An Explainable PCA-XGBoost Model for Predicting Bloodstream Infection in Hemodialysis Patients
DOI:
https://doi.org/10.63158/journalisi.v8i4.1694Keywords:
Bloodstream Infection, Hemodialysis, XGBoost, PCA, SHAP, Explainable AIAbstract
Bloodstream infection (BSI) is a life-threatening complication in hemodialysis (HD) patients with catheter-based vascular access, carrying mortality rates of 15–50%, yet early detection remains challenging due to high-dimensional clinical data with significant multicollinearity. This study develops a BSI prediction model integrating Principal Component Analysis (PCA), XGBoost, Synthetic Minority Oversampling Technique (SMOTE), and dual Explainable AI (XAI) methods to improve predictive performance and clinical transparency. A dataset of 391 HD patients (18.9% BSI-positive) was preprocessed with encoding, standardization, and median imputation. PCA reduced 37 features to 29 components retaining 95.0% variance; SMOTE was applied inside each cross-validation fold to prevent leakage; and hyperparameters were optimized via RandomizedSearchCV. The proposed model achieved 83.5% accuracy, 33.3% recall, 43.5% F1-score, 85.5% AUC-ROC, and 0.643 PR-AUC, outperforming the baseline (81.0% accuracy, 0.0% recall, 0.190 PR-AUC). Bootstrap 95% confidence intervals and Brier score calibration are reported; results require cautious interpretation given the small positive test set (n=15). SHAP and LIME identified PC1 (hematological parameters) and PC2 (inflammatory markers) as dominant predictors. This study explores PCA, XGBoost, and dual XAI integration for BSI prediction in HD patients, an approach not extensively examined in this context. External multicenter prospective validation is required before clinical deployment.
Downloads
References
[1] O. Remez-Gabay, F. Y. A. Vdovich, G. Barbara, J. Jiries, and E. Kruzel-Davila, "Hemodiafiltration Attenuates NETosis Compared With High-Flux Hemodialysis in End-Stage Kidney Disease Patients," Kidney Int. Rep., vol. 10, no. 9, pp. 3070–3080, Sep. 2025. doi: 10.1016/j.ekir.2025.06.002.
[2] W. C. Lok, A. K. Bhatt, D. Bhave, J. E. Aruny, L. A. D. B. Silva, S. O. Trerotola, and G. A. Beathard, "Vascular Access: 2019 Clinical Practice Guideline from the American Society of Diagnostic and Interventional Nephrology and the Society of Interventional Radiology," J. Vasc. Access, vol. 21, no. 1_suppl, pp. 1–248, Jan. 2020. doi: 10.1177/1129729819897865.
[3] A. Ababneh, M. Al Domi, and A. M. Rababa'h, "Antimicrobial use and mortality among ICU patients with bloodstream infections," Heliyon, vol. 8, no. 8, p. e10076, Aug. 2022. doi: 10.1016/j.heliyon.2022.e10076.
[4] R. Murri, M. Taccari, V. Camici, F. C. S. M. A. D. Francesco, R. M. R. G. M. C. M. Fantoni, and F. L. V. M. M. R. M. G. S. T. M. A. M. Cauda, "A Machine Learning Predictive Model of Bloodstream Infection in Hospitalized Patients," Diagnostics, vol. 14, no. 4, p. 445, Feb. 2024. doi: 10.3390/diagnostics14040445.
[5] C. Wang, G. Wang, Y. Wang, and Y. Wang, "Development and evaluation of a model for predicting the risk of healthcare-associated infections in ICU," Front. Public Health, vol. 12, pp. 1–10, Dec. 2024. doi: 10.3389/fpubh.2024.1444176.
[6] Y. Luo, X. Chen, Y. Zhang, H. Li, J. Wang, and Q. Huang, "Development and validation of an interpretable machine learning model for predicting in-hospital mortality for ischemic stroke patients in ICU," Int. J. Med. Inform., vol. 198, p. 105874, Jun. 2025. doi: 10.1016/j.ijmedinf.2025.105874.
[7] Alamsyah and T. Fadila, "Increased accuracy of prediction hepatitis disease using PCA on a support vector machine," J. Phys.: Conf. Ser., vol. 1968, no. 1, Jul. 2021. doi: 10.1088/1742-6596/1968/1/012016.
[8] L. Mochurad, V. Babii, Y. Boliubash, and Y. Mochurad, "Improving stroke risk prediction by integrating XGBoost, optimized PCA, and XAI," BMC Med. Inform. Decis. Mak., vol. 25, no. 1, 2025. doi: 10.1186/s12911-025-02894-z.
[9] Y. Peng, S. Zhong, X. Li, F. Yu, and Z. Tang, "An artificial intelligence model to predict mortality among hemodialysis patients," Comput. Biol. Med., vol. 168, p. 107764, Jan. 2025. doi: 10.1016/j.compbiomed.2025.107764.
[10] T. Zhou, Z. Ren, Y. Ma, L. He, J. Liu, J. Tang, and H. Zhang, "Early identification of bloodstream infection in hemodialysis patients by machine learning," Heliyon, vol. 9, no. 7, p. e18263, Jul. 2023. doi: 10.1016/j.heliyon.2023.e18263.
[11] T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, San Francisco, CA, USA, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
[12] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002. doi: 10.1613/jair.953.
[13] S. M. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions," in Advances in Neural Information Processing Systems, vol. 30, Long Beach, CA, USA, Dec. 2017, pp. 4765–4774.
[14] M. T. Ribeiro, S. Singh, and C. Guestrin, "'Why Should I Trust You?': Explaining the Predictions of Any Classifier," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, San Francisco, CA, USA, Aug. 2016, pp. 1135–1144. doi: 10.1145/2939672.2939778.
[15] G. S. Collins, J. B. Reitsma, D. G. Altman, and K. G. M. Moons, "Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD): The TRIPOD Statement," Ann. Intern. Med., vol. 162, no. 1, pp. 55–63, Jan. 2015. doi: 10.7326/M14-0697.
[16] G. S. Collins, K. G. M. Moons, J. A. Dhiman, S. G. F. S. R. Reitsma, R. D. Riley, and D. G. Altman, "PROBAST: A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies," Ann. Intern. Med., vol. 170, no. 1, pp. 51–58, Jan. 2019. doi: 10.7326/M18-1376.
[17] J. Davis and M. Goadrich, "The Relationship Between Precision-Recall and ROC Curves," in Proc. 23rd Int. Conf. Mach. Learn., Pittsburgh, PA, USA, Jun. 2006, pp. 233–240. doi: 10.1145/1143844.1143874.
[18] M. A. Loc, F. Renard, L. Fiedler, B. Marg, J. Renn, and D. Faller, "Catheter-Related Bloodstream Infections in Patients on Long-Term Hemodialysis: Epidemiology, Risk Factors, and Prevention Strategies," J. Clin. Med., vol. 12, no. 5, p. 1793, Mar. 2023. doi: 10.3390/jcm12051793.
[19] E. W. Steyerberg, A. J. Vickers, N. R. Cook, T. A. Gerds, M. Gonen, N. Obuchowski, M. J. Pencina, and M. W. Kattan, "Assessing the performance of prediction models: a framework for some traditional and novel measures," Epidemiology, vol. 21, no. 1, pp. 128–138, Jan. 2010. doi: 10.1097/EDE.0b013e3181c30fb2.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
