Machine Learning Prediction of Low Quality of Life in Patients With Chronic Kidney Disease Using XGBoost and Explainable Artificial Intelligence
Keywords:
Chronic kidney disease, quality of life, machine learning, XGBoost, explainable artificial intelligence, SHAP, predictive modelingAbstract
Objective: This study aimed to predict low quality of life among patients with chronic kidney disease using the XGBoost machine learning algorithm and to identify the most important predictors through SHAP-based explainable artificial intelligence analysis.
Methods and Materials: This cross-sectional predictive modeling study was conducted among 426 patients with chronic kidney disease in Tehran, Iran. Data were collected using a demographic and clinical information checklist, medical record data, laboratory indicators, and the Kidney Disease Quality of Life questionnaire. Low quality of life was defined as a total quality-of-life score below 50 and was used as the binary outcome variable. After data preprocessing, missing-value management, and encoding of categorical variables, the dataset was divided into training and testing sets. Logistic regression, support vector machine, random forest, and XGBoost models were developed and compared. Five-fold cross-validation and hyperparameter tuning were applied to optimize model performance. The final model was interpreted using SHAP values to determine global and patient-level feature importance.
Findings: Patients with low quality of life had significantly longer disease duration, lower estimated glomerular filtration rate, higher dialysis frequency, longer dialysis duration, more comorbidities, greater medication burden, lower hemoglobin, lower serum albumin, higher serum phosphorus, and higher serum creatinine levels than patients without low quality of life (p < 0.05). Among the evaluated models, XGBoost showed the strongest predictive performance, with accuracy of 0.847, sensitivity of 0.829, specificity of 0.860, precision of 0.806, F1-score of 0.817, and area under the receiver operating characteristic curve of 0.912. SHAP analysis identified burden of kidney disease score, serum albumin, hemoglobin, estimated glomerular filtration rate, number of comorbidities, dialysis status, disease duration, serum phosphorus, cardiovascular disease, and number of prescribed medications as the most influential predictors.
Conclusion: The XGBoost model demonstrated strong and interpretable performance in predicting low quality of life among patients with chronic kidney disease, and SHAP analysis showed that patient-reported burden, renal function, anemia, nutritional status, comorbidity load, and treatment-related factors jointly contributed to risk prediction.
Downloads
References
Abe, M., Hatta, T., Imamura, Y., Sakurada, T., & Kaname, S. (2025). Examine the Optimal Multidisciplinary Care Teams for Patients With Chronic Kidney Disease From a Nationwide Cohort Study. Kidney Research and Clinical Practice, 44(2), 249-264. https://doi.org/10.23876/j.krcp.23.026
Adebayo, O. C., Nkoy, A. B., Lambertus, P. v. d. H., Labarque, V., Levtchenko, E., Delanaye, P., & Pottel, H. (2022). Glomerular Hyperfiltration: Part 2—clinical Significance in Children. Pediatric Nephrology, 38(8), 2529-2547. https://doi.org/10.1007/s00467-022-05826-5
Altamura, S., Pietropaoli, D., Lombardi, F., Pinto, R. D., & Ferri, C. (2023). An Overview of Chronic Kidney Disease Pathophysiology: The Impact of Gut Dysbiosis and Oral Disease. Biomedicines, 11(11), 3033. https://doi.org/10.3390/biomedicines11113033
Bu, J. J., Delavar, A., Dayao, J. K., Lieu, A., Chuter, B., Chen, K., Nishihara, T., Meller, L., Camp, A., Lee, J., & Baxter, S. L. (2024). Evaluation and Optimization of Diabetic Retinopathy Screenings for Uninsured Latinx Patients in a Resource-Limited Student-Run Free Clinic. Journal of Student-Run Clinics, 10(1). https://doi.org/10.59586/jsrc.v10i1.407
