Skip to content
1887

Journal of Medical Microbiology logo Journal of Medical Microbiology

Volume 73, Issue 11

Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with infection: a single-centred retrospective study No Access

Abstract

() is a widely disseminated betaherpesvirus that typically induces latant infections. In immunocompromised populations, especially transplant and HIV-infected patients, infection increases in-hospital mortality.

Although machine learning models have been widely used in clinical diagnosis and prognosis prediction, reports on machine learning model predictions for the in-hospital mortality of HIV/AIDS patients with infection have not been reported.

Analyze the general gemographic and clinical characteristics of HIV/AIDS patients with infection and identify the factors affecting the prognosis of this population, which will help to reduce their in-hospital mortality.

Hospitalized HIV/AIDS patients with infection were recruited from the Fourth People’s Hospital of Nanning, Guangxi, from 2012 to 2019. After dividing them into survival and death groups based on their in-hospital survival status, their general and clinical profiles were described. Following 1 : 3 propensity score matching to equalize baseline characteristics, three machine-learning models (Random Forest, Support Vector Machine and eXtreme Gradient Boosting) were deployed to forecast factors influencing prognosis. The SHapley Additive exPlanations tool explained the models.

A total of 1102 HIV/AIDS patients with infection were analysed. There was no statistical difference in the general condition of the study subjects (＞0.05). Prevalent complications/coinfections included pneumonia (63.6%), (47.2%) and oral fungal infections (44.6%). There were significant differences between the groups in pneumonia, and hypoproteinaemia (<0.05). The differences in laboratory indicators between patients were also statistically significant (<0.05). The three machine learning models demonstrated good performance, identifying primary predictors of mortality. Pneumonia, urea, indirect bilirubin and platelet distribution width exhibited positive associations with death, with higher levels correlating with an increased mortality risk. Conversely, CD4 T-cell count, CD8 T-cell count and platelet displayed negative correlations with mortality.

HIV/AIDS patients with CMV infection exhibit distinctive clinical features impacting survival outcomes. Machine learning models accurately identify key influencing factors and predict mortality risk in this population, which appears to be essential to reducing in-hospital mortality.

  • Received:
  • Accepted:
  • Published Online:
Keyword(s): Cytomegalovirus , HIV/AIDS , machine learning models , mortality rate and prognosis
Funding
This study was supported by the:
  • Guangxi Medical University Training Program for Young Leading Talents（to Junjun Jiang)
    • Principal Award Recipient: JunjunJiang
© 2024 The Authors
Loading

Article metrics loading...

/content/journal/jmm/10.1099/jmm.0.001935
2024-11-28
2025-11-18

Metrics

Loading full text...

Full text loading...

