Skip to main content
SpringerLink
Log in

Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values

  • Original Article
  • Published:
Inflammopharmacology Aims and scope Submit manuscript

Abstract

Background

Haemoperfusion (HP) is an innovative extracorporeal therapy that utilizes special cartridges to filter the blood, effectively removing pro-inflammatory cytokines, toxins, and pathogens in COVID-19 patients. This retrospective cohort study aimed to assess the clinical benefits of HP for severe COVID-19 cases using Shapley values for machine learning models.

Methods

The research involved 578 inpatients (≥ 20 years old) admitted to Baqiyatallah hospital (Tehran, Iran). The control group (359 patients) received standard treatment, including high doses of corticosteroids (a single 500 mg methylprednisolone pulse, followed by 250 mg for 2 days), categorized as regimen (I). On the other hand, the HP group (219 patients) received regimen II, consisting of the same corticosteroid treatment (regimen I) along with haemoperfusion using Cytosorb H300. The frequency of haemoperfusion sessions varied based on the type of lung involvement determined by chest CT scans. In addition, the value function \({\text{v}}\) defines the Shapley value of the \(i\)th feature for the query point \({\text{x}}\), where the input matrix features represent individual characteristics, drugs, and history and clinical conditions of the patient.

Results

Our data showed a favorable clinical response in the HP group compared to the control group. Notably, one-to-three sessions of HP using the CytoSorb® 300 cartridge led to reduced ventilation requirements and mortality rates in severe COVID-19 patients. Shapley values were calculated to evaluate the contribution of haemoperfusion among other factors, such as side effects, medications, and individual characteristics, to COVID-19 patient outcomes. In addition, there is a significant difference between the two groups among the treatments and medications used remdesivir, adalimumab, tocilizumab, favipiravir, Interferon beta-1a, enoxaparin prophylaxis, enoxaparin full dose, heparin prophylaxis, and heparin full dose (P < 0.05).

It seems that haemoperfusion has a positive impact on the reduction of inflammation markers and renal functional such as ferritin and creatinine, respectively, as well as d-dimer and WBC levels in the HP group were significantly lower than the control group.

Conclusion

The findings indicated that haemoperfusion played a crucial role in predicting patient survival, making it a significant feature in classifying patients' prognoses.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2.
Fig. 3

Similar content being viewed by others

Availability of data and materials

The datasets used and/or analyzed during the current study are available from the corresponding authors on reasonable request.

References

  • Abbasi S, Naderi Z, Amra B, Atapour A, Dadkhahi SA, Eslami MJ, Hajian MR, Hashemi M, Hashemi ST, Iraj B, Khorvash F, Madadi S, Pour HM, Mansourian M, Rezvani M, Sami R, Soltaninejad F, Shahidi S, Vahdat S, Zamani Z, Moeinzadeh F (2021) Haemoperfusion in patients with severe COVID-19 respiratory failure, lifesaving or not? J Res Med Sci 27(26):34. https://doi.org/10.4103/jrms.JRMS_1122_20. (PMID:34345245; PMCID:PMC8305775)

    Article  Google Scholar 

  • Abedian M, Hejazi M (2023) Optimal strategy selection under fuzzy environment for strategic planning methodology selection: an SWOT approach. Cybern Syst. https://doi.org/10.1080/01969722.2023.2166255

    Article  Google Scholar 

  • Balas RB, Meliț LE, Mărginean CO (2023) COVID-19 and cardiac implications: still a mystery in clinical practice. Rev Cardiovasc Med 24(5):125

    Article  Google Scholar 

  • Bui TN, Ngo HA, Huynh NM, Do-Tran NH, Le LD, Nguyen TA (2022) High-dose methylprednisolone pulse therapy for the treatment of patients with severe COVID-19: results from a prospective observational study. J Intensive Med 2(03):197–198

    Article  PubMed  PubMed Central  Google Scholar 

  • Cao X (2020) COVID-19: immunopathology and its implications for therapy. Nat Rev Immunol 20(5):269–270

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Cegolon L, Einollahi B, Panahi Y, Imanizadeh S, Rezapour M, Javanbakht M, Mastrangelo G (2022b) On therapeutic plasma exchange against severe COVID-19-associated pneumonia: an observational clinical study. Front Nutr 9:809823

