Skip to main content

Advertisement

SpringerLink
Log in

Machine-learning-derived sepsis bundle of care

  • Original
  • Published:
Intensive Care Medicine Aims and scope Submit manuscript

A Correspondence to this article was published on 02 January 2023

Abstract

Purpose

Compliance to the Surviving Sepsis Campaign (SSC) guidelines is limited. This is known to be associated with increased mortality. The aim of this retrospective cohort study was to identify among the SCC guidelines the optimal bundle of recommendations that minimize 28-day mortality.

Methods

We used a training cohort to identify, using a least absolute shrinkage and selection operator penalized machine learning model, this bundle. Patients with sepsis/septic shock admitted to the intensive care unit (ICU) were extracted from two US databases, the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database (training and internal validation cohorts) and the eICU Collaborative Research Database (eICU-CRD) (external validation cohort). In the validation cohorts, we defined a bundle group that includes patients who were treated with at least all the recommendations selected in our bundle and a no-bundle group that includes patients in whom at least one recommendation from our bundle was omitted.

Results

All-cause 28-day mortality was the primary outcome measure. A total of 42,735 patients were included. Six recommendations (antimicrobials, balanced crystalloid, insulin therapy, corticosteroids, vasopressin, and bicarbonate therapy) were identified from the training cohort to be included in our bundle. In the propensity score-(PS)-matched internal validation cohort, the bundle group was associated with a lower mortality (OR 0.41 [0.33–0.53]; p < 0.001) compared to the no-bundle group. This was confirmed in the PS-matched external validation cohort (OR 0.75 [0.60–0.94]; p 0.02).

Conclusion

Our bundle of six recommendations is associated with a dramatic reduction in mortality in sepsis and septic shock. This bundle needs to be evaluated prospectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Data availability

This study was performed with the data from the Medical Information Mart for Intensive Care (MIMIC)-IV version 1.0 and the eICU Collaborative Research Database (eICU-CRD) version 1.2. Even though datasets are de-identified, restrictions have been imposed on data sharing since they contain sensitive information. Conventions are signed for researchers before any access to the data. For data access, interested researchers must fulfill all of the following requirements: be a credentialed user of https://physionet.org/, finish required training and sign the data use agreement for the project.

References

  1. Singer M, Deutschman CS, Seymour CW, Shankar-Hari M, Annane D, Bauer M et al (2016) The third international consensus definitions for sepsis and septic shock (Sepsis-3). JAMA 315(8):801–810

    Article  CAS  Google Scholar 

  2. Fleischmann-Struzek C, Mellhammar L, Rose N, Cassini A, Rudd KE, Schlattmann P et al (2020) Incidence and mortality of hospital- and ICU-treated sepsis: results from an updated and expanded systematic review and meta-analysis. Intensive Care Med 46(8):1552–1562

    Article  CAS  Google Scholar 

  3. Angus DC, van der Poll T (2013) Severe sepsis and septic shock. N Engl J Med 369(9):840–851

    Article  CAS  Google Scholar 

  4. Gaieski DF, Edwards JM, Kallan MJ, Carr BG (2013) Benchmarking the incidence and mortality of severe sepsis in the United States. Crit Care Med 41(5):1167–1174

    Article  Google Scholar 

  5. Evans L, Rhodes A, Alhazzani W, Antonelli M, Coopersmith CM, French C et al (2021) Executive summary: surviving sepsis campaign: International Guidelines for the Management of Sepsis and Septic Shock 2021. Crit Care Med 49(11):1974–1982

    Article  Google Scholar 

  6. Leone M, Ragonnet B, Alonso S, Allaouchiche B, Constantin JM, Jaber S et al (2012) Variable compliance with clinical practice guidelines identified in a 1-day audit at 66 French adult intensive care units. Crit Care Med 40(12):3189–3195

    Article  Google Scholar 

  7. Bitton E, Zimmerman S, Azevedo LCP, Benhamou D, Cecconi M, De Waele JJ et al (2022) An international survey of adherence to Surviving Sepsis Campaign Guidelines 2016 regarding fluid resuscitation and vasopressors in the initial management of septic shock. J Crit Care 68:144–154

