Browse Articles

Over the last few decades, childhood stunting has persisted as a major global challenge. This study hypothesized that TPTO (Tree-based Pipeline Optimization Tool), an AutoML (automated machine learning) tool, would outperform all pre-existing machine learning models and reveal the positive impact of economic prosperity, strong familial traits, and resource attainability on reducing stunting risk. Feature correlation plots revealed that maternal height, wealth indicators, and parental education were universally important features for determining stunting outcomes approximately two years after birth. These results help inform future research by highlighting how demographic, familial, and socio-economic conditions influence stunting and providing medical professionals with a deployable risk assessment tool for predicting childhood stunting.

Uveal melanoma (UM) is a rare subtype of melanoma but the most frequent primary cancer of the eye in adults. The goal of this study was to research the genetic causes of UM through a comprehensive frequency analysis of base-pair mismatches in patient genomes. Results showed a total of 130 genetic mutations, including seven recurrent mutations, with most mutations occurring in chromosomes 3 and X. Recurrent mutations varied from 8.7% to 17.39% occurrence in the UM patient sample, with all mutations identified as missense. These findings suggest that UM is a recessive heterogeneous disease with selective homozygous mutations. Notably, this study has potential wider significance because the seven genes targeted by recurrent mutations are also involved in other cancers.

In this study, the authors investigate the demographic indicators for voter shift between the 2016 and 2020 presidential elections based on demographic data put through a K-nearest neighbors classification algorithm and Principal Component Analysis.

While remarkable in its ability to mirror human cognition, machine learning and its associated algorithms often require extensive data to prove effective in completing tasks. However, data is not always plentiful, with unpredictable events occurring throughout our daily lives that require flexibility by artificial intelligence utilized in technology such as personal assistants and self-driving vehicles. Driven by the need for AI to complete tasks without extensive training, the researchers in this article use fluid intelligence assessments to develop an algorithm capable of generalization and abstraction. By forgoing prioritization on skill-based training, this article demonstrates the potential of focusing on a more generalized cognitive ability for artificial intelligence, proving more flexible and thus human-like in solving unique tasks than skill-focused algorithms.

Here the authors investigated the role of agricultural fertilizers as potential contributors to greenhouse gas emissions. In contrast to the typical investigations that consider microbiological processes, the authors considered purely chemical processes. Based on their results they found that as much as 20.41% of all CO₂ emission from land-based activities could be a result of mineral nitrogen fertilizers.

Here, seeking to develop more efficient solar cells, the authors investigated photo-electrochemical (PEC) solar cells, specifically molybdenum diselenide (MoSe₂) based on its high resistance to corrosion. They found that the percentage efficiency of these PEC solar cells was proportional to light intensity^–0.9 and that performance was positively influenced by increasing the electrolyte volume. They suggest that studies such as these can lead to new insight into reaction-based solar cells.

Regenerative medicine has become a mainstay in recent times, and employing stem cells to treat several degenerative, inflammatory conditions has resulted in very promising outcomes. These forms of cell-based therapies are novel approaches to existing treatment modalities. In this study, the authors compared the concentrations of the cytokines PDGF, IL-8, and VEGF between conditioned and spent media of mesenchymal stem cells (MSCs) to evaluate their potential therapeutic properties for wound healing in inflammatory conditions. They hypothesized that conditioned media contains higher concentrations of wound healing cytokines compared to spent media. The authors found that while IL-8 and VEGF were present in highest concentrations in conditioned media, PDGF was present in maximal amounts in spent media.

Cell segmentation is the task of identifying cell nuclei instances in fluorescence microscopy images. The goal of this paper is to benchmark the performance of representative deep learning techniques for cell nuclei segmentation using standard datasets and common evaluation criteria. This research establishes an important baseline for cell nuclei segmentation, enabling researchers to continually refine and deploy neural models for real-world clinical applications.

Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

In this study, the authors test ways to increase knowledge of green consumerism amongst high school students. Their knowledge was measured based on the New Ecological Paradigm Scale.