Department of Nephrology, West China Hospital, Sichuan University, No. 37, Guoxue alley, Chengdu, Sichuan Zipcode:610000, China.
Department of Nephrology, West China Hospital, Sichuan University, No. 37, Guoxue alley, Chengdu, Sichuan Zipcode:610000, China.
Int Immunopharmacol. 2022 Sep;110:108966. doi: 10.1016/j.intimp.2022.108966. Epub 2022 Jun 25.
Lupus nephritis (LN) is a major organ complication and cause of morbidity and mortality in patients with systemic lupus erythematosus. This study aims to provide the clinician with a quantitative tool for the prediction of the individual remission probability of LN and obtain new insights for improved clinical management in LN treatment.
A total of 301 patients with renal biopsy-proven LN were recruited and randomly divided into model construction and validation group. The least absolute shrinkage and selection operator regression analysis was conducted to select significant variables, and a multivariate Cox regression predictive model was established. The performance of the model was verified and tested with 1000-bootstrap validation in the validation group. Finally, the nomogram was constructed, and the performance was evaluated. The predictive accuracy and efficiency were verified through receiver operation characteristic and calibration curves.
A total of 210 and 91 patients who all received renal biopsy were included in the training and validation group, respectively. A final prognostic model was established, which included the course of LN, gender, 24h-proteinuria, creatinine, triglycerides, FIB, Complement C3, anti-dsDNA antibody, tubular atrophy and classification of kidney biopsy. Moreover, an easy-to-use nomogram was built based on the predictive model. The areas under the curve (AUC) of the 1, 2, 5-year prediction were 77.12, 77.98 and 87.01 in the training group, respectively. In the validation group, the AUC of the 1, 2, 5-year prediction were 81.42, 87.20 and 92.81 respectively, which indicated good performance in predicting the remission probability of LN.
This novel model was constructed to predict the remission probability of patients with LN for the first time. This model displayed good predictive performance and was easy to use for clinical practice.
狼疮肾炎（LN）是系统性红斑狼疮患者的主要器官并发症和发病率及死亡率的原因。本研究旨在为临床医生提供一种预测 LN 个体缓解概率的定量工具，并为 LN 治疗的临床管理提供新的见解。
共纳入 301 例经肾活检证实的 LN 患者，并随机分为模型构建和验证组。采用最小绝对收缩和选择算子回归分析选择显著变量，并建立多变量 Cox 回归预测模型。在验证组中进行 1000 次自举验证以验证和测试模型的性能。最后构建列线图，并评估其性能。通过接受者操作特征和校准曲线验证预测准确性和效率。
共有 210 例和 91 例患者均接受了肾活检，分别纳入训练组和验证组。建立了最终的预后模型，其中包括 LN 病程、性别、24 小时蛋白尿、肌酐、甘油三酯、纤维蛋白原、补体 C3、抗双链 DNA 抗体、肾小管萎缩和肾活检分类。此外，基于预测模型构建了一个易于使用的列线图。在训练组中，1、2、5 年预测的曲线下面积（AUC）分别为 77.12、77.98 和 87.01。在验证组中，1、2、5 年预测的 AUC 分别为 81.42、87.20 和 92.81，表明该模型在预测 LN 缓解概率方面具有良好的性能。
这是首次构建预测 LN 患者缓解概率的新型模型。该模型具有良好的预测性能，易于在临床实践中使用。
