medigraphic.com
Colegio de Medicina Interna de México.

2024, Número 6

<< Anterior Siguiente >>

Med Int Mex 2024; 40 (6)


Biomarcadores de la inflamación como predictores de gravedad y mortalidad en pacientes con COVID-19 grave: estudio basado en algoritmos de clasificación de aprendizaje automático

Jiménez JX, Barragán HIJ, Jiménez JS, Vuelvas OCR, Cortés ÁNY

Idioma: Español
Referencias bibliográficas: 39
Paginas: 346-355
Archivo PDF: 250.54 Kb.


RESUMEN

Objetivo: Evaluar, a través de algoritmos de clasificación de aprendizaje automático, el valor predictivo de los biomarcadores de inflamación para predecir el alta del hospital de pacientes con COVID-19 grave.
Materiales y Métodos: Estudio retrospectivo observacional de un solo centro que evaluó los registros clínicos de pacientes atendidos entre marzo de 2021 y enero de 2022 con un método de muestreo sistemático. Se utilizaron como variables predictoras los valores demográficos y clínicos que incluyeron los valores de dímero D, procalcitonina, ferritina y fibrinógeno de cada paciente.
Resultados: Se incluyeron 191 pacientes. El análisis de diferentes algoritmos de aprendizaje automático mostró que el algoritmo de máquina de vectores de soporte con núcleo obtuvo el mejor rendimiento con precisión de 0.80, desviación estándar de 0.06 y sensibilidad de 0.71. Asimismo, el dímero D (RM: 1.0032 [1.0130, 1.7230], p ‹ 0.05; AUC: 0.580), la ferritina (RM: 1.023 [1.019, 1.843], p ‹ 0.05, AUC: 0.885) y la relación ferritina-procalcitonina (RM: 1.324 [1.012, 1.478], p ‹ 0.05; AUC: 0.859) fueron predictores potenciales de la progresión y de eventos fatales generados por la COVID-19.
Conclusiones: Los algoritmos de clasificación obtenidos por aprendizaje automático son una herramienta útil para predecir la gravedad y los desenlaces fatales en los brotes infecciosos. En este estudio se demostró que el dímero D es el mejor predictor de la gravedad y de eventos fatales por COVID-19 grave.


REFERENCIAS (EN ESTE ARTÍCULO)

  1. Msemburi, W, Karlinsky, A, Knutson, V, Aleshin-Guendel,S, et al. The WHO estimates of excess mortality associatedwith the COVID-19 pandemic. Nature 2023; 613 (7942).https://doi.org/10.1038/s41586-022-05522-2

  2. Akman C, Bakırdöğen S. The role of serum inflammatorymarkers, albumin, and hemoglobin in predicting the diagnosisin patients admitted to the emergency departmentwith a pre-diagnosis of COVID-19. Rev Assoc Med Bras2021; 67. doi: 10.1590/1806-9282.67.Suppl1.20200917

  3. Conway EM, Mackman N, Warren RQ, Wolberg AS, et al.Understanding COVID-19-associated coagulopathy. NatureReviews Immunology 2022; 22 (10): 639-649. https://doi.org/10.1038/s41577-022-00762-9

  4. Huang C, Wang Y, Li X, Ren L, et al. Clinical features ofpatients infected with 2019 novel coronavirus in Wuhan,China. Lancet 2020; 395 (10223): 497-506. doi: 10.1016/S0140-6736(20)30183-5

  5. Mehta P, McAuley DF, Brown M, Sanchez E, et al. COVID-19:consider cytokine storm syndromes and immunosuppression.Lancet (London, England) 2020; 395 (10229): 1033-1034. doi: 10.1016/S0140-6736(20)30628-0

  6. Pranata R, Henrina J, Lim MA, Lawrensia S, et. al. Clinicalfrailty scale and mortality in COVID-19: a systematic reviewand dose-response meta-analysis. Arch Gerontol Geriatr2021; 93: 104324. doi: 10.1016/j.archger.2020.104324

  7. Beltrán-García J, Osca-Verdegal R, Pallardó FV, Ferreres J,et al. Oxidative stress and inflammation in COVID-19-associatedsepsis: the potential role of anti-oxidant therapyin avoiding disease progression. Antioxidants 2020; 9 (10):936. doi: 10.3390/antiox9100936

  8. Hu H, Yao N, Qiu Y. Comparing rapid scoring systems inmortality prediction of critically ill patients with novelcoronavirus disease. Acad Emerg Med 2020; 27 (6): 461-8.doi: 10.1111/acem.13992

