Predictive Models of Patient Severity in Intensive Care Units Based on Serum Cytokine Profiles: Advancing Rapid Analysis
Source abstract
Abstract
Predicting disease states and outcomes—and anticipating the need for specific procedures—enhances the efficiency of patient management, particularly in the dynamic and heterogenous environments of intensive care units (ICUs). This study aimed to develop robust predictive models using small sets of blood analytes to predict disease severity and mortality in ICUs, as fewer analytes are advantageous for future rapid analyses using biosensors, enabling fast clinical decision-making. Given the substantial impact of inflammatory processes, this research examined the serum profiles of 25 cytokines, either in association with or independent of nine routine blood analyses. Serum samples from 24 male COVID-19 patients admitted to an ICU were divided into three groups: Group A, including less severe patients, and Groups B and C, that needed invasive mechanical ventilation (IMV). Patients from Group C died within seven days after the current analysis. Naïve Bayes models were developed using the full dataset or with feature subsets selected either through an information gain algorithm or univariate data analysis. Strong predictive models were achieved for IMV (AUC = 0.891) and mortality within homogeneous (AUC = 0.774) or more heterogeneous (AUC = 0.887) populations utilizing two to nine features. Despite the small sample, these findings underscore the potential for effective prediction models based on a limited number of analytes.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sepsis Diagnosis and Treatment · Metabolomics and Mass Spectrometry Studies · Machine Learning in Healthcare
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
NMS—NOVA Medical School, FCM—Faculdade de Ciências Médicas, Universidade NOVA de Lisboa, Campo Mártires da Pátria 130, 1169-056 Lisbon, Portugal
ISEL—Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Rua Conselheiro Emídio Navarro 1, 1959-007 Lisbon, Portugal
CHRC—Comprehensive Health Research Centre, Universidade NOVA de Lisboa, 1150-082 Lisbon, Portugal
CIMOSM—Centro de Investigação em Modelação e Optimização de Sistemas Multifuncionais, ISEL—Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, Rua Conselheiro Emídio Navarro 1, 1959-007 Lisbon, Portugal
CIMA—Research Centre for Mathematics and Applications, Rua Conselheiro Emídio Navarro 1, 1959-007 Lisbon, Portugal
NOVA Math—Center for Mathematics and Applications, NOVA FCT—NOVA School of Science and Technology, Universidade NOVA de Lisboa, Largo da Torre, 2829-516 Caparica, Portugal
Centro de Química Estrutural—Institute of Molecular Sciences, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049-001 Lisbon, Portugal
Intensive Care Department, ULSSJ—Unidade Local de Saúde de São José, Rua José António Serrano, 1150-199 Lisbon, Portugal
Integrated Pathophysiological Mechanisms, CHRC—Comprehensive Health Research Centre, NMS—NOVA Medical School, FCM—Faculdade de Ciências Médicas, Universidade NOVA de Lisboa, Campo Mártires da Pátria 130, 1169-056 Lisbon, Portugal
iBB—Institute for Bioengineering and Biosciences, i4HB—The Associate Laboratory Institute for Health and Bioeconomy, IST—Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, 1049-001 Lisbon, Portugal
Funding
Fundação para a Ciência e a Tecnologia (FCT)
References (73)
Show source-provided references
1. ICU Scoring Systems10.4037/ccn2021613 ↗
2. Scoring systems in the intensive care unit: A compendium10.4103/0972-5229.130573 ↗
3. Yu, Z., Li, X., Zhao, J., and Sun, S. (2022). Identification of hospitalized mortality of patients with COVID-19 by machine learning models based on blood inflammatory cytokines. Front. Public Health, 10.10.3389/fpubh.2022.1001340 ↗
