Early identification of sepsis has been shown to significantly improve patient prognosis.
OBJECTIVE:
Therefore, the aim of this meta-analysis is to systematically evaluate the diagnostic efficacy of machine-learning algorithms for sepsis prediction.
METHODS:
Systematic searches were conducted in PubMed, Embase and Cochrane databases, covering literature up to December 2023. The keywords included machine learning, sepsis and prediction. After screening, data were extracted and analysed from studies meeting the inclusion criteria. Key evaluation metrics included sensitivity, specificity and the area under the curve (AUC) for diagnostic accuracy.
RESULTS:
The meta-analysis included a total of 21 studies with a data sample size of 4,158,941. Overall, the pooled sensitivity was 0.82 (95% confidence interval [CI] 0.70–0.90; 0.001; 99.7%), the specificity was 0.91 (95% CI 0.86–0.94; 0.001; 99.9%), and the AUC was 0.94 (95% CI 0.91–0.96). The subgroup analysis revealed that in the emergency department setting (6 studies), the pooled sensitivity was 0.79 (95% CI 0.68–0.87; 0.001; 99.6%), the specificity was 0.94 (95% CI 0.90–0.97; 0.001; 99.9%), and the AUC was 0.94 (95% CI 0.92–0.96). In the Intensive Care Unit setting (11 studies), the sensitivity was 0.91 (95% CI 0.75–0.97; 0.001; 98.3%), the specificity was 0.85 (95% CI 0.75–0.92; 0.001; 99.9%), and the AUC was 0.93 (95% CI 0.91–0.95). Due to the limited number of studies in the in-hospital and mixed settings ( 3), no pooled analysis was performed.
CONCLUSION:
Machine-learning algorithms have demonstrated excellent diagnostic accuracy in predicting the occurrence of sepsis, showing potential for clinical application.
RuddKEJohnsonSCAgesaKM, et al. Global, regional, and national sepsis incidence and mortality, 1990-2017: analysis for the Global Burden of Disease Study. Lancet.2020; 395(10219): 200-211. doi: 10.1016/S0140-6736(19)32989-7.
2.
Fleischmann-StruzekCMellhammarLRoseN, et al. Incidence and mortality of hospital- and ICU-treated sepsis: results from an updated and expanded systematic review and meta-analysis. Intensive Care Med.2020; 46(8): 1552-1562. doi: 10.1007/s00134-020-06151-x.
3.
BosmannMWardPA. The inflammatory response in sepsis. Trends Immunol.2013; 34(3): 129-136. doi: 10.1016/j.it.2012.09.004.
4.
JacobiJ. The pathophysiology of sepsis – 2021 update: Part 2, organ dysfunction and assessment. Am J Health Syst Pharm.2022; 79(6): 424-436. doi: 10.1093/ajhp/zxab393.
5.
RhodesAEvansLEAlhazzaniW, et al. Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock: 2016. Intensive Care Med.2017; 43(3): 304-377. doi: 10.1007/s00134-017-4683-6.
6.
YadavPYadavSK. Progress in Diagnosis and Treatment of Neonatal Sepsis: A Review Article. JNMA J Nepal Med Assoc.2022; 60(247): 318-324. Published 2022 Mar 11. doi: 10.31729/jnma.7324.
7.
CockrellCAnG. Sepsis reconsidered: Identifying novel metrics for behavioral landscape characterization with a high-performance computing implementation of an agent-based model. J Theor Biol.2017; 430: 157-168. doi: 10.1016/j.jtbi.2017.07.016.
8.
RatzingerFHaslacherHPerkmannT, et al. Machine learning for fast identification of bacteraemia in SIRS patients treated on standard care wards: a cohort study. Sci Rep.2018; 8(1): 12233. Published 2018 Aug 15. doi: 10.1038/s41598-018-30236-9.
9.
StemmerAShadmiRBregman-AmitaiO, et al. Using machine learning algorithms to review computed tomography scans and assess risk for cardiovascular disease: Retrospective analysis from the National Lung Screening Trial (NLST). PLoS One.2020; 15(8): e0236021. Published 2020 Aug 3. doi: 10.1371/journal.pone.0236021.
