Browse Articles

The authors explore how diversity in data sets contributes to bias in artificial intelligence.

Concerns regarding the rapid spread of Sars-CoV2 in early 2020 led company and local governmental officials in many states to ask people to work from home and avoid leaving their homes; measures commonly referred to as shutdowns. Here, the authors investigate how shutdowns affected carbon monoxide (CO) levels in 15 US states using publicly available data. Their results suggest that CO levels decreased as a result of these measures over the course of 2020, a trend which started to reverse after shutdowns ended.

Previously established data indicate that cemeteries have contributed to groundwater and soil pollution, as embalming fluids can impact the microbiomes that exist in decomposing remains. In this study, Caputo et al hypothesized that microbial variation would be high between cemeteries from different eras due to dissimilarities between embalming techniques employed, and furthermore, that specific microbes would act as an indication for certain contaminants. Overall, they found that there is a variation in the microbiomes of the different eras’ cemeteries according to the concentrations of the phyla and their more specific taxa.

Coronary heart disease (CHD) is the leading cause of death in the U.S., responsible for nearly 700,000 deaths in 2021, and is marked by artery clogging that can lead to heart attacks. Traditional prediction methods require expensive clinical tests, but a new study explores using machine learning on demographic, clinical, and behavioral survey data to predict CHD.

The authors look at using publicly available data and machine learning to see if they can develop a criminal activity index for counties within the state of California.

With advancements in machine learning a large data scale, high throughput virtual screening has become a more attractive method for screening drug candidates. This study compared the accuracy of molecular descriptors from two cheminformatics Mordred and PaDEL, software libraries, in characterizing the chemo-structural composition of 53 compounds from the non-nucleoside reverse transcriptase inhibitors (NNRTI) class. The classification model built with the filtered set of descriptors from Mordred was superior to the model using PaDEL descriptors. This approach can accelerate the identification of hit compounds and improve the efficiency of the drug discovery pipeline.

Machine learning algorithms are becoming increasingly popular for data crunching across a vast area of scientific disciplines. Here, the authors compare two machine learning algorithms with respect to accuracy and user-friendliness and find that random forest algorithms outperform logistic regression when applied to the same dataset.

This study explores the factors that influence coffee quality ratings using data from the Coffee Quality Institute. Through a regression model based on gradient descent, the authors aimed to predict coffee ratings (total cup points) and hypothesized that sweetness and the coffee producer would be the most influential factors.

The authors use machine learning to analyze electroencephalogram data and identify slowing patterns that can indicate undetected disorders like epilepsy or dementia

It can be challenging for the general public to understand data on medical risk. Weseley-Jones and Mordechai tackle this issue by conducting a survey to assess people's skill and comfort with understanding medical risk information in percentage and frequency formats.