  9. Yan L, Zhang H-T, Goncalves J, Xiao Y, et al. An interpretablemortality prediction model for COVID-19 patients. NatureMach Intell 2020; 2: 283-8. https://doi.org/10.1038/s42256-020-0180-7

  10. Malki Z, Atlam E-S, Hassanien AE, Dagnew G, et al. Associationbetween weather data and COVID-19 pandemicpredicting mortality rate: machine learning approaches.Chaos Solitons Fractals 2020; 138: 110137. doi: 10.1016/j.chaos.2020.110137

  11. Shanbehzadeh M, Nopour R, Kazemi-Arpanahi H. Comparisonof four data mining algorithms for predicting colorectalcancer risk. J Adv Med Biomed Res 2021; 29 (133): 100-8.DOI:10.30699/jambs.29.133.100

  12. Shipe ME, Deppen SA, Farjah F, Grogan EL. Developingprediction models for clinical use using logistic regression:an overview. J Thorac Dis 2019; 11 (Suppl 4): S574. doi:10.21037/jtd.2019.01.25

  13. Gao Y, Cai G-Y, Fang W, Li H-Y, et al. Machine learning basedearly warning system enables accurate mortality riskprediction for COVID-19. Nat Commun 2020; 11 (1): 1-10.doi.org/10.1038/s41467-020-18684-2

  14. Henry BM, Benoit SW, de Oliveira MHS, Hsieh WC, et. al.Laboratory abnormalities in children with mild and severecoronavirus disease 2019 (COVID-19): A pooled analysisand review. Clin Biochem 2020; 81: 1-8. doi: 10.1016/j.clinbiochem.2020.05.012

  15. Sui J, Noubouossie DF, Gandotra S, Cao L. Elevated plasmafibrinogen is associated with excessive inflammation anddisease severity in COVID-19 patients. Front Cell InfectMicrobiol 2021; 11. doi: 10.3389/fcimb.2021.734005

  16. Sukrisman L, Sinto R. Coagulation profile and correlationbetween Dímero-D, inflammatory markers, and COVID-19severity in an Indonesian national referral hospital. J IntMed Res 2021; 49 (11). doi: 10.1177/03000605211059939

  17. Zeng F, Huang Y, Guo Y, Yin M, et al. Association of inflammatorymarkers with the severity of COVID-19: A metaanalysis.Int J Infect Dis 2020; 96: 467. doi: 10.1016/j.ijid.2020.05.055

  18. Alvarez-Perez FJ, Castelo-Branco M, Alvarez-Sabin J.Usefulness of measurement of fibrinogen, D-dimer, Ddimer/fibrinogen ratio, C reactive protein and erythrocytesedimentation rate to assess the pathophysiology and mechanismof ischemic stroke. J Neurol Neurosurg Psychiatry2011; 82 (9). doi: 10.1136/jnnp.2010.230870

  19. Hajsadeghi S, Kerman SR, Khojandi M, Vaferi H, et al. Accuracyof D-dimer:fibrinogen ratio to diagnose pulmonary thromboembolismin patients admitted to intensive care units.Cardiovasc J Afr 2012; 23 (8). doi: 10.5830/CVJA-2012-041

  20. Kara H, Bayir A, Degirmenci S, Kayis SA, et al. D-dimerand D-dimer/fibrinogen ratio in predicting pulmonaryembolism in patients evaluated in a hospital emergencydepartment. Acta Clin Belg 2014; 69 (4). doi:10.1179/2295333714Y.0000000029

  21. Kucher N, Kohler HP, Dornhöfer T, Wallmann D, Lämmle B.Accuracy of D-dimer/fibrinogen ratio to predict pulmonaryembolism: A prospective diagnostic study. J Thromb Hemost2003; 1 (4). doi: 10.1046/j.1538-7836.2003.00145.x

  22. Murat S, Murat B, Dural M, Mert GO, Cavusoglu Y. Prognosticvalue of D-dimer/fibrinogen ratio on in-hospitaloutcomes of patients with heart failure and COVID-19.Biomark Med 2021; 15 (16). doi: 10.2217/bmm-2021-0341

  23. Rajendran V, Gopalan S, Varadaraj P, Pandurangan V, et al.Course of COVID-19 based on admission D-dimer levelsand its influence on thrombosis and mortality. J Clin MedRes 2021; 13 (7). doi: 10.14740/jocmr4550

