narrative review.

Zhang J, Yan W, Dong Y, Luo X, Miao H, Maimaijuma T, Xu X, Jiang H, Huang Z, Qi L, Liang G.Zhang J, et al.J Thorac Dis. 2024 Aug 31;16(8):5457-5476. doi: 10.21037/jtd-24-1191. Epub 2024 Aug 28.J Thorac Dis. 2024.PMID: 39268131Free PMC article.Review.

Machine Learning-Based Risk Prediction of Discharge Status for Sepsis.

Cai K, Lou Y, Wang Z, Yang X, Zhao X.Cai K, et al.Entropy (Basel). 2024 Jul 25;26(8):625. doi: 10.3390/e26080625.Entropy (Basel). 2024.PMID: 39202095Free PMC article.

References

Fleischmann C, Scherag A, Adhikari NKJ, et al. Assessment of global incidence and mortality of hospital-treated sepsis. current estimates and limitations. Am J Respir Crit Care Med. 2016;193:259–272. doi: 10.1164/rccm.201504-0781OC. - DOI - PubMed Rhee C, Dantes R, Epstein L, et al. Incidence and trends of sepsis in US hospitals using clinical vs claims data, 2009–2014. JAMA. 2017;318:1241. doi: 10.1001/jama.2017.13836. - DOI - PMC - PubMed Álvaro-Meca A, Jiménez-Sousa MA, Micheloud D, et al. Epidemiological trends of sepsis in the twenty-first century (2000–2013): an analysis of incidence, mortality, and associated costs in Spain. Popul Health Metr. 2018;16:4. doi: 10.1186/s12963-018-0160-x. - DOI - PMC - PubMed Seymour CW, Gesten F, Prescott HC, et al. Time to treatment and mortality during mandated emergency care for sepsis. N Engl J Med. 2017;376:2235–2244. doi: 10.1056/NEJMoa1703058. - DOI - PMC - PubMed Liu VX, Fielding-Singh V, Greene JD, et al. The timing of early antibiotics and hospital mortality in sepsis. Am J Respir Crit Care Med. 2017;196:856–863. doi: 10.1164/rccm.201609-1848OC. - DOI - PMC - PubMed

Publication types

Actions

Actions

MeSH terms

Actions

Actions

Actions

Actions

Actions

Actions

LinkOut - more resources

Full Text Sources

Europe PubMed Central PubMed Central Springer

Other Literature Sources

The Lens - Patent Citations Database

Medical

ClinicalTrials.gov MedlinePlus Health Information

Miscellaneous

NCI CPTAC Assay Portal

网址：Machine learning for the prediction of sepsis: a systematic review and meta https://klqsh.com/news/view/249247

相关内容

Prevalence of frailty in 62 countries across the world: a systematic review and meta
Effects of Collagen Supplements on Skin Aging: A Systematic Review and Meta
Impact of Aligners and Fixed Appliances on Oral Health during Orthodontic Treatment: A Systematic Review and Meta
Orthodontic Compliance Assessment: A Systematic Review
Updated Guidelines for the Orthodontic Management of Traumatized and Endodontically Treated Teeth: A Review Study
Optimal Treatment Timing in Orthodontics: A Scoping Review
The potential for artificial intelligence in healthcare
Radiomics: the bridge between medical imaging and personalized medicine
Screening for depression in primary care with Patient Health Questionnaire
Cancer Statistics, 2021

随便看看