基于生物标志物和电子患者数据的机器学习风险评分的推导和验证，以预测糖尿病肾脏疾病的进展。
Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease.
机构信息
Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Renalytix AI Plc, Cardiff, UK.
出版信息
Diabetologia. 2021 Jul;64(7):1504-1515. doi: 10.1007/s00125-021-05444-0. Epub 2021 Apr 2.
AIM
Predicting progression in diabetic kidney disease (DKD) is critical to improving outcomes. We sought to develop/validate a machine-learned, prognostic risk score (KidneyIntelX™) combining electronic health records (EHR) and biomarkers.
METHODS
This is an observational cohort study of patients with prevalent DKD/banked plasma from two EHR-linked biobanks. A random forest model was trained, and performance (AUC, positive and negative predictive values [PPV/NPV], and net reclassification index [NRI]) was compared with that of a clinical model and Kidney Disease: Improving Global Outcomes (KDIGO) categories for predicting a composite outcome of eGFR decline of ≥5 ml/min per year, ≥40% sustained decline, or kidney failure within 5 years.
RESULTS
In 1146 patients, the median age was 63 years, 51% were female, the baseline eGFR was 54 ml min [1.73 m], the urine albumin to creatinine ratio (uACR) was 6.9 mg/mmol, follow-up was 4.3 years and 21% had the composite endpoint. On cross-validation in derivation (n = 686), KidneyIntelX had an AUC of 0.77 (95% CI 0.74, 0.79). In validation (n = 460), the AUC was 0.77 (95% CI 0.76, 0.79). By comparison, the AUC for the clinical model was 0.62 (95% CI 0.61, 0.63) in derivation and 0.61 (95% CI 0.60, 0.63) in validation. Using derivation cut-offs, KidneyIntelX stratified 46%, 37% and 17% of the validation cohort into low-, intermediate- and high-risk groups for the composite kidney endpoint, respectively. The PPV for progressive decline in kidney function in the high-risk group was 61% for KidneyIntelX vs 40% for the highest risk strata by KDIGO categorisation (p < 0.001). Only 10% of those scored as low risk by KidneyIntelX experienced progression (i.e., NPV of 90%). The NRI for the high-risk group was 41% (p < 0.05).
CONCLUSIONS
KidneyIntelX improved prediction of kidney outcomes over KDIGO and clinical models in individuals with early stages of DKD.
目的
预测糖尿病肾病（DKD）的进展对于改善预后至关重要。我们旨在开发/验证一种基于机器学习的、结合电子健康记录（EHR）和生物标志物的预后风险评分（KidneyIntelX™）。
方法
这是一项观察性队列研究，纳入了来自两个 EHR 相关生物库的患有现患 DKD/储存血浆的患者。训练了一个随机森林模型，并比较了该模型与临床模型和肾脏病预后质量倡议（KDIGO）分类在预测 5 年内 eGFR 下降≥5 ml/min/1.73m2、持续下降≥40%或肾衰竭的复合终点方面的表现（AUC、阳性和阴性预测值[PPV/NPV]和净重新分类指数[NRI]）。
结果
在 1146 名患者中，中位年龄为 63 岁，51%为女性，基线 eGFR 为 54 ml/min[1.73m]，尿白蛋白与肌酐比值（uACR）为 6.9mg/mmol，随访时间为 4.3 年，21%发生了复合终点事件。在推导中的交叉验证（n=686）中，KidneyIntelX 的 AUC 为 0.77（95%CI 0.74，0.79）。在验证中（n=460），AUC 为 0.77（95%CI 0.76，0.79）。相比之下，临床模型的 AUC 在推导中为 0.62（95%CI 0.61，0.63），在验证中为 0.61（95%CI 0.60，0.63）。使用推导中的截断值，KidneyIntelX 将验证队列的 46%、37%和 17%分别分层为低、中、高危组，用于复合肾脏终点。在高危组中，肾功能进行性下降的阳性预测值（PPV）为 61%，而 KDIGO 分类的最高风险分层为 40%（p<0.001）。仅有 10%的低危组患者发生进展（即，KidneyIntelX 的阴性预测值为 90%）。高危组的 NRI 为 41%（p<0.05）。
结论
在患有早期 DKD 的个体中，KidneyIntelX 改善了 KDIGO 和临床模型对肾脏结局的预测。
Zotero 插件