    Article  PubMed  PubMed Central  Google Scholar 

  • Cegolon L, Einollahi B, Panahi Y, Imanizadeh S, Rezapour M, Javanbakht M, Mastrangelo G (2022) On the efficacy of therapeutic plasma exchange against severe COVID-19 pneumonia: a clinical observational study. J Clin Immunol

  • Chen S et al (2023) Advances in attractive therapeutic approach for macrophage activation syndrome in COVID-19. Front Immunol. https://doi.org/10.3389/fimmu.2023.1200289

    Article  PubMed  PubMed Central  Google Scholar 

  • Cutuli SL et al (2023) Antimicrobial exposure in critically ill patients with sepsis-associated multi-organ dysfunction requiring extracorporeal organ support: a narrative review. Microorganisms 11(2):473

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Dastan F, Saffaei A, Mortazavi SM, Jamaati H, Adnani N, Samiee Roudi S, Hashemian SM (2020) Continues renal replacement therapy (CRRT) with disposable haemoperfusion cartridge: a promising option for severe COVID-19. J Glob Antimicrob Resist 21:340–341

    Article  PubMed  PubMed Central  Google Scholar 

  • Elwan TH et al (2023) Unveiling the role of inflammatory mediators and gut microbiome in appendicitis: types and applications in clinical scoring. Adv Gut Microbiome Res 2023:1–12

    Article  Google Scholar 

  • Esmaeili Vardanjani A, Ronco C, Rafiei H, Golitaleb M, Pishvaei MH, Mohammadi M (2021) Early haemoperfusion for cytokine removal may contribute to prevention of intubation in patients infected with COVID-19. Blood Purif 50(2):257–260

    Article  CAS  PubMed  Google Scholar 

  • Ghaleh HEG, Izadi M, Javanbakht M, Ghanei M, Einollahi B, Jafari NJ, Alvanagh AG (2023) Cytokine profile and antioxidants status in the moderate and severe COVID-19 patients: a trial of ozone therapy impact as a medicinal supplement. Inflammopharmacology 31(6):3029–3036

    Article  CAS  PubMed  Google Scholar 

  • Han H, Ma Q, Li C, Liu R, Zhao L, Wang W, Xia Y (2020) Profiling serum cytokines in COVID-19 patients reveals IL-6 and IL-10 are disease severity predictors. Emerg Microbes Infect 9(1):1123–1130

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Hsu CY, Rheima AM, Kadhim MM, Ahmed NN, Mohammed SH, Abbas FH, Kianfar E (2023) An overview of nanoparticles in drug delivery: properties and applications. South Afr J Chem Eng 46:233–270

    Article  Google Scholar 

  • Huang C, Wang Y, Li X, Ren L, Zhao J, Hu Y, Cao B (2020) Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China. The Lancet 395(10223):497–506

    Article  CAS  Google Scholar 

  • Jacques-Aviñó C et al (2020) Gender-based approach on the social impact and mental health in Spain during COVID-19 lockdown: a cross-sectional study. BMJ Open 10(11):e044617

    Article  PubMed  Google Scholar 

  • Ju H et al (2023) Recent trends in anti-cancer activities of terrestrial plants-based polysaccharides: a review. Carbohydr Polym Technol Appl 6:100341

    CAS  Google Scholar 

  • Kianfar E (2021a) Magnetic nanoparticles in targeted drug delivery: a review. J Supercond Novel Magn 34(7):1709–1735

    Article  CAS  Google Scholar 

  • Kianfar E (2021b) Protein nanoparticles in drug delivery: animal protein, plant proteins and protein cages, albumin nanoparticles. J Nanobiotechnol 19(1):159

    Article  CAS  Google Scholar 

  • Li M et al (2023) An order-invariant and interpretable dilated convolution neural network for chemical process fault detection and diagnosis. IEEE Trans Autom Sci Eng. https://doi.org/10.1109/TASE.2023.3290202

    Article  Google Scholar 

  • Long X et al (2023) Identifying the evolution of primary oxidation mechanisms and pollutant degradation routes in the electro-cocatalytic Fenton-like systems. J Hazard Mater 445:130577

    Article  CAS  PubMed  Google Scholar 

  • Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. Advances in neural information processing systems

