{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T07:31:51Z","timestamp":1775547111773,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004242","name":"Princess Nourah bint Abdulrahman University","doi-asserted-by":"publisher","award":["PNURSP2025R721"],"award-info":[{"award-number":["PNURSP2025R721"]}],"id":[{"id":"10.13039\/501100004242","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Aim: Nephrotic syndrome (NS) represents a complex glomerular disorder with significant clinical heterogeneity across pediatric and adult populations. Although glucocorticosteroids have constituted the mainstay of therapeutic intervention for more than six decades, primary treatment resistance manifests in approximately 20% of pediatric patients and 50% of adult cohorts. Steroid-resistant nephrotic syndrome (SRNS) is associated with substantially greater morbidity compared to steroid-sensitive nephrotic syndrome (SSNS), characterized by both iatrogenic glucocorticoid toxicity and progressive nephron loss with attendant decline in renal function. Based on this, the current study aims to develop a robust machine learning (ML) model integrated with explainable artificial intelligence (XAI) to distinguish SRNS and identify important biomarker candidate metabolites. Methods: In the study, biomarker candidate compounds obtained from proton nuclear magnetic resonance (1 H NMR) metabolomics analyses on plasma samples taken from 41 patients with NS (27 SSNS and 14 SRNS) were used. We developed ML models to predict steroid resistance in pediatric NS using metabolomic data. After preprocessing with MICE-LightGBM imputation for missing values (&lt;30%) and standardization, the dataset was randomly split into training (80%) and testing (20%) sets, repeated 100 times for robust evaluation. Four supervised algorithms (XGBoost, LightGBM, AdaBoost, and Random Forest) were trained and evaluated using AUC, sensitivity, specificity, F1-score, accuracy, and Brier score. XAI methods including SHAP (for global feature importance and model interpretability) and LIME (for individual patient-level explanations) were applied to identify key metabolomic biomarkers and ensure clinical transparency of predictions. Results: Among four ML algorithms evaluated, Random Forest demonstrated superior performance with the highest accuracy (0.87 \u00b1 0.12), sensitivity (0.90 \u00b1 0.18), AUC (0.92 \u00b1 0.09), and lowest Brier score (0.20 \u00b1 0.03), followed by LightGBM, AdaBoost, and XGBoost. The superiority of the Random Forest model was confirmed by paired t-tests, which revealed significantly higher AUC and lower Brier scores compared to all other algorithms (p &lt; 0.05). SHAP analysis identified key metabolomic biomarkers consistently across all models, including glucose, creatine, 1-methylhistidine, homocysteine, and acetone. Low glucose and creatine levels were positively associated with steroid resistance risk, while higher propylene glycol and carnitine concentrations increased SRNS probability. LIME analysis provided patient-specific interpretability, confirming these metabolomic patterns at individual level. The XAI approach successfully identified clinically relevant metabolomic signatures for predicting steroid resistance with high accuracy and interpretability. Conclusions: The present study successfully identified candidate metabolomic biomarkers capable of predicting SRNS prior to treatment initiation and elucidating critical molecular mechanisms underlying steroid resistance regulation.<\/jats:p>","DOI":"10.3390\/ph18111659","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:47:58Z","timestamp":1762177678000},"page":"1659","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Machine Learning-Integrated Explainable Artificial Intelligence Approach for Predicting Steroid Resistance in Pediatric Nephrotic Syndrome: A Metabolomic Biomarker Discovery Study"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9848-7958","authenticated-orcid":false,"given":"Fatma Hilal","family":"Yagin","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Faculty of Medicine, Malatya Turgut Ozal University, 44280 Malatya, T\u00fcrkiye"},{"name":"Department of Computer Science, Lakehead University, Thunder Bay, ON P7B 5E1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1453-0937","authenticated-orcid":false,"given":"Feyza","family":"Inceoglu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Faculty of Medicine, Malatya Turgut Ozal University, 44280 Malatya, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5406-098X","authenticated-orcid":false,"given":"Cemil","family":"Colak","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Medical Informatics, Faculty of Medicine, Inonu University, 44280 Malatya, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7273-4041","authenticated-orcid":false,"given":"Amal K.","family":"Alkhalifa","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah A.","family":"Alzakari","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5735-3825","authenticated-orcid":false,"given":"Mohammadreza","family":"Aghaei","sequence":"additional","affiliation":[{"name":"Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology (NTNU), 6002 Alesund, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1592\/phco.23.8.1021.32885","article-title":"Management of nephrotic syndrome in children","volume":"23","author":"Robinson","year":"2003","journal-title":"Pharmacother. J. Hum. Pharmacol. Drug Ther."