References

  1. Ssentongo P, Hehnly C, Birungi P, Roach MA, Spady J et al. Congenital cytomegalovirus infection burden and epidemiologic risk factors in countries with universal screening: a systematic review and meta-analysis. JAMA Netw Open 2021; 4:e2120736 [View Article] [PubMed]
     [Google Scholar]
  2. Zuhair M, Smit GSA, Wallis G, Jabbar F, Smith C et al. Estimation of the worldwide seroprevalence of cytomegalovirus: a systematic review and meta-analysis. Rev Med Virol 2019; 29:e2034 [View Article] [PubMed]
     [Google Scholar]
  3. Griffiths PD. CMV as a cofactor enhancing progression of AIDS. J Clin Virol 2006; 35:489–492 [View Article] [PubMed]
     [Google Scholar]
  4. Webster A, Cook DG, Emery VC, Lee CA, Grundy JE et al. Cytomegalovirus infection and progression towards aids in haemophiliacs with human immunodeficiency virus infection[J]. Lancet 1989; 334:63–66 [View Article]
     [Google Scholar]
  5. Gianella S, Massanella M, Wertheim JO, Smith DM. The sordid affair between human herpesvirus and HIV. J Infect Dis 2015; 212:845–852 [View Article] [PubMed]
     [Google Scholar]
  6. Henrich TJ, Hobbs KS, Hanhauser E, Scully E, Hogan LE et al. Human immunodeficiency virus type 1 persistence following systemic chemotherapy for malignancy. J Infect Dis 2017; 216:254–262 [View Article] [PubMed]
     [Google Scholar]
  7. Gianella S, Anderson CM, Var SR, Oliveira MF, Lada SM et al. Replication of human herpesviruses is associated with higher HIV DNA levels during antiretroviral therapy started at early phases of HIV infection. J Virol 2016; 90:3944–3952 [View Article] [PubMed]
     [Google Scholar]
  8. Deayton JR, Sabin CA, Johnson MA, Emery VC, Wilson P et al. Importance of cytomegalovirus viraemia in risk of disease progression and death in HIV-infected patients receiving highly active antiretroviral therapy. Lancet 2004; 363:2116–2121 [View Article]
     [Google Scholar]
  9. Spector SA, Wong R, Hsia K, Pilcher M, Stempien MJ. Plasma cytomegalovirus (CMV) DNA load predicts CMV disease and survival in AIDS patients. J Clin Invest 1998; 101:497–502 [View Article] [PubMed]
     [Google Scholar]
  10. Schleiss MR, Bangdiwala AS, Skipper S et al. Cytomegalovirus viremia associated with increased mortality in cryptococcal meningitis in sub-saharan africa. Clin Infect Dis 2020; 71(3):525–531 [View Article] [PubMed]
     [Google Scholar]
  11. Fielding K, Koba A, Grant AD, Charalambous S, Day J et al. Cytomegalovirus viremia as a risk factor for mortality prior to antiretroviral therapy among hiv-infected gold miners in South Africa. PLoS One 2011; 6:e25571 [View Article]
     [Google Scholar]
  12. Mayaphi SH, Brauer M, Morobadi DM, Mazanderani AH, Mafuyeka RT et al. Cytomegalovirus viral load kinetics in patients with hiv/aids admitted to a medical intensive care unit: a case for pre-emptive therapy. PLoS One 2014; 9:e93702 [View Article]
     [Google Scholar]
  13. Evans C, Mutasa K, Rukobo S, Govha M, Mushayanembwa P et al. Inflammation and cytomegalovirus viremia during pregnancy drive sex-differentiated differences in mortality and immune development in HIV-exposed infants. Nat Commun 2024; 15:2909 [View Article]
     [Google Scholar]
  14. Obermeyer Z, Emanuel EJ. Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med 2016; 375:1216–1219 [View Article] [PubMed]
     [Google Scholar]
  15. Rajkomar A, Oren E, Chen K, Dai AM, Hajaj N et al. Scalable and accurate deep learning with electronic health records. NPJ Digital Med 2018; 1:18 [View Article]
     [Google Scholar]
  16. Abdar M, Książek W, Acharya UR, Tan R-S, Makarenkov V et al. A new machine learning technique for an accurate diagnosis of coronary artery disease. Comput Methods Programs Biomed 2019; 179:104992 [View Article] [PubMed]
     [Google Scholar]
  17. Mayampurath A, Ajith A, Anderson-Smits C, Chang S-C, Brouwer E et al. Early diagnosis of primary immunodeficiency disease using clinical data and machine learning. J Allergy Clin Immunol Pract 2022; 10:3002–3007 [View Article] [PubMed]
     [Google Scholar]
  18. Heo J, Yoon JG, Park H, Kim YD, Nam HS et al. Machine learning–based model for prediction of outcomes in acute stroke. Stroke 2019; 50:1263–1265 [View Article]
     [Google Scholar]
  19. De Filippo O, Cammann VL, Pancotti C, Di Vece D, Silverio A et al. Machine learning‐based prediction of in‐hospital death for patients with takotsubo syndrome: the InterTAK‐ML model. European J of Heart Fail 2023; 25:2299–2311 [View Article]
     [Google Scholar]
  20. Ge J, Xu Y. Internal medical[M], 8th. edn Beijing: People’s Medical Publishing House; 2015
     [Google Scholar]
  21. Binquet C, Saillour F, Bernard N, Rougier M-B, Leger F et al. Prognostic factors of survival of hiv-infected patients with cytomegalovirus disease: aquitaine cohort, 1986-1997. groupe d’epidémiologie clinique du sida en aquitaine (gecsa)[J]. Eur J Epidemiol 2000; 16:425–432 [View Article]
     [Google Scholar]
  22. Gianella S, Letendre S. Cytomegalovirus and hiv: a dangerous pas de deux[J]. J Infect Dis 2016; 214 Suppl 2:S67–74 [View Article]
     [Google Scholar]
  23. Ruffini DD, Madhi SA. The high burden of Pneumocystis carinii pneumonia in African HIV-1-infected children hospitalized for severe pneumonia. AIDS 2002; 16:105–112 [View Article]
     [Google Scholar]
  24. Goussard P, Kling S, Gie RP, Nel ED, Heyns L et al. CMV pneumonia in HIV‐infected ventilated infants. Pediatr Pulmonol 2010; 45:650–655 [View Article]
