A machine learning diagnostic model for Pneumocystis jirovecii pneumonia in patients with severe pneumonia.
Diagnostic model
Machine learning
Pneumocystis jirovecii pneumonia
Severe pneumonia
Journal
Internal and emergency medicine
ISSN: 1970-9366
Titre abrégé: Intern Emerg Med
Pays: Italy
ID NLM: 101263418
Informations de publication
Date de publication:
09 2023
09 2023
Historique:
received:
17
02
2023
accepted:
17
06
2023
medline:
18
9
2023
pubmed:
2
8
2023
entrez:
2
8
2023
Statut:
ppublish
Résumé
The diagnosis of Pneumocystis jirovecii pneumonia (PCP) in patients presenting with severe pneumonia is challenging and delays in treatment were associated with worse prognosis. This study aimed to develop a rapid, easily available, noninvasive machine learning diagnostic model for PCP among patients with severe pneumonia. A retrospective study was performed in West China Hospital among consecutive patients with severe pneumonia who had undergone bronchoalveolar lavage for etiological evaluation between October 2010 and April 2021. Factors associated with PCP were identified and four diagnostic models were established using machine learning algorithms including Logistic Regression, eXtreme Gradient Boosting, Random Forest (RF) and LightGBM. The performance of these models were evaluated by the area under the receiver operating characteristic curve (AUC). Ultimately, 704 patients were enrolled and randomly divided into a training set (n = 564) and a testing set (n = 140). Four factors were ultimately selected to establish the model including neutrophil, globulin, β-D-glucan and ground glass opacity. The RF model exhibited the greatest diagnostic performance with an AUC of 0.907. The calibration curve and decision curve analysis also demonstrated its accuracy and applicability. We constructed a PCP diagnostic model in patients with severe pneumonia using four easily available and noninvasive clinical indicators. With satisfying diagnostic performance and good clinical practicability, this model may help clinicians to make early diagnosis of PCP, reduce the delays of treatment and improve the prognosis among these patients.
Sections du résumé
BACKGROUND
The diagnosis of Pneumocystis jirovecii pneumonia (PCP) in patients presenting with severe pneumonia is challenging and delays in treatment were associated with worse prognosis. This study aimed to develop a rapid, easily available, noninvasive machine learning diagnostic model for PCP among patients with severe pneumonia.
METHODS
A retrospective study was performed in West China Hospital among consecutive patients with severe pneumonia who had undergone bronchoalveolar lavage for etiological evaluation between October 2010 and April 2021. Factors associated with PCP were identified and four diagnostic models were established using machine learning algorithms including Logistic Regression, eXtreme Gradient Boosting, Random Forest (RF) and LightGBM. The performance of these models were evaluated by the area under the receiver operating characteristic curve (AUC).
RESULTS
Ultimately, 704 patients were enrolled and randomly divided into a training set (n = 564) and a testing set (n = 140). Four factors were ultimately selected to establish the model including neutrophil, globulin, β-D-glucan and ground glass opacity. The RF model exhibited the greatest diagnostic performance with an AUC of 0.907. The calibration curve and decision curve analysis also demonstrated its accuracy and applicability.
CONCLUSIONS
We constructed a PCP diagnostic model in patients with severe pneumonia using four easily available and noninvasive clinical indicators. With satisfying diagnostic performance and good clinical practicability, this model may help clinicians to make early diagnosis of PCP, reduce the delays of treatment and improve the prognosis among these patients.
Identifiants
pubmed: 37530943
doi: 10.1007/s11739-023-03353-1
pii: 10.1007/s11739-023-03353-1
doi:
Substances chimiques
beta-Glucans
0
Types de publication
Randomized Controlled Trial
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1741-1749Subventions
Organisme : National Natural Science Foundation of China
ID : Grant No. 81600057
Informations de copyright
© 2023. The Author(s), under exclusive licence to Società Italiana di Medicina Interna (SIMI).