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"502","DOI":"10.2215\/CJN.05960616","article-title":"Focal segmental glomerulosclerosis","volume":"12","author":"Rosenberg","year":"2017","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/S0140-6736(03)14184-0","article-title":"Nephrotic syndrome in childhood","volume":"362","author":"Eddy","year":"2003","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"65","DOI":"10.9734\/ijmpcr\/2024\/v17i2378","article-title":"Insights into Nephrotic Syndrome in Pediarics: Case Series Analysis","volume":"17","author":"Sireesha","year":"2024","journal-title":"Int. J. Med. Pharm. Case Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1111\/j.1442-200x.2004.01920.x","article-title":"Primary nephrotic syndrome during childhood in Turkey","volume":"46","author":"Ekim","year":"2004","journal-title":"Pediatr. Int."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/s00467-017-3838-6","article-title":"Genetic testing in steroid-resistant nephrotic syndrome: Why, who, when and how?","volume":"34","author":"Preston","year":"2017","journal-title":"Pediatr. Nephrol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"319","DOI":"10.2174\/1381612826666201102104412","article-title":"Steroid-resistant nephrotic syndrome in children: A mini-review on genetic mechanisms, predictive biomarkers and pharmacotherapy strategies","volume":"27","author":"Guo","year":"2021","journal-title":"Curr. Pharm. Des."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s00467-021-04983-3","article-title":"Update on the treatment of steroid-sensitive nephrotic syndrome","volume":"37","author":"Zotta","year":"2022","journal-title":"Pediatr. Nephrol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.19082\/2039","article-title":"Immunosuppressive therapy in children with steroid-resistant, frequently-relapsing, and steroid-dependent idiopathic nephrotic syndrome: A single center experience","volume":"8","author":"Moustafa","year":"2016","journal-title":"Electron. Physician"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"105189","DOI":"10.1016\/j.phrs.2020.105189","article-title":"Why do some asthma patients respond poorly to glucocorticoid therapy?","volume":"160","author":"Henderson","year":"2020","journal-title":"Pharmacol. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"76","DOI":"10.3121\/cmr.2024.1917","article-title":"Clinicopathological pattern of renal biopsies in children with nephrotic syndrome","volume":"22","author":"Kumar","year":"2024","journal-title":"Clin. Med. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.2215\/CJN.05260610","article-title":"Clinical utility of genetic testing in children and adults with steroid-resistant nephrotic syndrome","volume":"6","author":"Bullich","year":"2011","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1038\/nrm.2016.25","article-title":"Metabolomics: Beyond biomarkers and towards mechanisms","volume":"17","author":"Johnson","year":"2016","journal-title":"Nat. Rev. Mol. Cell Biol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cca.2013.03.033","article-title":"Metabolomics in chronic kidney disease","volume":"422","author":"Zhao","year":"2013","journal-title":"Clin. Chim. Acta"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1002\/med.21883","article-title":"Metabolomics as a tool for the early diagnosis and prognosis of diabetic kidney disease","volume":"42","author":"Pereira","year":"2022","journal-title":"Med. Res. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Emwas, A.-H., Roy, R., McKay, R.T., Tenori, L., Saccenti, E., Gowda, G.N., Raftery, D., Alahmari, F., Jaremko, L., and Jaremko, M. (2019). NMR spectroscopy for metabolomics research. Metabolites, 9.","DOI":"10.3390\/metabo9070123"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e14746","DOI":"10.1111\/ijcp.14746","article-title":"Multi-parameter-based radiological diagnosis of Chiari Malformation using Machine Learning Technology","volume":"75","author":"Tetik","year":"2021","journal-title":"Int. J. Clin. Pract."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yagin, F.H., Colak, C., Algarni, A., Gormez, Y., Guldogan, E., and Ardig\u00f2, L.P. (2024). Hybrid explainable artificial intelligence models for targeted metabolomics analysis of diabetic retinopathy. Diagnostics, 14.","DOI":"10.3390\/diagnostics14131364"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liebal, U.W., Phan, A.N., Sudhakar, M., Raman, K., and Blank, L.M. (2020). Machine learning applications for mass spectrometry-based metabolomics. Metabolites, 10.","DOI":"10.3390\/metabo10060243"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Galal, A., Talal, M., and Moustafa, A. (2022). Applications of machine learning in metabolomics: Disease modeling and classification. Front. Genet., 13.","DOI":"10.3389\/fgene.2022.1017340"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"100829","DOI":"10.1016\/j.ajogmf.2022.100829","article-title":"Integrated