Neural Network-Based Calculator for Rat Glomerular Filtration Rate

Abstract

Glomerular filtration is a pivotal process of renal physiology, and its alterations are a central pathological event in acute kidney injury and chronic kidney disease. Creatinine clearance (ClCr), a standard method for glomerular filtration rate (GFR) measurement, requires a long and tedious procedure of timed (usually 24 h) urine collection. We have developed a neural network (NN)-based calculator of rat ClCr from plasma creatinine (pCr) and body weight. For this purpose, matched pCr, weight, and ClCr trios from our historical records on male Wistar rats were used. When evaluated on the training (1165 trios), validation (389), and test sets (660), the model committed an average prediction error of 0.196, 0.178, and 0.203 mL/min and had a correlation coefficient of 0.863, 0.902, and 0.856, respectively. More importantly, for all datasets, the NN seemed especially effective at comparing ClCr among groups within individual experiments, providing results that were often more congruent than those measured experimentally. ACLARA, a friendly interface for this calculator, has been made publicly available to ease and expedite experimental procedures and to enhance animal welfare in alignment with the 3Rs principles by avoiding unnecessary stressing metabolic caging for individual urine collection.

Keywords: calculator; creatinine clearance; machine learning; neural network; rat glomerular filtration rate.

Figure 1

Summary of the datasets used for model development and field testing. Data trios were composed of matched pCr, ClCr, and body weight data.

Figure 2

Comparison of the measured ClCr and estimated ClCr, corresponding to four exemplifying actual experiments using data from the training and validation sets. ClCr, creatinine clearance. CORR, Pearson product-moment correlation coefficient. MAE, mean average error.

Figure 3

Comparison of the measured ClCr and estimated ClCr, corresponding to four exemplifying actual experiments, using data from the test set. ClCr, creatinine clearance. CORR, Pearson product-moment correlation coefficient. MAE, mean average error.

Figure 4

Prediction error analysis. Prediction error box plots according to the rat’s body weight range (top) and the mClCr range (bottom). Error bars represent the 2.5th and 97.5th percentiles. A scatter plot of prediction errors is also shown superimposed.