Références
Pegorie M, Denning DW, Welfare W (2017) Estimating the burden of invasive and serious fungal disease in the United Kingdom. J Infect 74(1):60–71. https://doi.org/10.1016/j.jinf.2016.10.005
doi: 10.1016/j.jinf.2016.10.005
pubmed: 27789254
Thomas CF Jr, Limper AH (2004) Pneumocystis pneumonia. N Engl J Med 350(24):2487–2498. https://doi.org/10.1056/NEJMra032588
doi: 10.1056/NEJMra032588
pubmed: 15190141
Avino LJ, Naylor SM, Roecker AM (2016) Pneumocystis jirovecii pneumonia in the non-hiv-infected population. Ann Pharmacother 50(8):673–679. https://doi.org/10.1177/1060028016650107
doi: 10.1177/1060028016650107
pubmed: 27242349
Fillatre P, Decaux O, Jouneau S et al (2014) Incidence of pneumocystis jiroveci pneumonia among groups at risk in HIV-negative patients. Am J Med 127(12):1242.e11–7. https://doi.org/10.1016/j.amjmed.2014.07.010
doi: 10.1016/j.amjmed.2014.07.010
pubmed: 25058862
Roux A, Canet E, Valade S et al (2014) Pneumocystis jirovecii pneumonia in patients with or without AIDS. France Emerg Infect Dis 20(9):1490–1497. https://doi.org/10.3201/eid2009.131668
doi: 10.3201/eid2009.131668
pubmed: 25148074
Reid AB, Chen SC, Worth LJ (2011) Pneumocystis jirovecii pneumonia in non-HIV-infected patients: new risks and diagnostic tools. Curr Opin Infect Dis 24(6):534–544. https://doi.org/10.1097/QCO.0b013e32834cac17
doi: 10.1097/QCO.0b013e32834cac17
pubmed: 21986616
Weyant RB, Kabbani D, Doucette K et al (2021) Pneumocystis jirovecii: a review with a focus on prevention and treatment. Expert Opin Pharmacother 22(12):1579–1592. https://doi.org/10.1080/14656566.2021.1915989
doi: 10.1080/14656566.2021.1915989
pubmed: 33870843
Sokulska M, Kicia M, Wesołowska M et al (2015) Pneumocystis jirovecii–from a commensal to pathogen: clinical and diagnostic review. Parasitol Res 114(10):3577–3585. https://doi.org/10.1007/s00436-015-4678-6
doi: 10.1007/s00436-015-4678-6
pubmed: 26281787
pmcid: 4562001
Li MC, Lee NY, Lee CC et al (2014) Pneumocystis jiroveci pneumonia in immunocompromised patients: delayed diagnosis and poor outcomes in non-HIV-infected individuals. J Microbiol Immunol Infect 47(1):42–47. https://doi.org/10.1016/j.jmii.2012.08.024
doi: 10.1016/j.jmii.2012.08.024
pubmed: 23063081
Azoulay E, Roux A, Vincent F et al (2018) A multivariable prediction model for pneumocystis jirovecii pneumonia in hematology patients with acute respiratory failure. Am J Respir Crit Care Med 198(12):1519–1526. https://doi.org/10.1164/rccm.201712-2452OC
doi: 10.1164/rccm.201712-2452OC
pubmed: 29995433
Metlay JP, Waterer GW, Long AC et al (2019) Diagnosis and treatment of adults with community-acquired pneumonia. An Official Clinical Practice Guideline of the American Thoracic Society and Infectious Diseases Society of America. Am J Respir Crit Care Med 200(7):e45–e67. https://doi.org/10.1164/rccm.201908-1581ST
doi: 10.1164/rccm.201908-1581ST
pubmed: 31573350
pmcid: 6812437
Del Corpo O, Butler-Laporte G, Sheppard DC et al (2020) Diagnostic accuracy of serum (1–3)-β-D-glucan for Pneumocystis jirovecii pneumonia: a systematic review and meta-analysis. Clin Microbiol Infect 26(9):1137–1143. https://doi.org/10.1016/j.cmi.2020.05.024
doi: 10.1016/j.cmi.2020.05.024
pubmed: 32479781
Ideguchi S, Yamamoto K, Hirayama T et al (2020) Diagnostic evaluation of serum (1, 3)-β-d-glucan levels using the Fungitec G-Test MK kit for pneumocystis jirovecii pneumonia (PCP) in non-HIV patients. Med Mycol. https://doi.org/10.1093/mmy/myaa101
doi: 10.1093/mmy/myaa101
pubmed: 33369648
Sax PE, Komarow L, Finkelman MA et al (2011) Blood (1->3)-beta-D-glucan as a diagnostic test for HIV-related pneumocystis jirovecii pneumonia. Clin Infect Dis 53(2):197–202. https://doi.org/10.1093/cid/cir335
doi: 10.1093/cid/cir335
pubmed: 21690628
pmcid: 3165964
Salerno D, Mushatt D, Myers L et al (2014) Serum and bal beta-D-glucan for the diagnosis of pneumocystis pneumonia in HIV positive patients. Respir Med 108(11):1688–1695. https://doi.org/10.1016/j.rmed.2014.09.017
doi: 10.1016/j.rmed.2014.09.017
pubmed: 25448310
pmcid: 4297544
Mercier T, Aissaoui N, Gits-Muselli M et al (2020) Variable correlation between bronchoalveolar lavage fluid fungal load and serum-(1,3)-β-d-glucan in patients with pneumocystosis—a multicenter ECMM excellence center study. J Fungi (Basel) 6(4):327. https://doi.org/10.3390/jof6040327