     [Google Scholar]
  25. Chintu C, Mudenda V, Lucas S, Nunn A, Lishimpi K et al. Lung diseases at necropsy in African children dying from respiratory illnesses: a descriptive necropsy study. Lancet 2002; 360:985–990 [View Article]
     [Google Scholar]
  26. Zampoli M, Morrow B, Hsiao N-Y, Whitelaw A, Zar HJ. Prevalence and outcome of cytomegalovirus-associated pneumonia in relation to human immunodeficiency virus infection. Pediatr Infect Dis J 2011; 30:413–417 [View Article]
     [Google Scholar]
  27. Rucar A, Totet A, Le Govic Y, Demey B, Damiani C. Pulmonary co-infections by Pneumocystis jirovecii and Herpesviridae: a seven-year retrospective study. Ann Clin Microbiol Antimicrob 2024; 23:8 [View Article] [PubMed]
     [Google Scholar]
  28. González-Quijada S, del Álamo-Martínez de Lagos M, Álvarez-Llabrés M, Pérez-González L. Cytomegalovirus antibody levels and mortality among hospitalised elderly patients. Ann Med 2020; 52:497–505 [View Article]
     [Google Scholar]
  29. Clift AK, Dodwell D, Lord S, Petrou S, Brady M et al. Development and internal-external validation of statistical and machine learning models for breast cancer prognostication: cohort study. BMJ 2023; 381:e073800 [View Article]
     [Google Scholar]
  30. Tang F, Xue C, Law MY, Wong C, Cho T et al. Prognostic prediction of cancer based on radiomics features of diagnostic imaging: the performance of machine learning strategies. J Digit Imaging 2023; 36:1081–1090 [View Article]
     [Google Scholar]
  31. Maurya NS, Kushwah S, Kushwaha S, Chawade A, Mani A. Prognostic model development for classification of colorectal adenocarcinoma by using machine learning model based on feature selection technique boruta. Sci Rep 2023; 13:6413 [View Article] [PubMed]
     [Google Scholar]
  32. Srisuriyajan P, Cheewaruangroj N, Polpinit P, Laovirojjanakul W. Cytomegalovirus retinitis screening using machine learning technology. Retina 2022; 42:1709–1715 [View Article]
     [Google Scholar]
  33. Szczawińska-Popłonyk A, Jończyk-Potoczna K, Ossowska L, Bręborowicz A, Bartkowska-Śniatkowska A et al. Cytomegalovirus pneumonia as the first manifestation of severe combined immunodeficiency. Cent Eur J Immunol 2014; 39:392–395 [View Article] [PubMed]
     [Google Scholar]
  34. Skipper CP, Hullsiek KH, Cresswell FV, Tadeo KK, Okirwoth M et al. Cytomegalovirus viremia as a risk factor for mortality in HIV-associated cryptococcal and tuberculous meningitis. Int J Infect Dis 2022; 122:785–792 [View Article] [PubMed]
     [Google Scholar]
  35. Shi M, Lin J, Wei W, Qin Y, Meng S et al. Machine learning-based in-hospital mortality prediction of HIV/AIDS patients with Talaromyces marneffei infection in Guangxi, China. PLoS Negl Trop Dis 2022; 16:e0010388 [View Article] [PubMed]
     [Google Scholar]
  36. Gabanti E, Lilleri D, Ripamonti F, Bruno F, Zelini P et al. Reconstitution of human cytomegalovirus–specific CD4 + T cells is critical for control of virus reactivation in hematopoietic stem cell transplant recipients but does not prevent organ infection. Biol Blood Marrow Transplant 2015; 21:2192–2202 [View Article]
     [Google Scholar]
  37. Tu W, Chen S, Sharp M, Dekker C, Manganello AM et al. Persistent and selective deficiency of CD4+ T cell immunity to cytomegalovirus in immunocompetent young children. J Immunol 2004; 172:3260–3267 [View Article] [PubMed]
     [Google Scholar]
  38. Sester M, Sester U, Gartner B, Heine G, Girndt M et al. Levels of virus-specific cd4 t cells correlate with cytomegalovirus control and predict virus-induced disease after renal transplantation1. Transplantation 2001; 71:1287–1294 [View Article]
     [Google Scholar]
  39. Lee SA, Sinclair E, Jain V, Huang Y, Epling L et al. Low proportions of CD28- CD8+ T cells expressing CD57 can be reversed by early ART initiation and predict mortality in treated HIV infection. J Infect Dis 2014; 210:374–382 [View Article] [PubMed]
     [Google Scholar]
  40. Haile K, Timerga A, Alemayehu M, Mose A. Diagnostic utility of haematological parameters in predicting the severity of HIV infection in southwestern Ethiopia: a comparative cross-sectional study. BMJ Open 2023; 13:e072678 [View Article] [PubMed]
     [Google Scholar]
  41. Awamura T, Nakasone ES, Gangcuangco LM, Subia NT, Bali A-J et al. Platelet and HIV interactions and their contribution to non-aids comorbidities. Biomolecules 2023; 13:1608 [View Article] [PubMed]
     [Google Scholar]
  42. Solomon Tsegaye T, Gnirß K, Rahe-Meyer N, Kiene M, Krämer-Kühl A et al. Platelet activation suppresses HIV-1 infection of T cells. Retrovirology 2013; 10:48 [View Article] [PubMed]
     [Google Scholar]
  43. Pretorius E. Platelets in HIV: a guardian of host defence or transient reservoir of the virus?. Front Immunol 2021; 12:649465 [View Article] [PubMed]
     [Google Scholar]
/content/journal/jmm/10.1099/jmm.0.001935
Loading
Machine learning-driven in-hospital mortality prediction in HIV/AIDS patients with Cytomegalovirus infection: a single-centred retrospective study
J. Med. Microbiol. 73, 001935 (2024); https://doi.org/10.1099/jmm.0.001935
/content/journal/jmm/10.1099/jmm.0.001935
/content/journal/jmm/10.1099/jmm.0.001935
Loading

Data & Media loading...

Supplements

Supplementary material 1

EXCEL

Most cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An error occurred
Approval was partially successful, following selected items could not be processed due to error