Browse Articles

In this study, three models are used to test the hypothesis that data-centric artificial intelligence (AI) will improve the performance of machine learning.

In this study, the authors ask whether a Tau immunotherapy treatment, Hsp70 protein treatment, or dual treatment approach of both the Tau imunotherapy treatment and Hsp70 protein treatment leads to a greater reduction in Tau protein concentration in Alzheimer's disease. Overall, they conclude that the effectiveness of the treatment ultimately relies on the stage of Alzheimer’s.

In this study, the authors hypothesized that the unique redox properties of cobalt oxide (Co₃O₄), combined with the conductive nature of the nickel foam (NF) substrate, synergistically enhances the catalytic performance for furfural oxidation. The study showed successful synthesis of Co₃O₄ nanoflowers directly grown on NF and tested their capacity to serve as a highly efficient electrocatalyst for furfural oxidation. Beyond furfural oxidation, this study also offers broader implications for sustainable chemistry by establishing design principles for efficient nucleophilic oxidation reaction catalysts, demonstrating an energy-saving alternative to conventional oxygen evolution reaction-coupled processes, and showcasing how biomass conversion can be integrated with renewable energy systems.

This study explored how green spaces, climate, traffic, and air quality (GCTA) collectively influence asthma-related emergency department visits in the U.S using machine learning models and explainable AI.

The authors looked at different factors, such as age, pre-existing conditions, and geographic region, and their ability to predict what an individual's health insurance premium would be.

Here, recognizing that brain aneurysms pose a severe threat, often misdiagnosed and leading to high mortality, particularly in younger individuals, the authors explored a novel computer-aided engineering approach. They used magnetic resonance angiography images and computational fluid dynamics, to improve aneurysm detection and risk assessment, aiming for more personalized treatment.

The authors looked at different models of semantic segmentation to determine which may be best used in the future for segmentation of CT scans to help diagnose certain conditions.

The authors looked at using machine learning to identify skills needed to apply for certain jobs, specifically looking at different techniques to parse apart the text. They found that Bidirectional Encoder Representation of Transforms (BERT) performed best.

Here the authors sought to use three machine learning models to predict poverty levels in Cambodia based on available household data. They found teat multilayer perceptron outperformed the other models, with an accuracy of 87 %. They suggest that data-driven approaches such as these could be used more effectively target and alleviate poverty.

Poor air quality is associated with negative effects on human health but can be difficult to measure in an accurate and cost-effective manner. The authors design and test a monitor for measuring indoor air quality using low-cost components.