doi: 10.3390/jof6040327
pubmed: 33271743
Cao Y, Chen J, Dong L (2022) Supplementary role of immunological indicators in the diagnosis and prognosis of pneumocystis pneumonia in non-HIV immunocompromised patients. Infect Drug Resist 15:4675–4683. https://doi.org/10.2147/IDR.S372427
doi: 10.2147/IDR.S372427
pubmed: 36034170
pmcid: 9406888
Fishman JA (2020) Pneumocystis jiroveci. Semin Respir Crit Care Med 41(1):141–157. https://doi.org/10.1055/s-0039-3399559
doi: 10.1055/s-0039-3399559
pubmed: 32000290
Cereser L, Dallorto A, Candoni A et al (2019) Pneumocystis jirovecii pneumonia at chest high-resolution computed tomography (HRCT) in non-HIV immunocompromised patients: spectrum of findings and mimickers. Eur J Radiol 116:116–127. https://doi.org/10.1016/j.ejrad.2019.04.025
doi: 10.1016/j.ejrad.2019.04.025
pubmed: 31153552
Kanne JP, Yandow DR, Meyer CA (2012) Pneumocystis jiroveci pneumonia: high-resolution CT findings in patients with and without HIV infection. Am J Roentgenol 198(6):W555–W561. https://doi.org/10.2214/AJR.11.7329
doi: 10.2214/AJR.11.7329
Vogel MN, Vatlach M, Weissgerber P et al (2012) HRCT-features of pneumocystis jiroveci pneumonia and their evolution before and after treatment in non-HIV immunocompromised patients. Eur J Radiol 81(6):1315–1320. https://doi.org/10.1016/j.ejrad.2011.02.052
doi: 10.1016/j.ejrad.2011.02.052
pubmed: 21420818
Rodriguez M, Fishman JA (2004) Prevention of infection due to Pneumocystis spp. in human immunodeficiency virus-negative immunocompromised patients. Clin Microbiol Rev 17(4):770–782. https://doi.org/10.1128/CMR.17.4.770-782.2004
doi: 10.1128/CMR.17.4.770-782.2004
pubmed: 15489347
pmcid: 523555
Neumann S, Krause SW, Maschmeyer G et al (2013) Primary prophylaxis of bacterial infections and pneumocystis jirovecii pneumonia in patients with hematological malignancies and solid tumors : guidelines of the Infectious Diseases Working Party (AGIHO) of the German Society of Hematology and Oncology (DGHO). Ann Hematol 92(4):433–442. https://doi.org/10.1007/s00277-013-1698-0
doi: 10.1007/s00277-013-1698-0
pubmed: 23412562
pmcid: 3590398
Simonds RJ, Lindegren ML, Thomas P et al (1995) Prophylaxis against pneumocystis carinii pneumonia among children with perinatally acquired human immunodeficiency virus infection in the United States. Pneumocystis carinii Pneumonia Prophylaxis Evaluation Working Group. N Engl J Med 332(12):786–790. https://doi.org/10.1056/NEJM199503233321206
doi: 10.1056/NEJM199503233321206
pubmed: 7862183
Bhagwat SP, Gigliotti F, Xu H et al (2006) Contribution of T cell subsets to the pathophysiology of pneumocystis-related immunorestitution disease. Am J Physiol Lung Cell Mol Physiol 291(6):L1256–L1266. https://doi.org/10.1152/ajplung.00079.2006
doi: 10.1152/ajplung.00079.2006
pubmed: 16891394
Apostolopoulou A, Fishman JA (2022) The pathogenesis and diagnosis of pneumocystis jiroveci pneumonia. J Fungi (Basel) 8(11):1167. https://doi.org/10.3390/jof8111167
doi: 10.3390/jof8111167
pubmed: 36354934
Calderón EJ, Gutiérrez-Rivero S, Durand-Joly I et al (2010) Pneumocystis infection in humans: diagnosis and treatment. Expert Rev Anti Infect Ther 8(6):683–701. https://doi.org/10.1586/eri.10.42
doi: 10.1586/eri.10.42
pubmed: 20521896
Senécal J, Smyth E, Del Corpo O et al (2022) Non-invasive diagnosis of Pneumocystis jirovecii pneumonia: a systematic review and meta-analysis. Clin Microbiol Infect 28(1):23–30. https://doi.org/10.1016/j.cmi.2021.08.017
doi: 10.1016/j.cmi.2021.08.017
pubmed: 34464734
Cruciani M, Marcati P, Malena M et al (2002) Meta-analysis of diagnostic procedures for pneumocystis carinii pneumonia in HIV-1-infected patients. Eur Respir J 20(4):982–989. https://doi.org/10.1183/09031936.02.01372002
doi: 10.1183/09031936.02.01372002
pubmed: 12412693
Kaplan JE, Benson C, Holmes KK, et al. (2009) Guidelines for prevention and treatment of opportunistic infections in HIV-infected adults and adolescents: recommendations from CDC, the National Institutes of Health, and the HIV Medicine Association of the Infectious Diseases Society of America. MMWR Recomm Rep 58(RR-4):1–CE4
Catherinot E, Lanternier F, Bougnoux ME et al (2010) Pneumocystis jirovecii pneumonia. Infect Dis Clin North Am 24(1):107–138. https://doi.org/10.1016/j.idc.2009.10.010
doi: 10.1016/j.idc.2009.10.010
pubmed: 20171548