Dataset Information

Detection of Synergistic Interaction on an Additive Scale Between Two Drugs on Abnormal Elevation of Serum Alanine Aminotransferase Using Machine-Learning Algorithms.

ABSTRACT: Drug-induced liver injury (DILI) is a common adverse drug reaction, with abnormal elevation of serum alanine aminotransferase (ALT). Several clinical studies have investigated whether a combination of two drugs alters the reporting frequency of DILI using traditional statistical methods such as multiple logistic regression (MLR), but this model may over-fit the data. This study aimed to detect a synergistic interaction between two drugs on the risk of abnormal elevation of serum ALT in Japanese adult patients using three machine-learning algorithms: MLR, logistic least absolute shrinkage and selection operator (LASSO) regression, and extreme gradient boosting (XGBoost) algorithms. A total of 58,413 patients were extracted from Nihon University School of Medicine's Clinical Data Warehouse and assigned to case (N = 4,152) and control (N = 54,261) groups. The MLR model over-fitted a training set. In the logistic LASSO regression model, three combinations showed relative excess risk due to interaction (RERI) for abnormal elevation of serum ALT: diclofenac and famotidine (RERI 2.427, 95% bootstrap confidence interval 1.226-11.003), acetaminophen and ambroxol (0.540, 0.087-4.625), and aspirin and cilostazol (0.188, 0.135-3.010). Moreover, diclofenac (adjusted odds ratio 1.319, 95% bootstrap confidence interval 1.189-2.821) and famotidine (1.643, 1.332-2.071) individually affected the risk of abnormal elevation of serum ALT. In the XGBoost model, not only the individual effects of diclofenac (feature importance 0.004) and famotidine (0.016), but also the interaction term (0.004) was included in important predictors. Although further study is needed, the combination of diclofenac and famotidine appears to increase the risk of abnormal elevation of serum ALT in the real world.

SUBMITTER: Akimoto H

PROVIDER: S-EPMC9298751 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAcetaminophen (APAP) is the most common cause liver injury following alcohol in US patients. Predicting liver injury and subsequent hepatic regeneration in patients taking therapeutic doses of APAP may be possible using new 'omic methods such as metabolomics and genomics. Multi'omic techniques increase our ability to find new mechanisms of injury and regeneration.MethodsWe used metabolomic and genomic data from a randomized controlled trial of patients administered 4 g of APAP per day for 14 days or longer with blood samples obtained at 0 (baseline), 4, 7, 10, 13 and 16 days. We used the highest ALT as the clinical outcome to be predicted in our integrated analysis. We used penalized regression to model the relationship between genetic variants and day 0 metabolite level, and then performed a metabolite-wide colocalization scan to associate the genetically regulated component of metabolite expression with ALT elevation. Genome-wide association study (GWAS) analyses were conducted for ALT elevation and metabolite level using linear regression, with age, sex, and the first five principal components included as covariates. Colocalization was tested via a weighted sum test.ResultsOut of the 164 metabolites modeled, 120 met the criteria for predictive accuracy and were retained for genetic analyses. After genomic examination, eight metabolites were found to be under genetic control and predictive of ALT elevation due to therapeutic acetaminophen. The metabolites were: 3-oxalomalate, allantoate, diphosphate, L-carnitine, L-proline, maltose, and ornithine. These genes are important in the tricarboxylic acid cycle (TCA), urea breakdown pathway, glutathione production, mitochondrial energy production, and maltose metabolism.ConclusionsThis multi'omic approach can be used to integrate metabolomic and genomic data allowing identification of genes that control downstream metabolites. These findings confirm prior work that have identified mitochondrial energy production as critical to APAP induced liver injury and have confirmed our prior work that demonstrate the importance of the urea cycle in therapeutic APAP liver injury.

Dataset Information

Detection of Synergistic Interaction on an Additive Scale Between Two Drugs on Abnormal Elevation of Serum Alanine Aminotransferase Using Machine-Learning Algorithms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets