Unsupervised machine learning model for analyzing nutritional support in mechanically ventilated patients

Authors

DOI:

https://doi.org/10.21527/2176-7114.2026.51.16971

Keywords:

Nutritional therapy, Mechanical ventilation, Critical care

Abstract

Nutritional support is essential for critically ill patients on mechanical ventilation, helping to prevent malnutrition, optimize clinical outcomes, and reduce mortality. However, there is still no consensus on the ideal timing for achieving caloric and protein goals, highlighting the need for further studies to guide evidence-based practices. This study aimed to model, in an unsupervised manner, nutritional intervention in critically ill patients on mechanical ventilation admitted to an Intensive Care Unit (ICU). A retrospective study was conducted using data from 260 patients treated in the ICU of a tertiary hospital in Maringá, Paraná, Brazil, through multiple correspondence analysis (MCA) and qualitative comparative analysis (QCA). The MCA explained approximately 21.8% of the variation in mortality outcomes, where being male, having no clinical complications or associated comorbidities, using vasopressors, initiating early nutritional therapy within 24 to 48 hours, having a body mass index between 25 and 29.9 kg/m², and achieving caloric and protein goals within five days were more prominently associated with mortality. QCA, in turn, demonstrated that, on average, 23% of deaths could be explained by the combination of dependent variables analyzed in this study, primarily body mass index, timing of enteral therapy initiation, caloric and protein goals, and vasopressor use. These findings suggest that, in the studied population, the combination of adequate nutritional supply and timely management was associated with better clinical outcomes, underscoring the need for care protocols that prioritize early nutritional assessment and intervention in critically ill patients on mechanical ventilation and enteral support.

References

1. Moreira da Silva C, Bonatto S, Luiza da Silva C, da Rocha Gaspar MD, Arcaro G. Relação entre pneumonia associada à ventilação mecânica e a permanência em unidade de terapia intensiva. Nursing (Edição Brasileira). 2021;24(283):6677–88. doi:10.36489/nursing.2021v24i283p6677-6688.

2. Schuetz P, Fehr R, Baechli V, Geiser M, Deiss M, Gomes F, et al. Individualised nutritional support in medical inpatients at nutritional risk: a randomised clinical trial. Lancet. 2019; 393:2312–21. doi:10.1016/S0140-6736(18)32776-4.

3. Tume L, Valla F, Joosten K, Chaparro C, Latten L, Marino L, et al. Nutritional support for children during critical illness: European Society of Pediatric and Neonatal Intensive Care (ESPNIC) metabolism, endocrine and nutrition section position statement and clinical recommendations. Intensive Care Med. 2020; 46:411–25. doi:10.1007/s00134-019-05922-5.

4. Koontalay A, Suksatan W, Sadang J, Prabsangob K. Optimal Nutritional Factors Influencing the Duration of Mechanical Ventilation Among Adult Patients with Critical Illnesses in an Intensive Care Unit. J Multidiscip Healthc. 2021; 14:1385–93. doi:10.2147/JMDH.S319553.

5. Wischmeyer PE, Puthucheary Z, San Millán I, Butz D, Grocott MPW. Muscle mass and physical recovery in ICU: innovations for targeting nutrition and exercise. Curr Opin Crit Care. 2017;23(4):269-78. doi:10.1097/MCC.0000000000000431

6. BRASPEN - Sociedade Brasileira de Nutrição Parenteral e Enteral. Diretriz Brasileira de Terapia Nutricional no paciente grave. Braspen J. 2023;38(Supl 2):2–4.

7. Lê S, Josse J, Husson F. FactoMineR: An R Package for Multivariate Analysis. J Stat Softw [Internet]. 2008;25(1):1–18.

8. Cuschieri S. The STROBE guidelines. Saudi J Anaesth. 2019 Apr;13(Suppl 1): S31-S34.

9. Beh EJ, Lombardo R. Correspondence Analysis: Theory, Practice and New Strategies. Chichester: Wiley; 2014.

10. Greenacre M, Blasius J. Multiple Correspondence Analysis and Related Methods. London: Chapman & Hall/CRC Press; 2006.