Cortés, M., Kallmeyer, A., Tarín, N., Cristóbal, C., Pello, A. M., Aceña, Á., Gutiérrez‐Landaluce, C., Huelmos, A., Alonso, J., López‐Bescós, L., Mahíllo, I., González‐Lorenzo, Ó., González‐Casaus, M. L., Egido, J., & Tuñón, J. (2025). Klotho Plasma Levels Are an Independent Predictorof Mortality in Women With Acute Coronary Syndrome. https://doi.org/10.21203/rs.3.rs-5676287/v1
Davis, O. M., Kore, R. A., Moore, A. M., Ware, J., Mehta, J. L., Arthur, J. M., Lynch, D., & Jain, N. (2023). Platelet Count and Platelet Volume in Patients With CKD. Journal of the American Society of Nephrology, 34(11), 1772-1775. https://doi.org/10.1681/asn.0000000000000220
Echefu, G., Stowe, I., Burka, S., Basu‐Ray, I., & Kumbala, D. (2023). Pathophysiological Concepts and Screening of Cardiovascular Disease in Dialysis Patients. Frontiers in Nephrology, 3. https://doi.org/10.3389/fneph.2023.1198560
Ferdinand, K. C., Norris, K. C., Rodbard, H. W., & Trujillo, J. (2023). Humanistic and Economic Burden of Patients With Cardiorenal Metabolic Conditions: A Systematic Review. Diabetes Therapy, 14(12), 1979-1996. https://doi.org/10.1007/s13300-023-01464-8
Ferro, C. J., Wanner, C., Luyckx, V. A., Stevens, K., Cerqueira, S. A., Darwish, R. A., Fernandez, B., Fiel, D., Filev, R., Grieger, M., Lopez, A., Luman, M., Małyszko, J., Nikolova‐Vlahova, M., Romero, F., Skalioti, C., Araújo, C., Ziediņa, I., Gallego, D., . . . Vanholder, R. (2025). ABCDE to Identify and Prevent Chronic Kidney Disease: A Call to Action. Nephrology Dialysis Transplantation, 40(9), 1786-1798. https://doi.org/10.1093/ndt/gfaf057
Gevaert, A. B., Mueller, S., Winzer, E. B., Duvinage, A., Caroline, M. V. D. H., Pieske‐Kraigher, E., Beckers, P., Edelmann, F., Wisløff, U., Pieske, B., Adams, V., Halle, M., & Craenenbroeck, E. M. V. (2022). Iron Deficiency Impacts Diastolic Function, Aerobic Exercise Capacity, and Patient Phenotyping in Heart Failure With Preserved Ejection Fraction: A Subanalysis of the OptimEx-Clin Study. Frontiers in Physiology, 12. https://doi.org/10.3389/fphys.2021.757268
Giudice, I. D., Starza, I. D., & Foà, R. (2021). Does MRD Have a Role in the Management of iNHL? Hematology, 2021(1), 320-330. https://doi.org/10.1182/hematology.2021000312
Inaba, M., & Mori, K. (2021). Extension of Healthy Life Span of Dialysis Patients in the Era of a 100-Year Life. https://doi.org/10.3390/books978-3-0365-2345-3
Jicman, D., Tatu, A. L., Lescai, A.-M., Popazu, C., Vlad, A., & Baltă, A. A. Ș. (2025). Psychological Distress and Kidney Failure as Predictors of Chemoradiotherapy Toxicity and Quality of Life in Patients With Head and Neck Cancer. Healthcare, 13(12), 1476. https://doi.org/10.3390/healthcare13121476
Kakumoto, A. (2024). Prognostic Impact of Tumor-Associated Neutrophils in Breast Cancer. International Journal of Clinical and Experimental Pathology, 17(3), 51-62. https://doi.org/10.62347/jqdq1527
Komaba, H., & Fukagawa, M. (2021). Jury Still Out on Whether FGF23 Is a Direct Contributor, a Useful Biomarker, or Neither. Kidney International, 100(5), 989-993. https://doi.org/10.1016/j.kint.2021.04.045
Lavery, J. P., Jones, I., & Sankaranarayanan, R. (2022). Cardiorenal Metabolic Syndrome: Reaching a Consensus in Shared Care. British Journal of Cardiac Nursing, 17(7), 1-12. https://doi.org/10.12968/bjca.2022.0055
Lloret, M. J., Fusaro, M., Jørgensen, H. S., Haarhaus, M., Gifre, L., Alfieri, C., Massó, E., D’Marco, L., Evenepoel, P., & Bover, J. (2024). Evaluating Osteoporosis in Chronic Kidney Disease: Both Bone Quantity and Quality Matter. Journal of clinical medicine, 13(4), 1010. https://doi.org/10.3390/jcm13041010