4. Prediction Model Based on the Combination of Cytokines and Lymphocyte Subsets for Prognosis of SARS-CoV-2 Infection10.1007/s10875-020-00821-7 ↗
5. Tulu, T.W., Wan, T.K., Chan, C.L., Wu, C.H., Woo, P.Y.M., Tseng, C.Z.S., Vodencarevic, A., Menni, C., and Chan, K.H.K. (2023). Machine learning-based prediction of COVID-19 mortality using immunological and metabolic biomarkers. BMC Digit. Health, 1.10.1186/s44247-022-00001-0 ↗
6. Outcome prediction model and prognostic biomarkers for COVID-19 patients in Vietnam10.1183/23120541.00481-2022 ↗
7. Added value of systemic inflammation markers in predicting pulmonary infection in stroke patients A retrospective study by machine learning analysis10.1097/MD.0000000000028439 ↗
8. Alanazi, A., Aldakhil, L., Aldhoayan, M., and Aldosari, B. (2023). Machine Learning for Early Prediction of Sepsis in Intensive Care Unit (ICU) Patients. Medicina, 59.10.3390/medicina59071276 ↗
9. Machine learning for the prediction of acute kidney injury in critical care patients with acute cerebrovascular disease10.1080/0886022X.2022.2036619 ↗
10. Treatments for COVID-1910.1146/annurev-med-052422-020316 ↗
11. MaxQuant enables high peptide identification rates, individualized p.p.b.-range mass accuracies and proteome-wide protein quantification10.1038/nbt.1511 ↗
12. The MaxQuant computational platform for mass spectrometry-based shotgun proteomics10.1038/nprot.2016.136 ↗
13. Andromeda: A peptide search engine integrated into the MaxQuant environment10.1021/pr101065j ↗
14. UniProt: The universal protein knowledgebase in 202110.1093/nar/gkaa1100 ↗
15. A Proteomics Approach to the Protein Normalization Problem: Selection of Unvarying Proteins for MS-Based Proteomics and Western Blotting10.1021/acs.jproteome.6b00403 ↗
16. Proteomics. Tissue-based map of the human proteome10.1126/science.1260419 ↗
17. Accurate Proteome-wide Label-free Quantification by Delayed Normalization and Maximal Peptide Ratio Extraction, Termed MaxLFQ10.1074/mcp.M113.031591 ↗
18. The Perseus computational platform for comprehensive analysis of (prote)omics data10.1038/nmeth.3901 ↗
19. PANTHER version 16: A revised family classification, tree-based classification tool, enhancer regions and extensive API10.1093/nar/gkaa1106 ↗
20. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)10.1016/j.cosrev.2021.100378 ↗
21. Medical data classification with Naive Bayes approach10.3923/itj.2012.1166.1174 ↗
22. On the Optimality of the Simple Bayesian Classifier under Zero-One Loss10.1023/A:1007413511361 ↗
23. Bayesian prediction of treatment outcome in anorexia nervosa: A preliminary study10.3109/08039488.2014.962612 ↗
24. Guido, R., Ferrisi, S., Lofaro, D., and Conforti, D. (2024). An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review. Information, 15.10.3390/info15040235 ↗
25. Entropy based C4.5-SHO algorithm with information gain optimization in data mining10.7717/peerj-cs.424 ↗
26. Proactively selection of input variables based on information gain factors for deep learning models in short-term solar irradiance forecasting10.1016/j.energy.2023.129261 ↗
27. Feature Selection for Classification using Principal Component Analysis and Information Gain10.1016/j.eswa.2021.114765 ↗
28. Determining threshold value on information gain feature selection to increase speed and prediction accuracy of random forest10.1186/s40537-021-00472-4 ↗
29. Impaired type I interferon activity and inflammatory responses in severe COVID-19 patients10.1126/science.abc6027 ↗
30. A comprehensive evaluation of the immune system response and type-I Interferon signaling pathway in hospitalized COVID-19 patients10.1186/s12964-022-00903-6 ↗
31. SARS-CoV-2 infection: The role of cytokines in COVID-19 disease10.1016/j.cytogfr.2020.06.001 ↗
32. The inhibition of IL-2/IL-2R gives rise to CD8+ T cell and lymphocyte decrease through JAK1-STAT5 in critical patients with COVID-19 pneumonia10.1038/s41419-020-2636-4 ↗
