Urinary chemical fingerprint left behind by repeated NSAID administration: Discovery of putative biomarkers using artificial intelligence

Abstract

Prediction and early detection of kidney damage induced by nonsteroidal anti-inflammatories (NSAIDs) would provide the best chances of maximizing the anti-inflammatory effects while minimizing the risk of kidney damage. Unfortunately, biomarkers for detecting NSAIDinduced kidney damage in cats remain to be discovered. To identify potential urinary biomarkers for monitoring NSAID-based treatments, we applied an untargeted metabolomics approach to urine collected from cats treated repeatedly with meloxicam or saline for up to 17 days. Applying multivariate analysis, this study identified a panel of seven metabolites that discriminate meloxicam treated from saline treated cats. Combining artificial intelligence machine learning algorithms and an independent testing urinary metabolome data set from cats with meloxicam-induced kidney damage, a panel of metabolites was identified and validated. The panel of metabolites including tryptophan, tyrosine, taurine, threonic acid, pseudouridine, xylitol and lyxitol, successfully distinguish meloxicam-treated and saline-treated cats with up to 75-100% sensitivity and specificity. This panel of urinary metabolites may prove a useful and non-invasive diagnostic tool for monitoring potential NSAID induced kidney injury in feline patients and may act as the framework for identifying urine biomarkers of NSAID induced injury in other species.

Applying metabolomics to veterinary pharmacology and therapeutics

“…ROC‐curve biomarker analysis is generally considered the best method for developing and assessing the performance of medical diagnostic tests (Xia et al, 2013). In order to minimize the likelihood of capturing irrelevant substances, the selection of potential biomarkers can be rigorously scrutinized by applying a combination of statistical tests such as the receiver operating characteristic curve, random forest, and PLS‐DA analyses (Broughton‐Neiswanger et al, 2020; Rivera‐Velez, Broughton‐Neiswanger, Suarez, Pinñyro, et al, 2019, Rivera‐Velez, Broughton‐Neiswanger, Suarez, Slovak, et al, 2019).…”

“…There are multiple validations models which are shown in Figure 3. The external validation method requires partitioning the data into a training set used to build a model, and a validation set used to assess the predictive ability of the model, where the validation set is in no way used to generate the trained model (Broughton‐Neiswanger et al, 2020; Chan et al, 2011; Worley, & Powers, 2013). This validation method should only be applied if enough individuals are available to build a reliable model (Triba et al, 2015).…”

“…Machine learning algorithms can integrate large datasets such as blood parameters, dietary habits, anthropometrics, physical activity metabolomics, and microbiome data to individualize phenotypes. These learned patterns are applied to test data sets of interest to make outcome predictions (Broughton‐Neiswanger et al, 2020; Zeevi et al, 2015). Machine learning algorithms used for the classification of data include Random Forest (Broughton‐Neiswanger et al, 2020), and the Support Vector Machine.…”

“…4 | ARTIFIand microbiome data to individualize phenotypes. These learned patterns are applied to test data sets of interest to make outcome predictions(Broughton-Neiswanger et al, 2020;Zeevi et al, 2015). Machine learning algorithms used for the classification of data include Random Forest(Broughton-Neiswanger et al, 2020), and the Support Vector Machine (Xia & Wishart, 2016)…”

Pharmacometabolomics with a combination of PLS‐DA and random forest algorithm analyses reveal meloxicam alters feline plasma metabolite profiles

“…If this is the case, some of the organic acids identified in this study could serve as biomarkers for monitoring nepphrotoxicity of meloxicam in cats. A recently published companion manuscript showed that changes in serum creatinine took 9 days to become elevated following meloxicam administration (Broughton‐Neiswanger et al., 2020). By comparison, the panel of metabolites described here distinguished meloxicam‐treated cats from saline‐treated control cats after 2 days of meloxicam administration in the testing data set of cats.…”