metabolomics and machine learning approach to predict hypertensive disorders of pregnancy","volume":"5","author":"Varghese","year":"2023","journal-title":"Am. J. Obstet. Gynecol. MFM"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Elguoshy, A., Zedan, H., and Saito, S. (2025). Machine learning-driven insights in cancer metabolomics: From subtyping to biomarker discovery and prognostic modeling. Metabolites, 15.","DOI":"10.3390\/metabo15080514"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"ref_26","first-page":"4766","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9919269","DOI":"10.1155\/2023\/9919269","article-title":"Interpretability of clinical decision support systems based on artificial intelligence from technological and medical perspective: A systematic review","volume":"2023","author":"Xu","year":"2023","journal-title":"J. Healthc. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.ekir.2019.09.010","article-title":"Predicting and defining steroid resistance in pediatric nephrotic syndrome using plasma metabolomics","volume":"5","author":"Gooding","year":"2020","journal-title":"Kidney Int. Rep."},{"key":"ref_29","first-page":"367","article-title":"Metabolic Imbalance of Homocysteine and Hydrogen Sulfide in Kidney Disease","volume":"25","author":"Karmin","year":"2017","journal-title":"Curr. Med. Chem."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1016\/j.celrep.2019.04.012","article-title":"Anaerobic Glycolysis Maintains the Glomerular Filtration Barrier Independent of Mitochondrial Metabolism and Dynamics","volume":"27","author":"Brinkkoetter","year":"2019","journal-title":"Cell Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1159\/000110876","article-title":"Mechanisms of Homocysteine-Induced Glomerular Injury and Sclerosis","volume":"28","author":"Yi","year":"2007","journal-title":"Am. J. Nephrol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.1140\/epjs\/s11734-024-01308-x","article-title":"Searches for the BSM scenarios at the LHC using decision tree-based machine learning algorithms: A comparative study and review of random forest, AdaBoost, XGBoost and LightGBM frameworks","volume":"233","author":"Choudhury","year":"2024","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"6937","DOI":"10.1007\/s13042-025-02654-5","article-title":"Comparative analysis of CatBoost, LightGBM, XGBoost, RF, and DT methods optimised with PSO to estimate the number of k-barriers for intrusion detection in wireless sensor networks","volume":"16","author":"Ileri","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Colak, C., Yagin, F.H., Algarni, A., Algarni, A., Al-Hashem, F., and Ardig\u00f2, L.P. (2025). Proposed Comprehensive Methodology Integrated with Explainable Artificial Intelligence for Prediction of Possible Biomarkers in Metabolomics Panel of Plasma Samples for Breast Cancer Detection. Medicina, 61.","DOI":"10.3390\/medicina61040581"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4053","DOI":"10.1007\/s00521-024-10724-y","article-title":"Explainable AI in action: A comparative analysis of hypertension risk factors using SHAP and LIME","volume":"37","author":"Donmez","year":"2025","journal-title":"Neural Comput. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e70056","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development","volume":"17","author":"Schmitt","year":"2024","journal-title":"Clin. Transl. Sci."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1016\/j.bbe.2022.06.007","article-title":"Diagnosis of Parkinson\u2019s disease based on SHAP value feature selection","volume":"42","author":"Liu","year":"2022","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Rao, S., Mehta, S., Kulkarni, S., Dalvi, H., Katre, N., and Narvekar, M. (2022, January 8\u201310). A study of LIME and SHAP model explainers for autonomous disease predictions. Proceedings of the 2022 IEEE Bombay Section Signature Conference (IBSSC), Mumbai, India.","DOI":"10.1109\/IBSSC56953.2022.10037324"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, T.V., Venkataiah, C., Rao, Y.M., Prasad, D.R., Chowdary, K.U., Jayamma, M., and Sireesha, R. (2024). A novel NASNet model with LIME explanability for lung disease classification. Biomed. Signal Process. Control, 93.","DOI":"10.1016\/j.bspc.2024.106114"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Reddy, K.A., Rahman, S.Z., Rao, B.M., Hussain, M.A., Sirisha, C., and Puligadda, M. (2025). Explainable AI in parkinson\u2019s disease detection: Leveraging lime for transparent model interpretation and improvement. Int. J. Syst. Assur. Eng. Manag., 1\u201312.","DOI":"10.1007\/s13198-025-02966-3"}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/18\/11\/1659\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T14:06:33Z","timestamp":1762178793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/18\/11\/1659"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"references-count":40,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["ph18111659"],"URL":"https:\/\/doi.org\/10.3390\/ph18111659","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]}}}