33. Khan, W.A. (2019). Cytokines and Interferons: Types and Functions. Autoantibodies and Cytokines, IntechOpen.
34. The Important Role of Interleukin-2 in COVID-19
35. The misunderstood link between SARS-CoV-2 and angiogenesis. A narrative review10.1016/j.pulmoe.2021.08.004 ↗
36. Bin. Clinical significance of mechanical ventilation on ischemic-reperfusion injury caused by lung chest trauma and VEGF expression levels in peripheral blood10.3892/etm.2017.4825 ↗
37. Jøntvedt Jørgensen, M., Holter, J.C., Christensen, E.E., Schjalm, C., Tonby, K., Pischke, S.E., Jenum, S., Skeie, L.G., Nur, S., and Lind, A. (2020). Increased interleukin-6 and macrophage chemoattractant protein-1 are associated with respiratory failure in COVID-19. Sci. Rep., 10.10.1038/s41598-020-78710-7 ↗
38. Predictive value of C-reactive protein in critically ill patients who develop acute lung injury10.1016/j.ejcdt.2014.10.006 ↗
39. Prediction of outcome and prognosis of patients on mechanical ventilation using body mass index, SOFA score, C-Reactive protein, and serum albumin
40. Russo, A., Tellone, E., Barreca, D., Ficarra, S., and Laganà, G. (2022). Implication of COVID-19 on Erythrocytes Functionality: Red Blood Cell Biochemical Implications and Morpho-Functional Aspects. Int. J. Mol. Sci., 23.10.3390/ijms23042171 ↗
41. Lechuga, G.C., Morel, C.M., and De-Simone, S.G. (2023). Hematological alterations associated with long COVID-19. Front. Physiol., 14.10.3389/fphys.2023.1203472 ↗
42. Ceccato, A., Panagiotarakou, M., Ranzani, O.T., Martin-Fernandez, M., Almansa-Mora, R., Gabarrus, A., Bueno, L., Cilloniz, C., Liapikou, A., and Ferrer, M. (2019). Lymphocytopenia as a Predictor of Mortality in Patients with ICU-Acquired Pneumonia. J. Clin. Med., 8.10.3390/jcm8060843 ↗
43. Lymphopenia: A useful predictor of COVID-19 disease severity and mortality10.12669/pjms.37.7.4085 ↗
44. Suspected myocardial injury in patients with COVID-19: Evidence from front-line clinical observation in Wuhan, China10.1016/j.ijcard.2020.03.087 ↗
45. Cardiovascular manifestations and treatment considerations in COVID-1910.1136/heartjnl-2020-317056 ↗
46. McKenna, E., Wubben, R., Isaza-Correa, J.M., Melo, A.M., Mhaonaigh, A.U., Conlon, N., O’Donnell, J.S., Ní Cheallaigh, C., Hurley, T., and Stevenson, N.J. (2022). Neutrophils in COVID-19: Not Innocent Bystanders. Front. Immunol., 13.10.3389/fimmu.2022.864387 ↗
47. The Level of Procalcitonin in Severe COVID-19 Patients: A Systematic Review and Meta-Analysis10.1007/978-3-030-59261-5_25 ↗
48. Lactate dehydrogenase levels predict coronavirus disease 2019 (COVID-19) severity and mortality: A pooled analysis10.1016/j.ajem.2020.05.073 ↗
49. Lopes-Pacheco, M., Silva, P.L., Cruz, F.F., Battaglini, D., Robba, C., Pelosi, P., Morales, M.M., Caruso Neves, C., and Rocco, P.R.M. (2021). Pathogenesis of Multiple Organ Injury in COVID-19 and Potential Therapeutic Strategies. Front. Physiol., 12.10.3389/fphys.2021.593223 ↗
50. Ferritin levels in patients with COVID-19: A poor predictor of mortality and hemophagocytic lymphohistiocytosis10.1111/ijlh.13309 ↗
51. Serum ferritin as a predictive biomarker in COVID-19. A systematic review, meta-analysis and meta-regression analysis10.1016/j.jcrc.2021.09.023 ↗
52. D-dimer levels on admission to predict in-hospital mortality in patients with COVID-1910.1111/jth.14859 ↗
53. Fibrinogen, Fibrin, and Fibrin Degradation Products in COVID-19
54. Patel, D., Kher, V., Desai, B., Lei, X., Cen, S., Nanda, N., Gholamrezanezhad, A., Duddalwar, V., Varghese, B., and Oberai, A.A. (2021). Machine learning based predictors for COVID-19 disease severity. Sci. Rep., 11.10.1038/s41598-021-83967-7 ↗
55. An algorithm to predict the need for invasive mechanical ventilation in hospitalized COVID-19 patients: The experience in Sao Paulo10.4266/acc.2022.00283 ↗