10.
McInnesMDFMoherDThombsBD, et al. Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies: The PRISMA-DTA Statement. JAMA.2018; 319(4): 388-396. doi: 10.1001/jama.2017.19163.
11.
BrownSMJonesJKuttlerKGKeddingtonRKAllenTLHaugP. Prospective evaluation of an automated method to identify patients with severe sepsis or septic shock in the emergency department. BMC Emerg Med.2016; 16(1): 31. Published 2016 Aug 22. doi: 10.1186/s12873-016-0095-0.
12.
DelahantyRJAlvarezJFlynnLMSherwinRLJonesSS. Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis. Ann Emerg Med.2019; 73(4): 334-344. doi: 10.1016/j.annemergmed.2018.11.036.
13.
HaugPFerraroJ. Using a semi-automated modeling environment to construct a Bayesian, sepsis diagnostic system. BCB ’16. 2016. doi: 10.1145/2975167.2985841.
14.
KijpaisalratanaNSanglertsinlapachaiDTecharatsamiSMusikatavornKSaorayaJ. Machine learning algorithms for early sepsis detection in the emergency department: A retrospective study. Int J Med Inform.2022; 160: 104689. doi: 10.1016/j.ijmedinf.2022.104689.
15.
KimJChangHKimDJangDHParkIKimK. Machine learning for prediction of septic shock at initial triage in emergency department. J Crit Care.2020; 55: 163-170. doi: 10.1016/j.jcrc.2019.09.024.
16.
MercurioLPouSDuffySEickhoffC. Risk Factors for Pediatric Sepsis in the Emergency Department: A Machine Learning Pilot Study. Pediatr Emerg Care.2023; 39(2): e48-e56. doi: 10.1097/PEC.0000000000002893.
17.
KhojandiATansakulVLiXKoszalinskiRSPaivaW. Prediction of Sepsis and In-Hospital Mortality Using Electronic Health Records. Methods Inf Med.2018; 57(4): 185-193. doi: 10.3414/ME18-01-0014.
18.
ThielSWRosiniJMShannonWDohertyJAMicekSTKollefMH. Early prediction of septic shock in hospitalized patients. J Hosp Med.2010; 5(1): 19-25. doi: 10.1002/jhm.530.
19.
ChenCChenBYangJ, et al. Development and validation of a practical machine learning model to predict sepsis after liver transplantation. Ann Med.2023; 55(1): 624-633. doi: 10.1080/07853890.2023.2179104.
20.
EskandariMAMoridaniMKMohammadiS. Detection of sepsis using biomarkers based on machine learning. Bratisl Lek Listy.2023; 124(3): 239-250. doi: 10.4149/BLL_2023_037.
21.
HenryKEHagerDNPronovostPJSariaS. A targeted real-time early warning score (TREWScore) for septic shock. Sci Transl Med.2015; 7(299): 299ra122. doi: 10.1126/scitranslmed.aab3719.
22.
HonoréAForsbergDAdolphsonKChatterjeeSJostKHerleniusE. Vital sign-based detection of sepsis in neonates using machine learning. Acta Paediatr.2023; 112(4): 686-696. doi: 10.1111/apa.16660.
23.
KamHJKimHY. Learning representations for the early detection of sepsis with deep neural networks. Comput Biol Med.2017; 89: 248-255. doi: 10.1016/j.compbiomed.2017.08.015.
24.
KimTTaeYYeoHJ, et al. Development and Validation of Deep-Learning-Based Sepsis and Septic Shock Early Prediction System (DeepSEPS) Using Real-World ICU Data. J Clin Med.2023; 12(22): 7156. Published 2023 Nov 17. doi: 10.3390/jcm12227156.
25.
LiuSFuBWangWLiuMSunX. Dynamic Sepsis Prediction for Intensive Care Unit Patients Using XGBoost-Based Model With Novel Time-Dependent Features. IEEE J Biomed Health Inform.2022; 26(8): 4258-4269. doi: 10.1109/JBHI.2022.3171673.
26.