    Article  CAS  Google Scholar 

  8. Kahn JM, Davis BS, Yabes JG, Chang CCH, Chong DH, Hershey TB et al (2019) Association between state-mandated protocolized sepsis care and in-hospital mortality among adults with sepsis. JAMA 322(3):240–250

    Article  Google Scholar 

  9. You JS, Park YS, Chung SP, Lee HS, Jeon S, Kim WY et al (2022) Relationship between time of emergency department admission and adherence to the Surviving Sepsis Campaign bundle in patients with septic shock. Crit Care 26(1):43

    Article  Google Scholar 

  10. Damiani E, Donati A, Serafini G, Rinaldi L, Adrario E, Pelaia P et al (2015) Effect of performance improvement programs on compliance with sepsis bundles and mortality: a systematic review and meta-analysis of observational studies. PLoS ONE 10(5):e0125827

    Article  Google Scholar 

  11. Semler MW, Wanderer JP, Ehrenfeld JM, Stollings JL, Self WH, Siew ED et al (2017) Balanced crystalloids versus saline in the intensive care unit. The SALT randomized trial. Am J Respir Crit Care Med 195(10):1362–1372

    Article  Google Scholar 

  12. Ou X, Hua Y, Liu J, Gong C, Zhao W (2017) Effect of high-flow nasal cannula oxygen therapy in adults with acute hypoxemic respiratory failure: a meta-analysis of randomized controlled trials. CMAJ 189(7):E260–E267

    Article  Google Scholar 

  13. National Heart, Lung, and Blood Institute PETAL Clinical Trials Network, Moss M, Huang DT, Brower RG, Ferguson ND, Ginde AA et al (2019) Early neuromuscular blockade in the acute respiratory distress syndrome. N Engl J Med 380(21):1997–2008

    Article  Google Scholar 

  14. Jaber S, Paugam C, Futier E, Lefrant JY, Lasocki S, Lescot T et al (2018) Sodium bicarbonate therapy for patients with severe metabolic acidaemia in the intensive care unit (BICAR-ICU): a multicentre, open-label, randomised controlled, phase 3 trial. Lancet 392(10141):31–40

    Article  CAS  Google Scholar 

  15. Marker S, Krag M, Perner A, Wetterslev J, Lange T, Wise MP et al (2019) Pantoprazole in ICU patients at risk for gastrointestinal bleeding-1-year mortality in the SUP-ICU trial. Acta Anaesthesiol Scand 63(9):1184–1190

    Article  CAS  Google Scholar 

  16. von Elm E, Altman DG, Egger M, Pocock SJ, Gøtzsche PC, Vandenbroucke JP et al (2014) The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: guidelines for reporting observational studies. Int J Surg 12(12):1495–1499

    Article  Google Scholar 

  17. Chen MY, Langan S, Benchimol EI (2016) Routinely collected electronic health data and STI research: RECORD extension to the STROBE guidelines. Sex Transm Infect 92(1):2–3

    Article  Google Scholar 

  18. Johnson A, Bulgarelli L, Pollard T, Horng S, Celi LA. MIMIC-IV (version 0.4). PhysioNet 2020

  19. Pollard TJ, Johnson AEW, Raffa JD, Celi LA, Mark RG, Badawi O (2018) The eICU Collaborative Research Database, a freely available multi-center database for critical care research [Internet]. Sci Data. https://doi.org/10.1038/sdata.2018.178

    Article  Google Scholar 

  20. Vincent JL, Moreno R, Takala J, Willatts S, De Mendonça A, Bruining H et al (1996) The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine. Intensive Care Med 22(7):707–710

    Article  CAS  Google Scholar 

  21. Le Gall JR, Lemeshow S, Saulnier F (1993) A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. JAMA 270(24):2957–2963

    Article  Google Scholar 

  22. Tibshirani R (1996) Regression shrinkage and selection via the Lasso. J R Stat Soc Series B Stat Methodol 58(1):267–288

    Google Scholar 

  23. Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1–22

    Article  Google Scholar 

  24. Seymour CW, Kennedy JN, Wang S, Chang CCH, Elliott CF, Xu Z et al (2019) Derivation, validation, and potential treatment implications of novel clinical phenotypes for sepsis. JAMA 321(20):2003–2017