56. Estimating risk of mechanical ventilation and in-hospital mortality among adult COVID-19 patients admitted to Mass General Brigham: The VICE and DICE scores10.1016/j.eclinm.2021.100765 ↗
57. Chen, G., Zhao, X., Chen, X., and Liu, C. (2023). Early decrease in blood lymphocyte count is associated with poor prognosis in COVID-19 patients: A retrospective cohort study. BMC Pulm. Med., 23.10.1186/s12890-023-02767-z ↗
58. Prognostic importance of monitoring the lymphocyte count in critically ill COVID-19 patients during the ICU stay10.1016/j.jcrc.2024.154673 ↗
59. Wang, S., Sheng, Y., Tu, J., and Zhang, L. (2021). Association between peripheral lymphocyte count and the mortality risk of COVID-19 inpatients. BMC Pulm. Med., 21.10.1186/s12890-021-01422-9 ↗
60. Host Response Changes and Their Association with Mortality in COVID-19 Patients with Lymphopenia10.1164/rccm.202305-0890OC ↗
61. A novel haemocytometric COVID-19 prognostic score developed and validated in an observational multicentre European hospital-based study10.7554/eLife.63195 ↗
62. Increased levels of plasma cytokines and correlations to organ failure and 30-day mortality in critically ill COVID-19 patients10.1016/j.cyto.2020.155389 ↗
63. dos Santos Medeiros, S.M.D.F.R., Sousa Lino, B.M.N., Perez, V.P., Sousa, E.S.S., Campana, E.H., Miyajima, F., Carvalho-Silva, W.H.V., Dejani, N.N., de Sousa Fernandes, M.S., and Yagin, F.H. (2024). Predictive biomarkers of mortality in patients with severe COVID-19 hospitalized in intensive care unit. Front. Immunol., 15.10.3389/fimmu.2024.1416715 ↗
64. Sharma, J., Rajput, R., Bhatia, M., Arora, P., and Sood, V. (2021). Clinical Predictors of COVID-19 Severity and Mortality: A Perspective. Front. Cell Infect. Microbiol., 11.10.3389/fcimb.2021.674277 ↗
65. Prediction of outcome in patients with acute respiratory distress syndrome by bronchoalveolar lavage inflammatory mediators10.1258/ebm.2009.009256 ↗
66. Hennus, M.P., Van Vught, A.J., Brabander, M., Brus, F., Jansen, N.J., and Bont, L.J. (2013). Mechanical Ventilation Drives Inflammation in Severe Viral Bronchiolitis. PLoS ONE, 8.10.1371/journal.pone.0083035 ↗
67. Jang, H.J., Leem, A.Y., Chung, K.S., Ahn, J.Y., Jung, J.Y., Kang, Y.A., Park, M.S., Kim, Y.S., and Lee, S.H. (2021). Soluble IL-2R Levels Predict in-Hospital Mortality in COVID-19 Patients with Respiratory Failure. J. Clin. Med., 10.10.21203/rs.3.rs-709180/v1 ↗
68. Vascular endothelial growth factor in severe sepsis and septic shock10.1213/ane.0b013e31816a643f ↗
69. Elevated plasma levels of selective cytokines in COVID-19 patients reflect viral load and lung injury10.1093/nsr/nwaa037 ↗
70. Smail, S.W., Babaei, E., Amin, K., and Abdulahad, W.H. (2023). Serum IL-23, IL-10, and TNF-α predict in-hospital mortality in COVID-19 patients. Front. Immunol., 14.10.3389/fimmu.2023.1145840 ↗
71. Mwangi, V.I., Netto, R.L.A., de Morais, C.E.P., Silva, A.S., Silva, B.M., Lima, A.B., Neves, J.C.F., Borba, M.G.S., Val, F.F.A., and de Almeida, A.C.G. (2023). Temporal patterns of cytokine and injury biomarkers in hospitalized COVID-19 patients treated with methylprednisolone. Front. Immunol., 16.10.3389/fimmu.2023.1229611 ↗
72. Silva, M.J.A., Ribeiro, L.R., Gouveia, M.I.M., Marcelino, B.d.R., dos Santos, C.S., Lima, K.V.B., and Lima, L.N.G.C. (2023). Hyperinflammatory Response in COVID-19: A Systematic Review. Viruses, 15.10.3390/v15020553 ↗
73. Sánchez-Montalvá, A., Álvarez-Sierra, D., Martínez-Gallo, M., Perurena-Prieto, J., Arrese-Muñoz, I., Ruiz-Rodríguez, J.C., Espinosa-Pereiro, J., Bosch-Nicolau, P., Martínez-Gómez, X., and Antón, A. (2022). Exposing and Overcoming Limitations of Clinical Laboratory Tests in COVID-19 by Adding Immunological Parameters; A Retrospective Cohort Analysis and Pilot Study. Front. Immunol., 13.10.3389/fimmu.2022.902837 ↗