11. Dusa A. Analysis of Necessity. In: QCA with R. Cham: Springer; 2019. doi:10.1007/978-3-319-75668-4_5.

12. R Core Team. R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing; 2023.

13. Textor J, Hardt J, Knüppel S. DAGitty: a graphical tool for analyzing causal diagrams. Epidemiology. 2011;22(5):745. doi:10.1097/EDE.0b013e318225c2be.

14. Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10(1):37–48. PMID: 9888278.

15. Mehta Y, Sunavala JD, Zirpe K, Tyagi N, Garg S, Sinha S, et al. Practice Guidelines for Nutrition in Critically Ill Patients: A Relook for Indian Scenario. Indian J Crit Care Med. 2018;22(4):263–73. doi: 10.4103/ijccm.IJCCM_3_18.

16. Singer P, Blaser AR, Berger MM, Calder PC, Casaer M, Hiesmayr M, et al. ESPEN practical and partially revised guideline: Clinical nutrition in the intensive care unit. Clin Nutr. 2023;42(9):1671–89. doi: 10.1016/j.clnu.2023.07.011.

17. Callahan J, Parot-Schinkel E, Asfar P, Ehrmann S, Tirot P, Guitton C. Impact of daily cyclic enteral nutrition versus standard continuous enteral nutrition in critically ill patients: a study protocol for a randomized clinical trial in three intensive care units in France (DC-SCENIC). BMJ Open [Internet]. 2024;14(5): e081978.

18. Reignier J, Plantefeve G, Mira JP, Argaud L, Asfar P, Aissaoui N, et al. Low versus standard calorie and protein feeding in ventilated adults with shock: a randomised, controlled, multicentre, open-label, parallel-group trial (NUTRIREA-3). Lancet Respir Med. 2023 Jul;11(7):602-12. doi:10.1016/S2213-2600(23)00092-9. Epub 2023 Mar 20. PMID:36958363.

19. Lew CCH, Lee ZY, Day AG, Jiang X, Bear D, Jensen GL, et al. The association between malnutrition and high protein treatment on outcomes in critically ill patients: a post hoc analysis of the EFFORT Protein randomized trial. Chest. 2024 Jun;165(6):1380-91. doi: 10.1016/j.chest.2024.02.008. Epub 2024 Feb 12. PMID:38354904.

20. Farina N, Nordbeck S, Montgomery M, Cordwin L, Blair F, Cherry-Bukowiec J, et al. Early enteral nutrition in mechanically ventilated patients with COVID-19 infection. Nutr Clin Pract. 2021 Apr;36(2):440-8. doi:10.1002/ncp.10629. Epub 2021 Mar 2. PMID:33651909; PMCID: PMC8014144.

21. Kaegi-Braun N, Tribolet P, Gomes F, Fehr R, Baechli V, Geiser M, et al. Six-month outcomes after individualized nutritional support during the hospital stay in medical patients at nutritional risk: Secondary analysis of a prospective randomized trial. Clin Nutr. 2020. doi:10.1016/j.clnu.2020.08.019.

22. Landoni G, Monaco F, Ti LK, Baiardo Redaelli M, Bradic N, Comis M, et al. A randomized trial of intravenous amino acids for kidney protection. N Engl J Med. 2024 Aug 22;391(8):687-98. doi:10.1056/NEJMoa2403769. Epub 2024 Jun 12. PMID:38865168.

23. Heyland DK, Patel J, Compher C, Rice TW, Bear DE, Lee ZY, et al. The effect of higher protein dosing in critically ill patients with high nutritional risk (EFFORT Protein): an international, multicentre, pragmatic, registry-based randomised trial. Lancet. 2023 Feb 18;401(10376):568-76. doi:10.1016/S0140-6736(22)02469-2. Epub 2023 Jan 25. Erratum in: Lancet. 2023 Mar 25;401(10381):1000. doi:10.1016/S0140-6736(23)00585-8. PMID:36708732.

24. Pardo E, Lescot T, Preiser J, Massanet P, Pons A, Jaber S, et al. Association between early nutrition support and 28-day mortality in critically ill patients: the FRANS prospective nutrition cohort study. Crit Care. 2023; 27:36. doi:10.1186/s13054-023-04316-2.

25. Huynen P, Casaer MP, Gunst J. Advancements in nutritional support for critically ill patients. Curr Opin Crit Care. 2025 Apr 1;31(2):212-18. doi:10.1097/MCC.0000000000001254. Epub 2025 Jan 29. PMID:39991851.