  • Maity S et al (2023) Targeting cytokine storm as the potential anti-viral therapy: Implications in regulating SARS-CoV-2 pathogenicity. Gene 881:147612

    Article  CAS  PubMed  Google Scholar 

  • Majeed AY, Zulkafli NES, Ad’hiah AH (2023) Serum profiles of pro-inflammatory and anti-inflammatory cytokines in non-hospitalized patients with mild/moderate COVID-19 infection. Immunol Lett 260:24–34

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • McElvaney OJ, McEvoy NL, McElvaney OF, Carroll TP, Murphy MP, Dunlea DM, McElvaney NG (2020) Characterization of the inflammatory response to severe COVID-19 illness. Am J Respir Crit Care Med 202(6):812–821

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Molaei H, Shojaeefar E, Nemati E, Khedmat L, Mojtahedi SY, Jonaidi Jafari N, Einollahi B (2022) Iranian patients co-infected with COVID-19 and mucormycosis: the most common predisposing factor, clinical outcomes, laboratory markers and diagnosis, and drug therapies. Infect Dis 54(8):600–613

    Article  CAS  Google Scholar 

  • Morsy MI et al (2021) A novel LC-MS/MS method for determination of the potential antiviral candidate favipiravir for the emergency treatment of SARS-CoV-2 virus in human plasma: Application to a bioequivalence study in Egyptian human volunteers. J Pharm Biomed Anal 199:114057

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Nayebi A et al (2023) WindowSHAP: an efficient framework for explaining time-series classifiers based on Shapley values. J Biomed Inform 144:104438

    Article  PubMed  Google Scholar 

  • Ni R et al (2023) Biologic mechanisms of macrophage phenotypes responding to infection and the novel therapies to moderate inflammation. Int J Mol Sci 24(9):8358

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Olsen LHB et al (2023), A comparative study of methods for estimating conditional Shapley values and when to use them. arXiv preprint arXiv:2305.09536

  • Onuk S et al (2023) Cytokine levels and severity of illness scoring systems to predict mortality in COVID-19 infection. Healthcare 11(3):387

    Article  PubMed  PubMed Central  Google Scholar 

  • Pan F et al (2020a) Time course of lung changes at chest CT during recovery from coronavirus disease 2019 (COVID-19). Radiology 295(3):715–721

    Article  PubMed  Google Scholar 

  • Pan F, Ye T, Sun P, Gui S, Liang B, Li L, Zheng C (2020b) Time course of lung changes at chest CT during recovery from coronavirus disease 2019 (COVID-19). Radiology 295(3):715–721

    Article  PubMed  Google Scholar 

  • Panahi Y, Einollahi B, Beiraghdar F, Darvishi M, Fathi S, Javanbakht M, Akhavan-Sigari R (2022) Fully understanding the efficacy profile of the COVID-19 vaccination and its associated factors in multiple real-world settings. Front Immunol 13:947602

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Pham K et al (2023) Machine learning-based pedotransfer functions to predict soil water characteristics curves. Transp Geotech 42:101052

    Article  Google Scholar 

  • Reddy S et al (2023) Predicting swarm equatorial plasma bubbles via machine learning and Shapley values. J Geophys Res: Space Phys. https://doi.org/10.1029/2022JA031183

    Article  Google Scholar 

  • Ronco C, Bellomo R (2022) Haemoperfusion: technical aspects and state of the art. Crit Care 26(1):1–12

    Article  Google Scholar 

  • Rostami Z, Futuhi F, Nemati E, Najafabadi AS, Javanbakht M, Ebrahimi M, Einollahi B (2022a) Dialysis during the COVID-19 pandemic: experiences from 4 dialysis centers in Iran. Nephro-Urol Mon. https://doi.org/10.5812/numonthly-127290

    Article  Google Scholar 

  • Rostami Z, Mastrangelo G, Einollahi B, Nemati E, Shafiee S, Ebrahimi M, Cegolon L (2022b) A prospective study on risk factors for acute kidney injury and all-cause mortality in hospitalized COVID-19 patients from Tehran (Iran). Front Immunol 13:874426

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Sayyadi M et al (2023) Status of major hemostatic components in the setting of COVID-19: the effect on endothelium, platelets, coagulation factors, fibrinolytic system, and complement. Ann Hematol 102(6):1307–1322