LiuFYaoJLiuCShouS. Construction and validation of machine learning models for sepsis prediction in patients with acute pancreatitis. BMC Surg.2023; 23(1): 267. Published 2023 Sep 1. doi: 10.1186/s12893-023-02151-y.
27.
ShashikumarSPLiQCliffordGDNematiS. Multiscale network representation of physiological time series for early prediction of sepsis. Physiol Meas.2017; 38(12): 2235-2248. Published 2017 Nov 30. doi: 10.1088/1361-6579/aa9772.
28.
ShimabukuroDWBartonCWFeldmanMDMatarasoSJDasR. Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial. BMJ Open Respir Res.2017; 4(1): e000234. Published 2017 Nov 9. doi: 10.1136/bmjresp-2017-000234.
29.
WangDLiJSunY, et al. A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients. Front Public Health.2021; 9: 754348. Published 2021 Oct 15. doi: 10.3389/fpubh.2021.754348.
30.
BartonCChettipallyUZhouY, et al. Evaluation of a machine learning algorithm for up to 48-hour advance prediction of sepsis using six vital signs. Comput Biol Med.2019; 109: 79-84. doi: 10.1016/j.compbiomed.2019.04.027.
31.
MaoQJayMHoffmanJL, et al. Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMJ Open.2018; 8(1): e017833. Published 2018 Jan 26. doi: 10.1136/bmjopen-2017-017833.
32.
OliveiraFLuísMSargentoS. Machine Learning for the Dynamic Positioning of UAVs for Extended Connectivity. Sensors (Basel).2021; 21(13): 4618. Published 2021 Jul 5. doi: 10.3390/s21134618.
33.
SullivanBA.. NagrajVP. BerryKL. et al. ‘Clinical and Vital Sign Changes Associated with Late-onset Sepsis in Very Low Birth Weight Infants at 3 NICUs’ 1. Technology and Health Care. 2021: 553-561. doi: 10.3233/NPM-200578.
34.
WesselsFBußoffIAdamS. et al. ‘Comorbidity Scores and Machine Learning Methods Can Improve Risk Assessment in Radical Cystectomy for Bladder Cancer’. 1.Technology and Health Care. 2022: 155-163. doi: 10.1155/2022/5032435.
35.
HazratifardMGebaliFMamunM. Using Machine Learning for Dynamic Authentication in Telehealth: A Tutorial. Sensors (Basel).2022; 22(19): 7655. Published 2022 Oct 9. doi: 10.3390/s22197655.
36.
BurrellARMcLawsMLFullickMSullivanRBSindhusakeD. SEPSIS KILLS: early intervention saves lives. Med J Aust.2016; 204(2): 73. doi: 10.5694/mja15.00657.
37.
Abd RahmanNHIbrahimAKHasikinKAbd RazakNA. Critical Device Reliability Assessment in Healthcare Services. J Healthc Eng.2023; 2023: 3136511. doi: 10.1155/2023/3136511.
38.
BegicEGurbeta PokvicLBegicZ, et al. From Heart Murmur to Echocardiography - Congenital Heart Defects Diagnostics Using Machine-Learning Algorithms. Psychiatr Danub Dec2021; 33(Suppl 13): 236-1246.
39.
BadnjevicACifrekMKorugaD. Integrated software suite for diagnosis of respiratory diseases. 2013; 564-568.
40.
MustaficLDGurbetaLBadnjevic-CengA. Diagnosis of Severe Aortic Stenosis Using Implemented Expert System. 2020.
41.
MooneySJPejaverV. Big Data in Public Health: Terminology, Machine Learning, and Privacy. Annu Rev Public Health.2018; 39: 95-10112. doi: 10.1146/annurev-publhealth-040617-014208.
42.
MoorMRieckBHornMJutzelerCRBorgwardtK. Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review. Front Med (Lausanne).2021; 8: 607952. Published 2021 May 28. doi: 10.3389/fmed.2021.607952.
43.
IslamKRPrithulaJKumarJ, et al. Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review. J Clin Med.2023; 12(17): 5658. Published 2023 Aug 30. doi: 10.3390/jcm12175658.