    Article  CAS  Google Scholar 

  25. Haute Autorité de Santé. Niveau de preuve et gradation des recommandations de bonne pratique. 2013. https://www.has-sante.fr/jcms/c_1600564/fr/niveau-de-preuve-et-gradation-des-recommandations-de-bonne-pratique-etat-des-lieux

  26. Rhee C, Yu T, Wang R, Kadri SS, Fram D, Chen HC et al (2021) Association Between implementation of the severe sepsis and septic shock early management bundle performance measure and outcomes in patients with suspected sepsis in US hospitals. JAMA Netw Open 4(12):e2138596

    Article  Google Scholar 

  27. Venkatesh B, Finfer S, Cohen J, Rajbhandari D, Arabi Y, Bellomo R et al (2018) Adjunctive glucocorticoid therapy in patients with septic shock. N Engl J Med 378(9):797–808

    Article  CAS  Google Scholar 

  28. Rygård SL, Butler E, Granholm A, Møller MH, Cohen J, Finfer S et al (2018) Low-dose corticosteroids for adult patients with septic shock: a systematic review with meta-analysis and trial sequential analysis. Intensive Care Med 44(7):1003–1016

    Article  Google Scholar 

  29. Annane D, Renault A, Brun-Buisson C, Megarbane B, Quenot JP, Siami S et al (2018) Hydrocortisone plus fludrocortisone for adults with septic shock. N Engl J Med 378(9):809–818

    Article  CAS  Google Scholar 

  30. Preiser JC, Devos P, Ruiz-Santana S, Mélot C, Annane D, Groeneveld J et al (2009) A prospective randomised multi-centre controlled trial on tight glucose control by intensive insulin therapy in adult intensive care units: the Glucontrol study. Intensive Care Med 35(10):1738–1748

    Article  CAS  Google Scholar 

  31. Griesdale DEG, de Souza RJ, van Dam RM, Heyland DK, Cook DJ, Malhotra A et al (2009) Intensive insulin therapy and mortality among critically ill patients: a meta-analysis including NICE-SUGAR study data. CMAJ 180(8):821–827

    Article  Google Scholar 

  32. NICE-SUGAR Study Investigators, Finfer S, Chittock DR, Su SYS, Blair D, Foster D et al (2009) Intensive versus conventional glucose control in critically ill patients. N Engl J Med 360(13):1283–1297

    Article  Google Scholar 

  33. Gordon AC, Mason AJ, Thirunavukkarasu N, Perkins GD, Cecconi M, Cepkova M et al (2016) Effect of early vasopressin vs norepinephrine on kidney failure in patients with septic shock: the VANISH randomized clinical trial. JAMA 316(5):509–518

    Article  CAS  Google Scholar 

  34. Russell JA, Walley KR, Singer J, Gordon AC, Hébert PC, Cooper DJ et al (2008) Vasopressin versus norepinephrine infusion in patients with septic shock. N Engl J Med 358(9):877–887

    Article  CAS  Google Scholar 

  35. Seymour CW, Gesten F, Prescott HC, Friedrich ME, Iwashyna TJ, Phillips GS et al (2017) Time to treatment and mortality during mandated emergency care for sepsis. N Engl J Med 376(23):2235–2244

    Article  Google Scholar 

  36. Kalil AC, Johnson DW, Lisco SJ, Sun J (2017) Early goal-directed therapy for sepsis: a novel solution for discordant survival outcomes in clinical trials. Crit Care Med 45(4):607–614

    Article  Google Scholar 

  37. Ferrer R, Artigas A, Suarez D, Palencia E, Levy MM, Arenzana A et al (2009) Effectiveness of treatments for severe sepsis: a prospective, multicenter, observational study. Am J Respir Crit Care Med 180(9):861–866

    Article  CAS  Google Scholar 

  38. Mathieu D, Neviere R, Billard V, Fleyfel M, Wattel F (1991) Effects of bicarbonate therapy on hemodynamics and tissue oxygenation in patients with lactic acidosis: a prospective, controlled clinical study. Crit Care Med 19(11):1352–1356

    Article  CAS  Google Scholar 

  39. Brown RM, Wang L, Coston TD, Krishnan NI, Casey JD, Wanderer JP et al (2019) Balanced crystalloids versus saline in sepsis. A secondary analysis of the SMART clinical trial. Am J Respir Crit Care Med 200(12):1487–1495