    Article  PubMed  PubMed Central  Google Scholar 

  • Selvaraj V et al (2021) Tocilizumab in hospitalized patients with COVID-19: a meta analysis of randomized controlled trials. Lung 199(3):239–248

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Smith M, Alvarez F (2021) Identifying mortality factors from Machine Learning using Shapley values - a case of COVID19. Expert Syst Appl 176:114832. https://doi.org/10.1016/j.eswa.2021.114832. (PMID: 33723478; PMCID: PMC7948528)

    Article  PubMed  PubMed Central  Google Scholar 

  • Soleimani A, Taba SMM, Hasibi Taheri S, Loghman AH, Shayestehpour M (2021a) The effect of haemoperfusion on the outcome, clinical and laboratory findings of patients with severe COVID-19: a retrospective study. New Microbes New Infect 44:100937. https://doi.org/10.1016/j.nmni.2021.100937. (PMID: 34490065; PMCID: PMC8410636)

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Tim Y et al (2023) Design process knowledge for crisis-driven information systems solutions: Insights on building digital resilience from an action design research study. Inf Syst J. https://doi.org/10.1111/isj.12457

    Article  Google Scholar 

  • Tlemsani I, Matthews R, Mohamed Hashim MA (2023) Revisiting Zakat with a distribution of weighted Shapley value. Int J Islam Middle East Financ Manag 16(6):1141–1158

    Google Scholar 

  • Winchester JF (2002) Dialysis and haemoperfusion in poisoning. Adv Ren Replace Ther 9(1):26–30

    Article  PubMed  Google Scholar 

  • Zhang C, Wu Z, Li JW, Zhao H, Wang GQ (2020) Cytokine release syndrome in severe COVID-19: interleukin-6 receptor antagonist tocilizumab may be the key to reduce mortality. Int J Antimicrob Agents 55(5):105954

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Zhang G, Su L, Wu W, Qiao Q, Gao S, Zhang Y, Zhang Y (2024) Efficacy of different doses of corticosteroids in treating severe COVID-19 pneumonia. Virol J 21(1):74

    Article  PubMed  PubMed Central  Google Scholar 

  • Zhu B et al (2021) Correlation between white blood cell count at admission and mortality in COVID-19 patients: a retrospective study. BMC Infect Dis 21:1–5

    Article  Google Scholar 

Download references

Acknowledgements

Thanks to guidance and advice from “Clinical Research Development Unit of Baqiyatallah Hospital".

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Nephrology and Urology Research Center, Clinical Science Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran

    Behzad Einollahi, Mohammad Javanbakht, Mehrdad Ebrahimi, Mohammad Ahmadi, Zahra Einollahi & Bentolhoda Beyram

  2. Biomedical Engineering Research Center, Clinical Science Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran

    Abolfazl Mirani & Ehsan Kianfar

  3. Health Research Center, Life Style Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran

    Morteza Izadi

  4. Department of Nephrology, Shahid Hasheminejad Kidney Center, School of Medicine, Iran University of Medical Sciences, Tehran, Iran

    Sholeh Ghasemi

Authors
  1. Behzad Einollahi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohammad Javanbakht
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mehrdad Ebrahimi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mohammad Ahmadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Morteza Izadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sholeh Ghasemi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Zahra Einollahi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Bentolhoda Beyram
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Abolfazl Mirani
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Ehsan Kianfar
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors’ participated design the study, performed the experiments, analyzed the results, and wrote the manuscript. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Behzad Einollahi, Abolfazl Mirani or Ehsan Kianfar.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval and consent to participate

This study was conducted according to the guidelines laid down in the Declaration of Helsinki, and all procedures involving research study participants were outlined in the study protocols approved by the Baqiyatallah Universities of Medical Science. This trial was also approved by the Independent Ethics Committees of University (The trial number, IR.BMSU.IRCT.1399.447). Written informed consent was obtained from all the participants.

Consent to publication

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Einollahi, B., Javanbakht, M., Ebrahimi, M. et al. Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values. Inflammopharmacol (2024). https://doi.org/10.1007/s10787-024-01494-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10787-024-01494-z

Keywords

Search

Navigation