Browse Articles

As AI becomes more integrated into healthcare, public trust in AI-developed treatment plans remains a concern, especially for emotionally charged health decisions. In a study of 81 community college students, AI-created treatment plans received lower trust ratings compared to physician-developed plans, supporting the hypothesis. The study found no significant differences in AI trust levels across demographic factors, suggesting overall skepticism toward AI-driven healthcare.

Breast cancer is the most common cancer in women, with approximately 300,000 diagnosed with breast cancer in 2023. It ranks second in cancer-related deaths for women, after lung cancer with nearly 50,000 deaths. Scientists have identified important genetic mutations in genes like BRCA1 and BRCA2 that lead to the development of breast cancer, but previous studies were limited as they focused on specific populations. To overcome limitations, diverse populations and powerful statistical methods like genome-wide association studies and whole-genome sequencing are needed. Explainable artificial intelligence (XAI) can be used in oncology and breast cancer research to overcome these limitations of specificity as it can analyze datasets of diagnosed patients by providing interpretable explanations for identified patterns and predictions. This project aims to achieve technological and medicinal goals by using advanced algorithms to identify breast cancer subtypes for faster diagnoses. Multiple methods were utilized to develop an efficient algorithm. We hypothesized that an XAI approach would be best as it can assign scores to genes, specifically with a 90% success rate. To test that, we ran multiple trials utilizing XAI methods through the identification of class-specific and patient-specific key genes. We found that the study demonstrated a pipeline that combines multiple XAI techniques to identify potential biomarker genes for breast cancer with a 95% success rate.

Human immunodeficiency virus (HIV), which affects tens of millions of individuals worldwide, can lead to acquired immunodeficiency syndrome (AIDS). While there is currently no cure for HIV, the development of small molecule antiretroviral agents has greatly improved the prognosis of infected individuals, especially in developed countries. Here, the authors employ homology modeling and molecular docking towards the identification of novel rilpivirine analogs that retain high binding affinity to clinically relevant rilpivirine-resistant mutations of the HIV reverse transcriptase enzyme.

This study explores how to predict and minimize distortion in 3D printed parts, particularly when using affordable PLA filament. The researchers developed a model using a gradient boosting regressor trained on 3D printing data, aiming to predict the necessary CAD dimensions to counteract print distortion.

Pediatric cancers pose unique challenges due to their rarity and distinct biological factors, emphasizing the need for accurate survival prediction to guide treatment. This study integrated generative AI and machine learning, including synthetic data, to analyze 9,184 pediatric cancer patients, identifying age at diagnosis, cancer types, and anatomical sites as significant survival predictors. The findings highlight the potential of AI-driven approaches to improve survival prediction and inform personalized treatment strategies, with broader implications for innovative healthcare 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.

Here the authors aimed to find the best preservative combinations to stop bacterial growth in food, using data modeling and biochemical experiments. They discovered that single preservatives are often not enough, with varying effectiveness against different bacteria, and suggest future research into combining preservatives for better results.

Here the authors aimed to compare the effects of artificial Allura Red AC dye and natural cochineal dye on the growth of Escherichia coli and Bacillus coagulans bacteria. Their research found that only Allura Red AC dye significantly affected bacterial growth, specifically amplifying E. coli growth. Based on their results, they suggest that Allura Red AC dye may increase the growth of E. coli bacteria within the human gut.

Here the authors aimed to understand factors influencing adolescent fentanyl exposure, hypothesizing a positive association between social media usage, socioeconomic factors, and fentanyl abuse among U.S. teens. Their analysis of the Monitoring the Future dataset revealed that a history of suspension and use of marijuana or alcohol were linked to higher fentanyl use, and while not statistically significant, a notable positive correlation between social media use and fentanyl frequency was observed.

This study aimed to determine whether artificial sweeteners are harmful to the human microbiome by investigating two different bacteria found to be advantageous to the human gut, Escherichia coli and Bacillus coagulans. Results showed dramatic reduction in bacterial growth for agar plates containing two artificial sweeteners in comparison to two natural sweeteners. This led to the conclusion that both artificial sweeteners inhibit the growth of the two bacteria and warrants further study to determine if zero-sugar sweeteners may be worse for the human gut than natural sugar itself.