Machine learning and cell imaging combine to predict effectiveness of multiple sclerosis medication

Brazilian researchers, in partnership with French institutions, have developed a tool that can predict how patients will respond to natalizumab, one of the most commonly used drugs for treating ...

AI system for rapid annotation of medical images could accelerate clinical research

Annotating regions of interest in medical images, a process known as segmentation, is often one of the first steps clinical ...
IEEE

Rainfall Classification Using Machine Learning Algorithms on Data Mining Platforms

Abstract: Weather conditions directly affect sectors such as agriculture and transport. With climate change, unpredictability is increasing and traditional calculation methods may not be sufficient.

MachineLearningLM Equips Large Models with a 'Machine Learning Engine' for Context Learning

Despite large language models (LLMs) possessing extensive world knowledge and strong reasoning capabilities, they are widely regarded as excellent few-shot learners; however, they still exhibit ...
C&EN

Quantifying Aviation-Related Contributions to Ambient Ultrafine Particle Number Concentrations Using Interpretable Machine Learning

Department of Environmental Health, Boston University School of Public Health, 715 Albany Street, Boston, Massachusetts 02118, United States ...
IEEE

FruitCheck: Machine Learning-Based Freshness Classification for Bananas, Mangoes, and Oranges

Abstract: Ensuring fruit's freshness is vital for food safety and control. This study presents FruitCheck, a machine learning-based system for fruit freshness classification. The proponents conducted ...
Frontiers

Identifying aging-related biomarkers in adipose tissue using integrative bioinformatics and machine-learning approaches: discovery of ELN, MXD1, and FGF21 as key genes

Background: Adipose tissue plays a critical role in aging and age-related diseases. However, the specific molecular and cellular alterations associated with aging in adipose tissue remain incompletely ...
GitHub

STiL: Semi-supervised Tabular-Image Learning for Comprehensive Task-Relevant Information Exploration in Multimodal Classification (CVPR 2025)

Overall framework of STiL. STiL encodes image-tabular data using $\phi$, decomposes modality-shared and -specific information through DCC $\psi$ (a), and outputs ...
C&EN

Using Environmental Mixture Exposure-Triggered Biological Knowledge-Driven Machine Learning to Predict Early Pregnancy Loss

Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China Institute of Reproductive and Child Health, Key Laboratory of Reproductive Health, ...