Department of Rheumatology, Ren Ji Hospital, Shanghai Jiaotong University School of Medicine, Shanghai.
Kidney Disease Center, First Affiliated Hospital, Zhejiang University School of Medicine.
Rheumatology (Oxford). 2022 Jul 6;61(7):2886-2893. doi: 10.1093/rheumatology/keab818.
To develop a short-term renal outcome prediction model for acute kidney injury (AKI) in patients with LN.
Two lupus AKI cohorts from two independent centres during 2013-2019 were included: a derivation cohort from a rheumatology centre and a validation cohort from a nephrology centre. Clinical characteristics and renal histologic features were obtained. The outcome measurement was the recovery of kidney function within 12 months. Lasso regression was used for feature selection. Prediction models with or without pathology were built and a nomogram was plotted. Model evaluation including calibration curve and decision curve analysis was performed.
A total of 130 patients were included in the derivation cohort and 96 patients in the validation cohort, of which 82 and 73 patients received a renal biopsy, respectively. The prognostic nomogram model without pathology included determinants of SLE duration, days from AKI onset to treatment and baseline creatinine level [C-index 0.85 (95% CI 0.78, 0.91) and 0.79 (95% CI 0.70, 0.88) for the two cohorts]. A combination of histologic tubulointerstitial (TI) fibrosis in the nomogram gave an incremental predictive performance (C-index 0.93 vs 0.85; P = 0.039) in the derivation cohort but failed to improve the performance in the validation cohort (C-index 0.81 vs 0.79; P = 0.78). Decision curve analysis suggested clinical benefit of the prediction models.
The predictive nomogram models might facilitate more accurate management for lupus patients with AKI.
为狼疮性肾炎（LN）患者的急性肾损伤（AKI）建立短期肾结局预测模型。
纳入了 2013 年至 2019 年两个独立中心的两个狼疮 AKI 队列：一个来自风湿病中心的队列和一个来自肾脏病中心的队列。获取了临床特征和肾脏组织学特征。结局测量是 12 个月内肾功能的恢复情况。使用套索回归进行特征选择。建立了有和没有病理学的预测模型，并绘制了诺模图。进行了模型评估，包括校准曲线和决策曲线分析。
共纳入了 130 例来自推导队列的患者和 96 例来自验证队列的患者，其中分别有 82 例和 73 例患者接受了肾活检。无病理学的预后诺模图模型包括 SLE 持续时间、AKI 发病到治疗的天数和基线肌酐水平的决定因素[两个队列的 C 指数分别为 0.85（95%CI 0.78，0.91）和 0.79（95%CI 0.70，0.88）]。在诺模图中加入组织学肾小管间质（TI）纤维化可提高预测性能（推导队列的 C 指数为 0.93 与 0.85 相比，P=0.039；验证队列的 C 指数为 0.81 与 0.79 相比，P=0.78）。决策曲线分析表明预测模型具有临床获益。
预测诺模图模型可能有助于更准确地管理狼疮性 AKI 患者。