  24. Zhou F, Yu T, Du R, Fan G, et al. Clinical course and riskfactors for mortality of adult inpatients with COVID-19 inWuhan, China: a retrospective cohort study. Lancet 2020;395 (10229): 1054-1062. https://doi.org/10.1016/S0140-6736(20)30566-3

  25. Rostami M, Mansouritorghabeh H. D-dimer levelin COVID-19 infection: a systematic review. ExpertRev Hematol 2020; 13 (11): 1265-1275. doi:10.1080/17474086.2020.1831383

  26. Yao Y, Cao J, Wang Q, Shi Q, et al. D-dimer as a biomarker fordisease severity and mortality in COVID-19 patients: a casecontrol study. J Intensive Care 2020; 8 (1). doi: 10.1186/s40560-020-00466-z

  27. Yu HH, Qin C, Chen M, Wang W, Tian DS. D-dimer levelis associated with the severity of COVID-19. Thromb Res2020; 195: 219-225. doi: 10.1016/j.thromres.2020.07.047

  28. Thachil J, Tang N, Gando S, Falanga A, et al. ISTH interimguidance on recognition and management of coagulopathyin COVID-19. J Thromb Haemost 2020; 18 (5): 1023-1026.doi: 10.1111/jth.14810

  29. Alunno A, Carubbi F, Rodríguez-Carrio J. Storm, typhoon,cyclone or hurricane in patients with COVID-19? Bewareof the same storm that has a different origin. RMD Open2020; 6 (1). doi: 10.1136/rmdopen-2020-001295

  30. Ruan Q, Yang K, Wang W, Jiang L, Song J. Clinical predictorsof mortality due to COVID-19 based on an analysis of dataof 150 patients from Wuhan, China. Intensive Care Med2020; 46 (5): 846-848. doi: 10.1007/s00134-020-05991-x

  31. Kernan KF, Carcillo JA. Hyperferritinemia and inflammation.Int Immunol 2017; 29 (9): 401-409. doi: 10.1093/intimm/dxx031

  32. Ramonfaur D, Aguirre-García GM, Diaz-Garza CA,Torre-Amione G, et al. Early increase of serum ferritinamong COVID-19 patients is associated with need ofinvasive mechanical ventilation and with in-hospitaldeath. Infect Dis (London) 2022; 54 (11): 810-818. doi:10.1080/23744235.2022.2101691

  33. Fox SE, Akmatbekov A, Harbert JL, Li G, et al. Pulmonaryand cardiac pathology in African American patients withCOVID-19: an autopsy series from New Orleans. LancetRespir Med 2020; 8 (7): 681-686. doi: 10.1016/S2213-2600(20)30243-5

  34. Kamat IS, Ramachandran V, Eswaran H, Guffey D, MusherDM. Procalcitonin to distinguish viral from bacterial pneumonia:a systematic review and meta-analysis. Clin InfectDis 2020; 70 (3): 538-542. doi: 10.1093/cid/ciz545

  35. Lippi G, Plebani. Procalcitonin in patients with severe coronavirusdisease 2019 (COVID-19): A meta-analysis. ClinChim Acta 2020; 505: 190. doi: 10.1016/j.cca.2020.03.004

  36. Moulaei K, Shanbehzadeh M, Mohammadi-Taghiabad Z, Kazemi-Arpanahi H. Comparing machine learning algorithms forpredicting COVID-19 mortality. BMC Med Inform Decis Mak2022; 22 (1): 2. https://doi.org/10.1186/s12911-021-01742-0

  37. Subudhi S, Verma A, Patel AB, Hardin CC, et al. Comparingmachine learning algorithms for predicting ICU admissionand mortality in COVID-19. npj Digit Med 2021; 4 (1): 87.https://doi.org/10.1038/s41746-021-00456-x

  38. Hachim IY, Hachim MY, Hannawi H, Naeem KB, et al. Theinflammatory biomarkers profile of hospitalized patientswith COVID-19 and its association with patient’s outcome:A single centered study. PloS One 2021; 16 (12). doi:10.1371/journal.pone.0260537

  39. Jiménez-Jiménez X, Alvarado-Romano V, Galaviz-Pérez RA,Maya-Piña LV, et al. Identification of clinical and demographicvariables associated with severe Covid-19 in subjects withrheumatic disease in a third-level hospital in Mexico City. SaludPublica Mex 2023; 65 (3): 300-302. doi: 10.21149/14235




2020     |     www.medigraphic.com