Predicting Progression of Chronic Kidney Disease in Sickle Cell Anemia Using Machine Learning Models (PREMIER)

摘要 镰状细胞病 (SCD) 的特点是影响多个终末器官的血管病变，并伴有并发症 包括慢性肾脏病（CKD）。蛋白尿是肾小球损伤的早期指标，常见于 SCD 并预测进行性肾脏疾病。 SCD 患者的肾功能下降速度比正常人更快 一般非裔美国人。 SCD 快速下降的发生率是正常人的 3 倍 一般人群。此外，高风险 APOL1 变异与以下风险增加相关： SCD 中的蛋白尿和 CKD 进展。肾脏疾病，无论严重程度如何，eGFR 快速下降 与 SCD 死亡率增加有关。因此，早期识别有进展风险的患者 CKD 的研究对于解决潜在的可改变的危险因素、减缓 eGFR 下降和降低死亡率非常重要。 尽管 CKD 患病率很高且导致发病率和死亡率增加，但可 SCD 相关肾脏疾病的治疗方法仍然有限。虽然血管紧张素转换酶抑制剂 （ACE-I）、血管紧张素受体阻滞剂（ARB）和羟基脲在短期研究中可减少白蛋白尿， 它们在预防或减缓 SCD 肾功能进行性丧失方面的益处仍不清楚。 我们最近报道，机器学习 (ML) 模型可以识别快速衰退的高风险患者 在肾功能方面。此外，较高的血红蛋白浓度也是血红蛋白下降的独立预测因素。 肾功能快速下降的可能性。血管内溶血对病理生理学的贡献 SCD 相关肾小球病，voxelotor，一种改变镰状血红蛋白氧亲和力的小分子 提高镰状红细胞存活率，可能减少肾小球损伤并减缓个体 CKD 的进展 与SCD。 在此应用中，我们建议进行一项前瞻性多中心研究，以构建基于机器学习的预测模型 患有 SCD 的成人 CKD 进展模型。此外，在预计有快速患病风险的个体中 肾功能下降，基于持续性白蛋白尿的存在（尿液 ACR ≥ 100 mg/g），我们将 评估 voxelotor 对蛋白尿、肾功能快速下降和 CKD 进展的影响。 随着对 SCD 病理生理学及其并发症的认识不断进步，结合 批准的药物疗法数量不断增加，及早识别有进展性肾病风险的患者 疾病和随后增加的死亡风险对于改变已知的危险因素、启动有针对性的 治疗并可能延长预期寿命。此外，已知溶血性贫血对 SCD 相关肾小球病和进行性肾病的发病机制，减少药物 溶血可能有助于预防和/或减缓肾病的进展 患者群体。

ABSTRACT Sickle cell disease (SCD) is characterized by a vasculopathy affecting multiple end organs, with complications including chronic kidney disease (CKD). Albuminuria, an early measure of glomerular injury, is common in SCD and predicts progressive kidney disease. Kidney function decline is faster in SCD patients than in the general African American population. The prevalence of rapid decline in SCD is 3-fold higher than in the general population. Furthermore, high-risk APOL1 variants are associated with an increased risk of albuminuria and progression of CKD in SCD. Kidney disease, regardless of severity, and rapid eGFR decline are associated with increased mortality in SCD. As such, early identification of patients at risk for progression of CKD is important to address potentially modifiable risk factors, slow eGFR decline and reduce mortality. Despite the high prevalence of CKD and its contribution to increased morbidity and mortality, available treatments for SCD-related kidney disease remain limited. Although angiotensin converting enzyme inhibitors (ACE-I), angiotensin receptor blockers (ARBs), and hydroxyurea decrease albuminuria in short-term studies, their benefits in preventing or slowing progressive loss of kidney function in SCD remain undefined. We have recently reported that machine learning (ML) models can identify patients at high risk for rapid decline in kidney function. Further, higher hemoglobin concentration is also an independent predictor of decreased odds of rapid kidney function decline. With the contribution of intravascular hemolysis to the pathophysiology of SCD-related glomerulopathy, voxelotor, a small molecule which modifies sickle hemoglobin oxygen affinity and improves sickle RBC survival, may decrease glomerular injury and slow the progression of CKD in individuals with SCD. In this application, we propose the conduct of a prospective, multicenter study to build a ML-based predictive model for progression of CKD in adults with SCD. Furthermore, in individuals predicted to be at risk for rapid decline in kidney function, based on the presence of persistent albuminuria (urine ACR ≥ 100 mg/g), we will evaluate the effect of voxelotor on albuminuria, rapid decline in kidney function and progression of CKD. With advances in the understanding of the pathophysiology of SCD and its complications, combined with an increasing number of approved drug therapies, early identification of patients at risk for progressive kidney disease and subsequent increased risk of death is necessary to modify known risk factors, initiate targeted therapies and possibly increase life expectancy. Further, with the known contribution of hemolytic anemia to the pathogenesis of SCD-related glomerulopathy and progressive kidney disease, drugs that decrease hemolysis are likely to be beneficial in preventing and/or slowing the progression of kidney disease in this patient population.