Division of Nephrology, Department of Internal Medicine, The Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China; Department of Biomedical Engineering, South China University of Technology, Guangzhou, China.
Am J Kidney Dis. 2013 Dec;62(6):1109-15. doi: 10.1053/j.ajkd.2013.07.010. Epub 2013 Sep 5.
Accurate estimation of glomerular filtration rate (GFR) is important in clinical practice. Current models derived from regression are limited by the imprecision of GFR estimates. We hypothesized that an artificial neural network (ANN) might improve the precision of GFR estimates.
A study of diagnostic test accuracy.
SETTING & PARTICIPANTS: 1,230 patients with chronic kidney disease were enrolled, including the development cohort (n=581), internal validation cohort (n=278), and external validation cohort (n=371).
Estimated GFR (eGFR) using a new ANN model and a new regression model using age, sex, and standardized serum creatinine level derived in the development and internal validation cohort, and the CKD-EPI (Chronic Kidney Disease Epidemiology Collaboration) 2009 creatinine equation.
Measured GFR (mGFR).
GFR was measured using a diethylenetriaminepentaacetic acid renal dynamic imaging method. Serum creatinine was measured with an enzymatic method traceable to isotope-dilution mass spectrometry.
In the external validation cohort, mean mGFR was 49±27 (SD) mL/min/1.73 m2 and biases (median difference between mGFR and eGFR) for the CKD-EPI, new regression, and new ANN models were 0.4, 1.5, and -0.5 mL/min/1.73 m2, respectively (P<0.001 and P=0.02 compared to CKD-EPI and P<0.001 comparing the new regression and ANN models). Precisions (IQRs for the difference) were 22.6, 14.9, and 15.6 mL/min/1.73 m2, respectively (P<0.001 for both compared to CKD-EPI and P<0.001 comparing the new ANN and new regression models). Accuracies (proportions of eGFRs not deviating >30% from mGFR) were 50.9%, 77.4%, and 78.7%, respectively (P<0.001 for both compared to CKD-EPI and P=0.5 comparing the new ANN and new regression models).
Different methods for measuring GFR were a source of systematic bias in comparisons of new models to CKD-EPI, and both the derivation and validation cohorts consisted of a group of patients who were referred to the same institution.
An ANN model using 3 variables did not perform better than a new regression model. Whether ANN can improve GFR estimation using more variables requires further investigation.
准确估计肾小球滤过率（GFR）在临床实践中很重要。目前基于回归的模型受到 GFR 估计不精确的限制。我们假设人工神经网络（ANN）可能会提高 GFR 估计的精度。
诊断测试准确性的研究。
共纳入 1230 例慢性肾脏病患者，包括发展队列（n=581）、内部验证队列（n=278）和外部验证队列（n=371）。
使用新的 ANN 模型和在发展和内部验证队列中得出的新回归模型（基于年龄、性别和标准化血清肌酐水平）以及慢性肾脏病流行病学合作组（CKD-EPI）2009 肌酐方程估计的 eGFR（eGFR）。
测量的 GFR（mGFR）。
使用二乙三胺五乙酸肾动态成像法测量 GFR。使用酶法测量血清肌酐，该方法可溯源至同位素稀释质谱法。
在外部验证队列中，平均 mGFR 为 49±27（SD）mL/min/1.73 m2，CKD-EPI、新回归和新 ANN 模型的偏倚（mGFR 与 eGFR 之间的中位数差异）分别为 0.4、1.5 和-0.5 mL/min/1.73 m2（P<0.001 和 P=0.02 与 CKD-EPI 相比，P<0.001 与新回归和 ANN 模型相比）。精度（差异的 IQR）分别为 22.6、14.9 和 15.6 mL/min/1.73 m2（与 CKD-EPI 相比均 P<0.001，与新 ANN 和新回归模型相比均 P<0.001）。准确性（eGFR 不偏离 mGFR>30%的比例）分别为 50.9%、77.4%和 78.7%（与 CKD-EPI 相比均 P<0.001，与新 ANN 和新回归模型相比均 P=0.5）。
用于测量 GFR 的不同方法是新模型与 CKD-EPI 比较中系统偏差的一个来源，并且推导和验证队列都由一组被转介到同一机构的患者组成。
使用 3 个变量的 ANN 模型并未优于新回归模型。ANN 是否可以使用更多变量来改善 GFR 估计，还需要进一步研究。
