A machine learning-based predictive tool for complete renal response in lupus nephritis leverages the 3-month treatment milestone
- 1Department of Rheumatology and Clinical Immunology, Peking University First Hospital, Beijing, China
- 2Beijing Key Laboratory of Precision Diagnosis and Treatment for Major Rheumatic and Immune Diseases, Beijing, China
Abstract
Lupus nephritis (LN) remains a major determinant of poor prognosis in systemic lupus erythematosus, yet reliable tools for early identification of unfavorable renal outcomes are lacking. This study aimed to identify early prognostic factors for complete renal response (CRR) at 12 months in active LN and to develop interpretable machine learning (ML) models for early prediction of treatment response. In this prospective cohort of 400 active LN patients followed for 12 months, the primary outcome was 12-month CRR. Candidate predictors were assessed at baseline and 3-month follow-up. Four ML models (Random Forest, Support Vector Machine, Elastic Net, and eXtreme Gradient Boosting) were developed and validated on a test set. Model performance was evaluated using area under the ROC curve (AUC), calibration and decision curve analyses, with feature importance assessed via SHapley Additive exPlanations (SHAP). 296 patients (74%) achieved CRR at 12 months. Baseline factors independently associated with CRR included 24-hour urinary total protein (24hUTP), higher serum albumin, shorter disease duration, and treatment-naïve status. Significant group differences emerged at 3 months across multiple parameters (all p < 0.05). Baseline‑only models showed limited discriminative ability (AUC ≤ 0.75), whereas incorporating 3-month data markedly improved performance; the Random Forest model achieved the best testing-set AUC (0.862, 95% CI: 0.775–0.949). SHAP analysis identified 3-month 24hUTP reduction as the most influential predictor of CRR. We developed an interpretable ML tool that accurately predicts 12-month CRR as early as 3 months post-treatment, highlighting the critical role of early proteinuria reduction as a key indicator for long-term renal outcomes.
Related
- Antimalarial Pharmacotherapy Gaps in Nigerian Children Under Five: A Predictive Machine Learning Analysis of Care-Seeking, Testing, and ACT Treatment Using NDHS 2023-24
- Additional B‐Lymphocyte Stimulator Inhibitors Treatment Facilitated Glucocorticoid Withdrawal in Lupus Nephritis Patients: A Real‐World Retrospective Observational Single‐Center Cohort Study
- Antihypertensive Pharmacotherapy Gaps in Nigeria: A Predictive Machine Learning Analysis of Treatment Uptake Amid Macroeconomic Shock, Using NDHS 2023-24
- Grading of intrarenal tertiary lymphoid structure-like aggregates and association with early treatment response in proliferative lupus nephritis
- Interpretable biomarker programs predict treatment response in lupus nephritis: patient-level validation across four regimens
BibTeX
@article{song2026machine,
title = {{A machine learning-based predictive tool for complete renal response in lupus nephritis leverages the 3-month treatment milestone}},
author = {Shan Song and Yong Fan and Xiaohui Zhang and Juntao Cheng and Dai Gao and Jiaying Zhang and Tingting Ding and Lanlan Ji and Zhuoli Zhang},
journal = {Renal Failure},
year = {2026},
month = nov,
doi = {10.1080/0886022x.2026.2751782},
url = {https://doi.org/10.1080/0886022x.2026.2751782},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - A machine learning-based predictive tool for complete renal response in lupus nephritis leverages the 3-month treatment milestone
AU - Shan Song
AU - Yong Fan
AU - Xiaohui Zhang
AU - Juntao Cheng
AU - Dai Gao
AU - Jiaying Zhang
AU - Tingting Ding
AU - Lanlan Ji
AU - Zhuoli Zhang
PY - 2026
DA - 2026/11/11
JO - Renal Failure
DO - 10.1080/0886022x.2026.2751782
UR - https://doi.org/10.1080/0886022x.2026.2751782
AB - Lupus nephritis (LN) remains a major determinant of poor prognosis in systemic lupus erythematosus, yet reliable tools for early identification of unfavorable renal outcomes are lacking. This study aimed to identify early prognostic factors for complete renal response (CRR) at 12 months in active LN and to develop interpretable machine learning (ML) models for early prediction of treatment response. In this prospective cohort of 400 active LN patients followed for 12 months, the primary outcome was 12-month CRR. Candidate predictors were assessed at baseline and 3-month follow-up. Four ML models (Random Forest, Support Vector Machine, Elastic Net, and eXtreme Gradient Boosting) were developed and validated on a test set. Model performance was evaluated using area under the ROC curve (AUC), calibration and decision curve analyses, with feature importance assessed via SHapley Additive exPlanations (SHAP). 296 patients (74%) achieved CRR at 12 months. Baseline factors independently associated with CRR included 24-hour urinary total protein (24hUTP), higher serum albumin, shorter disease duration, and treatment-naïve status. Significant group differences emerged at 3 months across multiple parameters (all p < 0.05). Baseline‑only models showed limited discriminative ability (AUC ≤ 0.75), whereas incorporating 3-month data markedly improved performance; the Random Forest model achieved the best testing-set AUC (0.862, 95% CI: 0.775–0.949). SHAP analysis identified 3-month 24hUTP reduction as the most influential predictor of CRR. We developed an interpretable ML tool that accurately predicts 12-month CRR as early as 3 months post-treatment, highlighting the critical role of early proteinuria reduction as a key indicator for long-term renal outcomes.
SN - 0886-022X
SN - 1525-6049
ER -