26. Pasechnik IN. Nutritional support for critically ill patients (Review). Gen Reanimatol. 2020;16(4):40–59. doi:10.15360/1813-9779-2020-4-40-59.

27. Zhu R, Zhang X, Zhang W, Wang S, Liu Y, Li W, et al. Immunonutrition for critically ill patients: a systematic review and meta-analysis. Nutrition. 2022 Feb; 93:111492. doi: 10.1016/j.nut.2021.111492. Epub 2021 Oct 6. PMID:34627823.

28.Lee Y‑F, Lin P‑R, Wu S‑H, Hsu H‑H, Yang S‑Y, Kor C‑T. Impact of the prognostic nutritional index on renal replacement therapy–free survival and mortality in patients on continuous renal replacement therapy. Ren Fail [Internet]. 2024 Dec;46(2):2365394. doi:10.1080/0886022X.2024.2365394.

29. Al-Dorzi HM, Arabi YM. Early enteral nutrition in critically ill patients: from recommendations to clinical practice. J Intensive Care Med. 2023 Jul;38(7):582-592. doi:10.1177/08850666221146047. Epub 2023 Jan 2. PMID:36595253.

30. Cechinel AC, Santos BS, Costa EDC, et al. Fragilidade e delirium em idosos hospitalizados: revisão sistemática com metanálise. Rev Lat Am Enfermagem. 2022;30:e3686. doi:10.1590/1518-8345.6120.3688.

31. Queiroz CA, Bacci MR. Influence of early hemodialysis on the septic acute kidney injury outcome. Rev Esc Enferm USP. 2022;56:e20220109. https://doi. org/10.1590/1980-220X-REEUSP-2022-0109en.

32. Jiang L, Jiang S, Lin Y, Li R, Ma Y, Chen X. Association of obesity with disease severity among patients with COVID-19: a systematic review and meta-analysis. Obes Rev. 2022 Jan;23(1): e13330. doi:10.1111/obr.13330. Epub 2021 Oct 18. PMID:34664799.

33. Lee JY, Kim HA, Huh K, Hyun M, Rhee JY, Jang S, et al. Risk factors for mortality and respiratory support in elderly patients hospitalized with COVID-19 in Korea. J Korean Med Sci. 2020 Jun 15;35(23): e223. doi:10.3346/jkms.2020.35. e223. PMID:32537965; PMCID: PMC7295434.

34. Sedhai YR, Shrestha D, Budhathoki P, Memon W, Acharya R, Asija A, et al. Vasopressin versus norepinephrine as the first-line vasopressor in septic shock: a meta-analysis. Crit Care Med. 2022 Jan;50(1):762

35. Arefian H, Vogel M, Kwetkat A, Hartmann M. Economic evaluation of interventions for prevention of hospital-acquired infections: a systematic review. PLoS One. 2021 Feb 11;16(2): e0246233. doi: 10.1371/journal.pone.0246233. PMID:33571240; PMCID: PMC7877876.

36. Caccialanza R, Laviano A, Lobascio F, Montagna E, Bruno R, Ludovisi S, et al. Early nutritional supplementation in non-critically ill patients hospitalized for the 2019 novel coronavirus disease (COVID-19): rationale and feasibility of a shared pragmatic protocol. Nutrition. 2020 Jun-Jul; 74:110835. doi: 10.1016/j.nut.2020.110835. Epub 2020 Apr 20. PMID:32360431; PMCID: PMC7166309.

37. Marik PE, Hooper MH. Normocaloric versus hypocaloric feeding on the outcomes of ICU patients: a meta-analysis. Nutrients. 2022 Jan 1;14(1):50. doi:10.3390/nu14010050. PMID:35008977; PMCID: PMC8745470.

Downloads

Published

2026-03-02

How to Cite

Matick, F. C. C., Gurgel, S. J. T., Massago, M., de Andrade, L., Mikcha, J. M. G., & Campanerut-Sá, P. A. Z. (2026). Unsupervised machine learning model for analyzing nutritional support in mechanically ventilated patients. Revista Contexto & Saúde, 26(51), e16971. https://doi.org/10.21527/2176-7114.2026.51.16971

Issue

Section

ORIGINAL ARTICLE