    Article  CAS  Google Scholar 

  40. Semler MW, Self WH, Wanderer JP, Ehrenfeld JM, Wang L, Byrne DW et al (2018) Balanced crystalloids versus saline in critically ill adults. N Engl J Med 378(9):829–839

    Article  Google Scholar 

  41. Avni T, Lador A, Lev S, Leibovici L, Paul M, Grossman A (2015) Vasopressors for the treatment of septic shock: systematic review and meta-analysis. PLoS ONE 10(8):e0129305

    Article  Google Scholar 

  42. Rochwerg B, Alhazzani W, Sindi A, Heels-Ansdell D, Thabane L, Fox-Robichaud A et al (2014) Fluid resuscitation in sepsis: a systematic review and network meta-analysis. Ann Intern Med 161(5):347–355

    Article  Google Scholar 

  43. Lewis SR, Pritchard MW, Evans DJ, Butler AR, Alderson P, Smith AF et al (2018) Colloids versus crystalloids for fluid resuscitation in critically ill people. Cochrane Database Syst Rev 8:CD000567

    Google Scholar 

  44. Wang H, Xu Q, Zhou L (2015) Large unbalanced credit scoring using Lasso-logistic regression ensemble. PLoS ONE 10(2):e0117844

    Article  Google Scholar 

  45. Fu GH, Yi LZ, Pan J (2019) LASSO-based false-positive selection for class-imbalanced data in metabolomics. J Chemom [Internet]. https://doi.org/10.1002/cem.3177

    Article  Google Scholar 

Download references

Funding

The authors received no specific funding for this work.

Author information

Authors and Affiliations

  1. Inserm UMR 1153, Center of Research in Epidemiology and StatisticS (CRESS), ECSTRRA Team, Université Paris Cité and Université Sorbonne Paris Nord, 75004, Paris, France

    Alexandre Kalimouttou & Romain Pirracchio

  2. Department of Medical Informatics, Assistance Publique Hôpitaux de Paris-Centre (AP-HP), Georges Pompidou European Hospital, Paris, France

    Alexandre Kalimouttou, Ivan Lerner & Anne-Sophie Jannot

  3. Inserm, Centre de Recherche des Cordeliers, Sorbonne Université, Université Paris Cité, 75006, Paris, France

    Ivan Lerner & Anne-Sophie Jannot

  4. HeKA, Inria Paris, 75015, Paris, France

    Ivan Lerner & Anne-Sophie Jannot

  5. Intensive Care Department, Assistance Publique Hôpitaux de Paris-Centre (AP-HP), Cochin Hospital, Université Paris Cité, Paris, France

    Chérifa Cheurfa

  6. Department of Anesthesia and Perioperative Medicine, Zuckerberg San Francisco General Hospital and Trauma Center, University of California San Francisco, 1001 Potrero Avenue, San Francisco, CA, 94910, USA

    Romain Pirracchio

Authors
  1. Alexandre Kalimouttou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ivan Lerner
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chérifa Cheurfa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anne-Sophie Jannot
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Romain Pirracchio
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

AK had full access to all of the data in the study and take responsibility for the integrity of the data and the accuracy of the data analysis. Concept and design: RP. Acquisition, analysis, or interpretation of data: AK, IL, CC, A-SJ, RP. Drafting of the manuscript: AK, IL, RP. Critical revision of the manuscript for important intellectual content: AK, IL, CC, A-SJ, RP. Statistical analysis: AK, IL. Administrative, technical, or material support: Jannot, RP. Supervision: RP, IL.

Corresponding author

Correspondence to Romain Pirracchio.

Ethics declarations

Conflicts of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Consent

Permission to use the data was obtained for both databases (No. 45398938). Because of the de-identified nature of the data, informed consent was waived. Consent was obtained for the original data collection.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 1773 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kalimouttou, A., Lerner, I., Cheurfa, C. et al. Machine-learning-derived sepsis bundle of care. Intensive Care Med 49, 26–36 (2023). https://doi.org/10.1007/s00134-022-06928-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00134-022-06928-2

Keywords

Search

Navigation