Neural Network-Based Calculator for Rat Glomerular Filtration Rate.

Óscar J Pellicer-Valero,María Paniagua-Sancho,Alfredo G Casanova,José D Martín-Guerrero,Francisco J López-Hernández,Giampiero A Massaro,Carlos Martínez-Salgado,Mykola Harvat,Isabel Fuentes-Calvo

doi:10.3390/biomedicines10030610

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.

Highlights

In this study we developed and experimentally validated a neural network-based calculator of ClCr for rats from a single analyte and body weight data, useful in both healthy and disease conditions
1554 data trios of measured ClCr, plasma creatinine (pCr), and body weight were collected from the historical records of our laboratory
Once the final model was obtained, it was used for model training, and the remaining 25% (389) was used for validation, which was utilized for making design decisions was field-tested against a third dataset with 660 data trios from rats and

Summary

Introduction

Alterations in GFR are a hallmark of many renal ailments, including acute kidney injury (AKI) [1] and chronic kidney disease (CKD) [2,3], and a gold standard diagnostic parameter [4–6]. Methods to measure GFR are based on the clearance of specific probe molecules from the blood. These must be cleared solely by renal excretion, not metabolized, freely filtered at the glomerulus, or secreted or reabsorbed by the tubule, and must not interfere with the GFR [7,8]. Different exogenous molecules with these characteristics have 4.0/).

Methods

Results

Discussion

Conclusion