Main Article Content

Abstract

ABSTRACT


Background. Inflammation is associated with rapid deterioration of kidney function, increased cardiovascular risk, and high mortality. The objective of this study was to develop a predictive model for the progression of inflammatory markers according to the stages of kidney disease (KD) in Cameroonian patients. Methods. We conducted an analytical study in which we analyzed inflammatory markers—C-reactive protein (CRP), procalcitonin (PCT), white blood cells (WBC), and blood platelets (PLT)—in 561 patients with KD at various stages. A Random Forest model was used as the prediction model, and a Receiver Operating Characteristic -ROC- curve was plotted to assess the model’s performance using the Area Under the Curve -AUC-. The model was considered acceptable if AUC > 0.7. The results showed that CRP did not vary significantly across kidney disease stages  *p = 0.12*, unlike PCT *P < .001* and WBC count *P= .045*, which showed significant increases at advanced stages, suggesting their relevance as indicators of inflammation. Platelet count -PLT- remained relatively stable *P = .6*. Correlation analyses revealed a weak association between CRP and WBC *r = 0.116, P < .01*, as well as between PCT and WBC *r = 0.094, P< .05*, while CRP and PCT *r = 0.028* did not appear to reflect the same inflammatory mechanism. Finally, the predictive model built from these markers demonstrated excellent discriminative ability *AUC > 0.8*, indicating its reliability in distinguishing disease stages and predicting the progression of inflammatory markers. Conclusion. PCT and WBC are relevant indicators of inflammation in the advanced stages of kidney disease, making them reliable tools for assessing and predicting the progression of KD in Cameroonian patients.
RÉSUMÉ
Contexte. L'inflammation est associée à une détérioration rapide de la fonction rénale, à un risque cardiovasculaire accru et à une mortalité élevée. L'objectif de cette étude était de développer un modèle prédictif de la progression des marqueurs inflammatoires en fonction des stades de la maladie rénale (MR) chez des patients camerounais. Méthodes. Nous avons mené une étude analytique au cours de laquelle nous avons analysé des marqueurs inflammatoires - la protéine C-réactive (PCR), la procalcitonine (PCT), les globules blancs (GB) et les plaquettes sanguines (PLT) - chez 561 patients atteints de MR à différents stades. Un modèle de forêt aléatoire a été utilisé comme modèle de prédiction, et une courbe caractéristique de fonctionnement du récepteur (ROC) a été tracée pour évaluer la performance du modèle à l'aide de la surface sous la courbe (AUC). Le modèle a été considéré comme acceptable si l'AUC > 0,7. Résultats. Les résultats ont montré que la PCR ne variait pas de manière significative entre les stades de la maladie rénale (p = 0,12), contrairement à la PCT (P < 0,001) et au nombre de GB (P = 0,045), qui ont montré des augmentations significatives aux stades avancés, suggérant leur pertinence en tant qu'indicateurs d'inflammation. Le nombre de plaquettes (PLT) est resté relativement stable (P = 0,6). Les analyses de corrélation ont révélé une faible association entre la PCR et les GB (r = 0,116, P < 0,01), ainsi qu'entre la PCT et les GB (r = 0,094, P < 0,05), tandis que la PCR et la PCT (r = 0,028) ne semblaient pas refléter le même mécanisme inflammatoire. Enfin, le modèle prédictif construit à partir de ces marqueurs a démontré une excellente capacité discriminative (AUC > 0,8), indiquant sa fiabilité pour distinguer les stades de la maladie et prédire la progression des marqueurs inflammatoires. Conclusion. La PCT et les GB sont des indicateurs pertinents de l'inflammation aux stades avancés de la maladie rénale, ce qui en fait des outils fiables pour évaluer et prédire la progression de la MR chez des patients camerounais.

Keywords

Predictive model, Inflammatory markers, Kidney disease, Cameroonian : Modèle prédictif, Marqueurs inflammatoires, Maladie rénale, Camerounais

Article Details

How to Cite
Elimby Ngande Lionel Patrick Joel, Nguea Ndjame Arlette, & Fouda Menye Epouse Ebana Hermine Danielle. (2026). Development of a Predictive Model for the Progression of Inflammatory Markers According to the Stages of Kidney Disease in Cameroonian Patients: Développement d’un Modèle Prédictif pour la Progression des Marqueurs Inflammatoires Selon les Stades de la Maladie Rénale chez des Patients Camerounais. HEALTH SCIENCES AND DISEASE, 27(2). https://doi.org/10.5281/zenodo.18315555