Luyckx, V. A., Tuttle, K. R., Abdellatif, D., Correa‐Rotter, R., Fung, W. W., Haris, A., Hsiao, L.-L., Khalife, M., Kumaraswami, L., Loud, F., Raghavan, V., Roumeliotis, S., Sierra, M., Ulasi, I., Wang, B., Lui, S. F., Liakopoulos, V., & Balducci, A. (2024). Mind the Gap in Kidney Care: Translating What We Know Into What We Do. Nephrology and Dialysis, 26(1), 9-22. https://doi.org/10.28996/2618-9801-2024-1-9-22
Mathur, V., Bushinsky, D. A., Inker, L. A., Klaerner, G., Li, E., Parsell, D., Perkovic, V., Stasiv, Y., Walker, M., Wesson, D. E., Wheeler, D. C., & Tangri, N. (2022). Design and Population of the VALOR-CKD Study: A Multicenter, Randomized, Double-Blind, Placebo-Controlled Trial Evaluating the Efficacy and Safety of Veverimer in Slowing Progression of Chronic Kidney Disease in Patients With Metabolic Acidosis. Nephrology Dialysis Transplantation, 38(6), 1448-1458. https://doi.org/10.1093/ndt/gfac289
Mori, T., Yano, T., Yoshioka, K., & Miyazaki, Y. (2023). Pre-Stroke Loop Diuretics and Anemia in Elderly Patients Were Associated With Severe Renal Dysfunction at the Onset of Acute Stroke. https://doi.org/10.1101/2023.07.10.23292484
Pöhlmann, J., Bergenheim, K., Sánchez, J. J. G., Rao, N., Briggs, A., & Pollock, R. F. (2022). Modeling Chronic Kidney Disease in Type 2 Diabetes Mellitus: A Systematic Literature Review of Models, Data Sources, and Derivation Cohorts. Diabetes Therapy, 13(4), 651-677. https://doi.org/10.1007/s13300-022-01208-0
Shen, Y., Chen, Y., Huang, S., Yao, X., Kanwar, Y. S., & Zhan, M. (2022). The Association Between Symptoms of Depression and Anxiety, Quality of Life, and Diabetic Kidney Disease Among Chinese Adults: A Cross-Sectional Study. International journal of environmental research and public health, 20(1), 475. https://doi.org/10.3390/ijerph20010475
Shrestha, S., Haq, K., Malhotra, D., & Patel, D. (2024). Care of Adults With Advanced Chronic Kidney Disease. Journal of clinical medicine, 13(15), 4378. https://doi.org/10.3390/jcm13154378
Singh, N., Faye, A. S., Abidi, M. Z., Grant, S. J., DuMontier, C., Iyer, A., Jain, N., Kochar, B., Lieber, S. B., Litke, R., Loewenthal, J., Masters, M. C., Nanna, M. G., Robison, R., Sattui, S. E., Sheshadri, A., Shi, S., Sherman, A. N., Walston, J., . . . Orkaby, A. R. (2024). Frailty Integration in Medical Specialties: Current Evidence and Suggested Strategies From The Clin‐STAR Frailty Interest Group. Journal of the American Geriatrics Society, 73(4), 1029-1040. https://doi.org/10.1111/jgs.19268
Streja, E., Norris, K. C., Budoff, M. J., Hashemi, L., Akbilgiç, O., & Kalantar‐Zadeh, K. (2021). The Quest for Cardiovascular Disease Risk Prediction Models in Patients With Nondialysis Chronic Kidney Disease. Current Opinion in Nephrology & Hypertension, 30(1), 38-46. https://doi.org/10.1097/mnh.0000000000000672
Toal, M., Fergie, R., Quinn, M., Hill, C., O’Neill, C., & Maxwell, A. P. (2025). Systematic Review of the Application of the Kidney Failure Risk Equation and Oxford Classification in Estimating Prognosis in IgA Nephropathy. Systematic Reviews, 14(1). https://doi.org/10.1186/s13643-024-02739-2
Yin, T., Chen, Y., Yuan, H., Zeng, X., & Fu, P. (2022). Relationship Between Modifiable Lifestyle Factors and Chronic Kidney Disease: A Bibliometric Analysis of Top-Cited Publications From 2011 to 2020. BMC Nephrology, 23(1). https://doi.org/10.1186/s12882-022-02745-3
Yoshida, S., Shiraishi, R., Nakayama, Y., & Taira, Y. (2023). Can Nutrition Contribute to a Reduction in Sarcopenia, Frailty, and Comorbidities in a Super-Aged Society? https://doi.org/10.20944/preprints202306.2123.v1
Zhu, M., Tang, L., Yang, W., Xu, Y., Che, X., Zhou, Y., Shao, X., Zhou, W., Zhang, M., Li, G., Zheng, M., Wang, Q., Li, H., & Mou, S. (2022). Predicting Progression of Kidney Injury Based on Elastography Ultrasound and Radiomics Signatures. Diagnostics, 12(11), 2678. https://doi.org/10.3390/diagnostics12112678
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Marcela Guardado (Author); Nazanin Nouri
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
