A Machine Learning Algorithm for Quantitatively Diagnosing Oxidative Stress Risks in Healthy Adult Individuals Based on Health Space Methodology: A Proof-of-Concept Study Using Korean Cross-Sectional Cohort Data

Blood Microbiota Profile Is Associated with the Responsiveness of Postprandial Lipemia to Platycodi radix Beverage: A Randomized Controlled Trial in Healthy Subjects

Prolonged postprandial hyperlipidemia may cause the development of cardiovascular diseases. This study explored whether postprandial triglyceride-rich lipoprotein (TRL) clearance responsiveness to Platycodi radix beverage (PR) is associated with changes in blood microbiota profiles. We conducted an 8-week randomized controlled clinical trial involving normolipidemic adults with low fruit and vegetable intakes. Participants underwent an oral fat tolerance test and 16S amplicon sequencing analysis of blood microbiota. Using the Qualitative Interaction Trees, we identified responders as those with higher baseline dietary fat intake (>38.5 g/day) and lipoprotein lipase levels (>150.6 ng/mL), who showed significant reductions in AUC for triglyceride (TG) and chylomicron-TG after the oral fat tolerance test. The LEfSe analysis showed differentially abundant blood microbiota between responders and non-responders. A penalized logistic regression algorithm was employed to predict the responsiveness to intervention on the TRL clearance based on the background characteristics, including the blood microbiome. Our findings suggest that PR intake can modulate postprandial TRL clearance in adults consuming higher fat intake over 38.5 g/day and low fruit and vegetable intake through shared links to systemic microbial signatures.

Artificial intelligence approaches to the biochemistry of oxidative stress: Current state of the art

Artificial intelligence (AI) and machine learning models are today frequently used for classification and prediction of various biochemical processes and phenomena. In recent years, numerous research efforts have been focused on developing such models for assessment, categorization, and prediction of oxidative stress. Supervised machine learning can successfully automate the process of evaluation and quantification of oxidative damage in biological samples, as well as extract useful data from the abundance of experimental results. In this concise review, we cover the possible applications of neural networks, decision trees and regression analysis as three common strategies in machine learning. We also review recent works on the various weaknesses and limitations of artificial intelligence in biochemistry and related scientific areas. Finally, we discuss future innovative approaches on the ways how AI can contribute to the automation of oxidative stress measurement and diagnosis of diseases associated with oxidative damage.