References

  1. 1. Thaha M, Widiana IGR. The Role of Inflammation in Chronic Kidney Disease. Indones J Kidney Hypertens. 2019;2(3):4‑13. 3
  2. 2. Donate-Correa J, Ferri CM, Sánchez-Quintana F, Pérez-Castro A, González-Luis A, Martín-Núñez E, Mora-Fernández C, Navarro-González JF. Inflammatory Cytokines in Diabetic Kidney Disease: Pathophysiologic and Therapeutic Implications. Front Med 2021;7.
  3. 3. Bello AK, Okpechi IG, Levin A, Ye F, Damster S, Arruebo S, Donner JA, Caskey FJ, Cho Y, Davids MR, Davison SN, Htay H, Jha V, Lalji R, Malik C, Nangaku M, See E, Sozio SM, Tonelli M, Wainstein M, Yeung EK, Johnson DW, Abu-Alfa AK, Amouzegar A, Anand S, Arogundade FA, Ashuntantang GE, Bavanandan S, Coppo R, Diongole HM, Divyaveer S, Ekrikpo UE, Ethier I, Fung WWS, Gaipov A, Ghimire A, Houston G, Ibrahim KS, Irish G, Jindal K, Kelly DM, Lightstone L, Madero M, Nalado AM, Neuen BL, Olanrewaju TO, Osman MA, Parekh RS, Petrova A, Prasad N, Prikhodina L, Racki S, Riaz P, Saad S, Sakajiki AM, Savaj S, Shah DS, Suzuki Y, Tesar V, Tiv S, Tungsanga S, Tzanno-Martins C, Viecelli A, Wang AYM, Wong MG, Zaidi D. An update on the global disparities in kidney disease burden and care across world countries and regions. Lancet Glob Health 2024;12(3):e382‑95.
  4. 4. Prevalence and determinants of chronic kidney disease in urban adults’ populations of northern Cameroon: a cross-sectional study |
  5. 5. Kamdem F, Mapoure Y, Hamadou B, Souksouna F, Doualla MS, Jingi AM, Kenmegne C, Lekpa FK, Fenkeu JK, Imandy G, Mefo’o JPN, Luma H. Prevalence and risk factors of peripheral artery disease in black Africans with HIV infection: a cross-sectional hospital-based study. Vasc Health Risk Manag 2018;14:401‑8.
  6. 6. Stanifer JW, Jing B, Tolan S, Helmke N, Mukerjee R, Naicker S, Patel U. The epidemiology of chronic kidney disease in sub-Saharan Africa: a systematic review and meta-analysis. Lancet Glob Health 2014;2(3):e174‑81.
  7. 7. Patrice HM, Pascal KA, François KF, Hilaire D, Solange DM, Gloria AE, Pierre CS. Markers and risk factors for chronic kidney disease in sub-Saharan Africans: baseline levels and 12-month trajectories in newly referred patients in Cameroon. BMC Nephrol 2020 ;21(1):101.
  8. 8. Hill NR, Fatoba ST, Oke JL, Hirst JA, O’Callaghan CA, Lasserson DS, Hobbs FDR. Global Prevalence of Chronic Kidney Disease – A Systematic Review and Meta-Analysis. PLOS ONE 2016;11(7):e0158765.
  9. 9. Wayne PA. Clinical and laboratory standards institute (CLSI). Perform Stand Antimicrob Susceptibility Test. 2015;
  10. 10. Reinhart K, Meisner M, Brunkhorst FM. Markers for Sepsis Diagnosis: What is Useful? Crit Care Clin [Internet]. 1 juill 2006 [cité 14 mars 2025];22(3):503‑19.
  11. 11. Gregoriano C, Heilmann E, Molitor A, Schuetz P. Role of procalcitonin use in the management of sepsis. J Thorac Dis;12
  12. 12. Wayne PA. Clinical and laboratory standards institute (CLSI). Perform Stand Antimicrob Susceptibility Test. 2015;
  13. 13. Levin A, Stevens PE, Bilous RW, Coresh J, Francisco ALMD, Jong PED, Griffith KE, Hemmelgarn BR, Iseki K, Lamb EJ, Levey AS, Riella MC, Shlipak MG, Wang H, White CT, Winearls CG. Kidney disease: Improving global outcomes (KDIGO) CKD work group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease. Kidney Int Suppl 2013;3(1):1‑150.
  14. 14. Breiman L. Random Forests. Mach Learn 2001;45(1):5‑32.
  15. 15. DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric Approach. Biometrics. 1988 ;44(3):837‑45.
  16. 16. Biau G, Scornet E. Rejoinder on: A random forest guided tour. TEST 2016 ;25(2):264‑8.
  17. 17. Zhang T, Widdop RE, Ricardo SD. Transition from acute kidney injury to chronic kidney disease: mechanisms, models, and biomarkers. Am J Physiol Renal Physiol. 2024;327(5):F788‑805.
  18. 18. Pepys MB, Hirschfield GM. C-reactive protein: a critical update. J Clin Invest. juin 2003;111(12):1805‑12.
  19. 19. Akchurin OM, Kaskel F. Update on Inflammation in Chronic Kidney Disease. Blood Purif 2015 ;39(1‑3):84‑92.
  20. 20. Zhou HH, Tang YL, Xu TH, Cheng B. C-reactive protein: structure, function, regulation, and role in clinical diseases. Front Immunol. 2024;15:1425168.
  21. 21. van Dissel JT. Procalcitonin and other markers of infection. What should be their role in clinical practice? Clin Microbiol Infect Off Publ Eur Soc Clin Microbiol Infect Dis. févr 2002;8(2):70‑3.
  22. 22. Mantovani A, Dinarello CA, Molgora M, Garlanda C. Interleukin-1 and Related Cytokines in the Regulation of Inflammation and Immunity. Immunity. 16 avr 2019;50(4):778‑95.
  23. 23. Reinhart K, Meisner M, Brunkhorst FM. Markers for sepsis diagnosis: what is useful? Crit Care Clin. juill 2006;22(3):503‑19, ix‑x.
  24. 24. Biau G, Scornet E. A random forest guided tour. TEST 2016 ;25(2):197‑227.
  25. 25. Kaze FF, Meto DT, Halle MP, Ngogang J, Kengne AP. Prevalence and determinants of chronic kidney disease in rural and urban Cameroonians: a cross-sectional study. BMC Nephrol juill 2015;16(1):117.
  26. 26. 26. Kurts C, Ginhoux F, Panzer U. Kidney dendritic cells: fundamental biology and functional roles in health and disease. Nat Rev Nephrol ;16(7):391‑407.

Similar Articles

1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.